Cookie Preference Centre

Your Privacy
Strictly Necessary Cookies
Performance Cookies
Functional Cookies
Targeting Cookies

Your Privacy

When you visit any web site, it may store or retrieve information on your browser, mostly in the form of cookies. This information might be about you, your preferences, your device or used to make the site work as you expect it to. The information does not usually identify you directly, but it can give you a more personalized web experience. You can choose not to allow some types of cookies. Click on the different category headings to find out more and change our default settings. However, you should know that blocking some types of cookies may impact your experience on the site and the services we are able to offer.

Strictly Necessary Cookies

These cookies are necessary for the website to function and cannot be switched off in our systems. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms. You can set your browser to block or alert you about these cookies, but some parts of the site may not work then.

Cookies used

Performance Cookies

These cookies allow us to count visits and traffic sources, so we can measure and improve the performance of our site. They help us know which pages are the most and least popular and see how visitors move around the site. All information these cookies collect is aggregated and therefore anonymous. If you do not allow these cookies, we will not know when you have visited our site.

Cookies used

Google Analytics

Functional Cookies

These cookies allow the provision of enhance functionality and personalization, such as videos and live chats. They may be set by us or by third party providers whose services we have added to our pages. If you do not allow these cookies, then some or all of these functionalities may not function properly.

Cookies used




Targeting Cookies

These cookies are set through our site by our advertising partners. They may be used by those companies to build a profile of your interests and show you relevant ads on other sites. They work by uniquely identifying your browser and device. If you do not allow these cookies, you will not experience our targeted advertising across different websites.

Cookies used


This site uses cookies and other tracking technologies to assist with navigation and your ability to provide feedback, analyse your use of our products and services, assist with our promotional and marketing efforts, and provide content from third parties


Here are some suggested Connections for you! - Log in to start networking.

Plum Voice - Blog

Page: 1 | 2 | 3

Bring Your Own Telecom: Is it Worth Doing?

The overwhelming majority of Plum customers use the telecom we provide as part of our service. After all, the whole idea behind offering managed telecom is to make voice technology easier for customers. By maintaining a system built on Tier 1 telecom provided by multiple carriers we’re also able to write 100% uptime guarantees into our SLAs.

These carriers provide us with phone numbers and network redundancy. Any call that enters our system using an 800 number under our control (i.e. a number we procure from a carrier or one that transferred to us through a RespOrg) can be routed to any geographic location, across any carrier. Sounds simple enough, right?

This situation isn’t always ideal for companies that do a lot of call transfers. The reason is that calls are held in our system for the entire length of the call, which can increase costs. Because of the way carrier billing works, we’re unable to do blind transfers out of our system.

BYOT – Bring Your Own Telecom

Occasionally, customers bring their own telecom to the table. Customers with their own SIP trunk can use that in conjunction with Plum’s voice automate products.

For a quick primer on what SIP trunking is check out our article on the subject, which also highlights many of the advantages of SIP trunking.

Companies interested in using their own telecom need to make sure that their SIP carrier’s session border controller has the ability to do SIP refers. A refer command releases a call from Plum’s IVR system and transfers the call to your system. This process enables carriers to properly track and bill both your company and Plum for usage.

Tale of the Tape


  • Ability to execute blind transfers
  • Telecom Flexibility: You have the ability to pick the telecom provider of your choice and to negotiate prices directly with them.
  • SIP transfers can transmit call metadata during call handoffs (transfers in/out)


  • Paying for telecom: Companies need to take a holistic view of the cost of telecom (usage, management, maintenance) to determine what kind of savings they would see over using Plum’s managed system.
  • Need to manage telecom backbone: This includes hardware and personnel to manage and maintain your telecom.
  • Single carrier: Relying on a single carrier creates a single point of failure in your voice channel. If something goes wrong with that carrier, your entire voice channel could suffer.  
  • BYO Telecom is not covered by Plum’s SLAs that guarantee 100% uptime.

For some companies, especially those that already have their own SIP trunks, supplying its own telecom may make sense. If the drawbacks of using your own telecom outweigh the advantages, Plum’s system is able to accommodate your company’s call volume.

To find out if your company is a good fit for BYOT with Plum, or if you have additional questions about BYO Telecom, SIP trunking, and the options available to your company for deploying Plum Voice solutions, contact one of our experts today.


Publish Date: July 26, 2018

Visa Verified: Plum Voice Secures a Listing on Visa’s Global Registry of Service Providers

Plum Voice has been at the vanguard of voice channel and IVR security for years. We pride ourselves on offering reliable cloud communications products that are compliant with some of the most desirable security standards in existence. These include PCI-DSS, HIPAA, and SOC2. As of May 2018, we can now add Visa Verified to that list as well.

What is Visa Verified?

Quite simply, Visa Verified is a program that vets the security of payments-related businesses in the Visa network. Visa compiles a list of verified vendors in its Global Registry of Service Providers, which gives businesses an up-to-date list of companies that meet Visa’s exacting security standards.

For each company on the list, Visa includes information about the type of validation they provide, the type(s) of service they offer, their operating regions, and more. This helps businesses to identify, narrow, and select vendors that meet their specific needs for a wide range of payment-related technologies.

How to get Visa Verified?

One of the major hurdles to get over in order to achieve Visa Verified status is PCI-DSS compliance. Fortunately, here at Plum Voice, our products have been PCI-DSS (Level 1) compliant for many years.

In order to qualify as a third-party Visa Verified service provider, it’s necessary to connect with a Visa Client Bank. After establishing that connection, the registration process requires third-party service providers to:

  • Describe how they handle cardholder data
  • Disclose any entities they use to support their operations (e.g., AMS, data centers, etc.)
  • Provide proof of compliance with the latest PCI-DSS standards

The partner Visa Client Bank in this process then vets the application and approves (or denies) it. Once approved, Visa adds the vendor to the Global Registry.

Extra Protection for You

Not all companies require their vendor partners to be Visa Verified, but even if your company doesn’t require it, when you partner with Plum Voice for IVR payments over the phone, you get the added protection that comes with Visa Verified. In addition to Visa, Plum Voice is listed on Mastercard’s roster of SDP Compliant Registered Service Providers.

Our platform undergoes rigorous security audits multiple times per year. The Visa Verified program simply provides additional data points and validation on our platform’s security.

At Plum, we’re proud to offer customers a wide range of security options that benefits many different industries.

For more information about our platform security, visit our Security and Compliance page.

If you have questions about how our secure voice communications products can help your company process more payments, contact us!


Publish Date: July 12, 2018

What You Need to Know about Poor Call Quality

Nowadays we take for granted how easy it is to make a phone call. We carry mini computers in our pockets that can contact any place in the world in real-time with a phone call or over the internet. Yet, with all that power we still end up with poor call quality all the time.

This is kind of ironic because it’s easier than ever to make phone calls, yet all that technology doesn’t guarantee a better calling experience.

Behind the scenes, telephony is incredibly complicated.

If you’re getting a lot of poor quality calls coming in, it’s good to know why.

Call Origins

Mobility is one the reasons why we rely on mobile phone so much. However, this same mobility can contribute to poor call quality.

Cell Phone Towers

When someone places a call on a mobile phone the first the radio in the phone does is contact their provider’s nearest phone tower. These phone towers handle tons of calls around the clock, but they only have a limited amount of bandwidth. So, once the call hits the tower, the tower determines how much bandwidth to allocate for the transfer of voice data.

Cell phone towers only have so much bandwidth to allocate so they tend to be conservative when doling it out. Video, for example, tends to be a higher priority than voice for providers. Video eats up a lot more of that finite bandwidth, too.

It seems that before anyone even begins dialing that they’re behind the 8-ball.

Audio Compression

This bandwidth decision is important because it affects how much compression is used on the audio for that call. A number of different audio codecs exist to perform this compression. One common codec is the Adaptive Multi-Rate (AMR) audio codec. This codec has several different compression rates it can use on a given call. The codec chooses the level of compression based on how much bandwidth is available from the tower handling the call.

If the tower is busy when the call is placed, the audio for that call will have more compression, which reduces the quality of the call. Also, once the compression level is established it’s set for the rest of the call. It doesn’t matter if more bandwidth becomes available during call.

Any problems that arise at this point in the phone call are near-end issues because they occur close to the point of origin.

It’s worth pointing out that calls made from landline phones (including SIP or VoIP) tend to not have these issues because they don’t face the same bandwidth challenges with respect to cell phone towers.

The In-Between

Once the tower figures out the bandwidth issue, it then connects the call to the PSTN. The call moves through the PSTN to the destination point. In the case of a Plum Voice IVR app, that would be one of our data centers.

The Destination

Our data centers are built specifically to handle high phone call volumes. We only use Tier 1 telecom to ensure that everything on our end is of the highest quality.

None of our components are wireless or rely on cell phone towers so we can ensure that incoming calls have the bandwidth necessary for clear phone calls.

If, for some reason, an issue occurred with one of our data centers that affected customer call quality then this would be considered a far-end issue because it happens far away, downstream from the origination point of the call.

Customer Considerations

If customers complain about call quality, you want to determine if this is a near- or far-end issue. An easy test would be to have callers try again from a landline. If this does not reproduce the call quality issues, then it was probably a near-end issue. Most of the time, call quality problems are near-end issues stemming from calls placed on a mobile device.

If the problem persists when calling from a landline, there may be a far-end issue. If you’ve ruled out a near-end issue and suspect a problem on our end, contact Plum support.



Publish Date: June 7, 2018

Fairly Allocate Call Transfers to Multiple Contact Centers

Juggling Multiple Call Centers

When customers call your company, you can provide a wide range of information and services with the right IVR applications. Sometimes, however, customers have complex issues that automation can’t address. When this happens, you want to make sure that you transfer your customer to the best possible person to quickly resolve their issue.

When you have multiple contact centers this job becomes even trickier. What if one of your contact centers performs better than another one, or if you’re bringing on a new call center and want to ease those agents into dealing with customer issues?

Fairly Allocating Call Transfers

What you need in this case is something that allows you to control call allocation. For example, say you already have one contact center, but your company’s growing so you need to bring a second one online.

Splitting call transfers between the two call centers 50/50 from the get-go might not be helpful for the new facility. Instead, let’s say you want to start off sending 80% of calls to your established facility, and only 20% to the new facility.

As the agents in the new facility get more familiar with your company and your customers you can gradually increase that the call transfer split to 50/50.

Plum Routes to the Rescue

The Plum Routes tool in Plum DEV was built for this exact purpose. Using Plum Routes lets you transfer calls to multiple phone numbers or SIP end points. With the Routes tool you can create groups based on the destination telephone number. Once you’ve created a group you can then choose the percentage of calls each number in that group will receive.

Routes lets you create as many groups as you want, and you can go back at any time and adjust the call allocations or add/remove phone numbers. This flexibility safeguards your company against changes – either planned or unplanned – that could have a negative impact on your customer support offerings. So, whether you’re switching between BPO contact centers, suffering from staffing shortages, or any other circumstance, Routes allows you to quickly and easily manage call transfer allocation across multiple phone numbers.

Contact one of our business development associates to learn more.



Publish Date: May 17, 2018

Making Natural Language Processing Feasible with Artificial Intelligence

In a past post, we discussed the technological and the financial challenges that go hand-in-hand with developing natural language processing (NLP) applications. While these challenges remain relevant, more recent developments mean it’s easier and less expensive to incorporate natural language processing into your voice channels.

Thanks to artificial intelligence (AI), companies can manage NLP apps more easily and for far less cost. They can do all of this by leveraging APIs for quick, easy access to AI engines. All these factors lower the entry barriers for companies interested in AI and NLP technology.

Enter AI

The big difference-maker here is artificial intelligence. Building and tuning grammars for NLP applications is one of the biggest drains on time and financial resources companies encounter with NLP. AI helps to mitigate that.

AI is able to take natural language phrases and extrapolate from them to figure out what other terms and phrases could work to accomplish the same task. The phrase collection and curation processes are much simpler, too.

Using the AI engine, you can see what input the application collects from real users. These responses can be added or removed from the algorithm the application uses to determine caller intent at your discretion. The more information you feed the AI application, the more accurate it will be.

AI Drives Down Costs

Grammar tuning is one of the most expensive aspects of creating NLP applications. AI reduces the amount of work necessary to get effective results.

Although most companies aren’t looking to dump tens of millions of dollars into NLP applications, the cost to get a good solution that actually works is a barrier for many businesses. Depending on the system, companies can expect to pay $1–2 million per year maintaining grammars for a NLP app.

This isn’t to suggest that AI-powered NLP is cheap. There are still telecom charges and the cost of accessing the AI system. However, it can be far less expensive than the old way of doing thing. AI, therefore, lowers the bar for entry into improve voice channel communications by making NLP more affordable.

APIs - The Right Building Blocks

All of this begs the question, how does a company go about taking advantage of these new developments in relation to AI and NLP? The answer is by using APIs.

APIs aren’t new. But they are the building blocks of the modern digital age in a lot of ways. Thanks to APIs, AI engines (like IBM’s Watson) are exponentially more accessible.

Benefits of NLP and AI in Voice Communications

Providing better customer experiences over the phone is one of the main reasons why companies are interested in NLP. As the first point of contact for many customers, phone menus can be frustrating and time consuming. This doesn’t bode well for customer experience.

Therefore, getting customers to the right people or self-service applications quickly is important for reducing those frustration levels. An AI-powered call-routing application provides this functionality. Instead of sitting through a laundry list of phone tree options, callers can simply say what they want to do and be directed to the right place.

Recent studies suggest that AI-powered call-routing can help reduce call duration by up to 50% and improve contact center productivity by up to 20%. These types of improvements can have a significant effect on customer satisfaction and experience.

Here at Plum, we’ve developed an AI-powered call-routing app for our communications platform. It provides companies with an NLP option for their voice channels and offers an easy, convenient point of entry for AI technology.

To learn more about AI and voice communications, check out our AI offerings.


Publish Date: February 8, 2018

Outsourcing or DIY? Find the Right IVR Development Approach

When it comes to development philosophy, businesses have a lot of different choices. And yet, it seems that no matter what a company chooses to do, development often comes down to building it yourself or paying someone else to do it.

As a company that offers development platforms, we see all kinds of development scenarios. Based on our years of experience, we can offer a few observations when it comes to development and IVR.

Outsource Everything

At one end of the spectrum, there are companies that want to outsource the entire development process. This is like handing over car keys to a newly licensed teenager. In a lot of ways, you’re giving them complete control and hoping that everything works out the way you want it to.

The upside of outsourcing is that you don’t have to put the time or energy into building and managing a particular solution. At some companies, it’s critical to recoup that time so people can focus on higher priority projects.

If the project being outsourced is, or closely integrates with a mission-critical process there can be some drawbacks to outsourcing. The biggest issue is that no one knows your business like you do.

This has the potential to create issues down the line because there is no guarantee that all changes or updates that your outsourced vendor makes will 1. be timely, or 2. reflect the needs of your business or your customers.

Now, this isn’t to say that outsourcing is a bad idea. These issues can certainly be overcome with the right relationship and enough time and effort. But if your company is one that doesn’t have the time or ability to guide a vendor through change orders, then you might want to re-consider your outsourcing strategy.

Here at Plum, we do offer professional services, and we build everything to spec. So, if you know exactly what you want we can build it for you. But our professional services are not 100% outsourced because we require input from you.

The DIY Approach

We’re talking about two different development approaches here, and the other one is ‘do it yourself’. This is like changing the oil on your car on your own instead of taking it to the dealership.

We’ve found that many of our most successful customers have taken a DIY approach. And when you think about it, this makes sense. Businesses that build their own applications are able to adapt their customer self-service applications to fit the changing needs of their business or their customers on the fly.

One of the biggest roadblocks to the DIY approach is the fact that IVR technology is so complex. Oftentimes, businesses think that it will take too much time to learn the technology. But that’s not really the story when considering Plum’s products.

For example, Plum Fuse is designed specifically to make the development process easy and more team-friendly. How does it accomplish this? We start with an intuitive, visual, drag-n-drop interface. There’s no coding necessary for most of the tasks in Fuse.

Developer resources, especially time, are precious commodities at almost every company. This is another area where Fuse helps businesses out. Your developers may need to help with the initial Fuse setup, ensuring that integrations and web services function properly, and things of that nature.

But once that initial setup is complete, there’s very little that developers have to do. One of our clients granted permission to their marketing manager and a business analyst to manage their Fuse apps. These individuals had no previous development experience.

In just a couple of hours poking around in Fuse, the marketing manager was able to update prompts, change call routing options, add pages to the application, and upload new audio.

Similarly, their business analyst was able to dig into the VoiceTrends data for their applications and identify trouble areas. VoiceTrends’ diagnostic flow feature does for IVR data analysis what Fuse’s visual editor does for IVR development: it makes it easier. The diagnostic flow is a visual representation of your call-flow data, showing how callers use your IVR applications.

Pick The Approach That’s Right For Your Company

It’s important to remember that the ‘correct’ development approach is the one that meets the needs of your business. For some that will mean outsourcing development and for others that will mean building their own applications. No matter what approach is right for you, Plum Voice has the technology to help you improve your customer self-service IVR applications.


Publish Date: November 30, 2017

IVR That Saves $5M per Month

Automation has a lot of benefits, like faster, more efficient customer service, increasing customer satisfaction, and improving customer experiences.

It can also save companies a lot of money. For some companies ‘a lot’ of money is A LOT.

See how one of Plum’s clients used IVR to take cost savings to new heights, and reaped additional benefits along the way.


Publish Date: November 16, 2017

The Limitations of Speech Rec & How to Combat Them

Automatic Speech Recognition (ASR) is pretty cool technology. Simply say something and a machine will do what you ask it to do. Usually.

When an ASR grammar is tuned properly and the call conditions are good, ASR works really well.

Unpacking that last sentence should help you understand a bit more about ASR, how it works, and how to recognize when to implement it.

Because let’s be honest, ASR provides a great customer experience, but no technology is perfect. You should be aware of some of ASRs limitations before going too crazy with it.


We’ve talked about ASR and how it relates to natural language processing, and even artificial intelligence so we don’t need to spend too much time on grammars. Nevertheless, grammars are the part of the speech rec system that is programmed with all the different utterances that could constitute a valid response to a prompt.

If an IVR asks you a yes/no question, there are tons of different ways to say ‘no’: nope, nah, nuh uh, no, etc. When people talk about tuning a grammar they’re talking about listening to all the different ways callers respond to prompts to ensure that those specific utterances are in the grammar.

For companies with broad national or global reach, this issue is compounded when you factor in different accents and dialects.

Connection Matters

As important as grammars are, it’s equally important to pay attention to phone connections. Any call that goes into Plum’s (or any other) IVR platform will traverse the PSTN at some point. The PSTN’s bandwidth is limited so all audio that travels across it is down-sampled and compressed to 8bit, 8kHz.

Remember tape dubbing? If you made a copy of a VHS or a cassette the copy wasn’t quite as clear as the original. If you made a copy of the copy, the third-generation copy was degraded even more than the previous copy. That’s essentially what’s happening with the down-sampling and compression.

This matters for speech rec because you want the ASR engine to have the highest quality audio possible when it tries to decode utterances.

There are other factors that affect audio quality as well. Jitter from VoIP phones, static on the line or a bad connection, and background noise all have a negative effect on audio quality.

This is one of the reasons that Plum prides itself on using only Tier 1 telecom providers with our cloud IVR platform. We want you to have the best audio connection and call quality possible.

Safety Valves

There are many pieces that go to the phone connection puzzle. And it’s important to remember that not every caller will be doing so from a busy city street undergoing major construction.

Still, you want all your callers to have a great experience. So here are a few tips to help those callers who run into issues with ASR.

  1. Even if ASR is your first choice for your callers, make sure that you provide DTMF options.
  2. If the ASR is having trouble understanding a caller’s responses, don’t continually re-prompt them or disconnect the call. Set a reasonable re-prompt threshold and then switch to emphasizing DTMF input instead.
  3. Make your prompts non-bargable. A bargable prompt is one where callers can input their response before the prompt finishes. With ASR enabled, activating the barge-in feature at the same time can have a negative effect.

Fortunately, with a modern, feature-rich IVR development platform, like Plum Fuse, you don’t have to worry about wasting a ton of development time planning for these exceptions. Fuse makes it easy to manage ASR, giving you granular control over when and how it’s used in your IVR applications.

Schedule a demo of Plum Fuse today to learn more.


Publish Date: November 2, 2017

Why Not All IVR Software Is Created Equal

The Cost of Poor Call Containment

For folks in the IVR world, the goal is to keep as many calls contained in the IVR as possible. This is known the call containment or automation rate. The higher the percentage of calls contained in the IVR the fewer calls agents have to field.

Unfortunately, legacy IVRs don’t do well when it comes to containment rate. Most companies are lucky if they can get their containment rate as high as 50%. If that number seems a bit low, well… it should. Especially for large enterprises that receive thousands of calls per day.

This chart shows how containment rates affect customer service costs for medium and large enterprises. Here we’re assuming that the companies field 90,000, and 3,000,000 calls per month, respectively. The average cost per call for an agent is $5, so we used that, and we’re assuming an IVR cost of $0.20 per call.

As you can see, a higher containment rate saves a lot of money.

How to Increase Containment Rates?

We’ve discussed containment rates here before, including analog ways to optimize your IVR and how to use diagnostic flow in VoiceTrends to get at the question of how to improve containment rates.

Nevertheless, the reality of IVR is that getting the efficiency you want can be a struggle with a legacy IVR system. And it’s not just because these systems aren’t user-friendly and take a long time to program.

No, legacy IVR systems simply aren’t designed to achieve that type of optimization. Too often, people think of IVR in terms of call routing. Here at Plum Voice, our IVR can certainly do that, but it’s designed to automate entire processes, from start to finish, using real-time data integrations.

Plum lets you expand the capabilities of your IVR so that you can automate more customer inquiries and provide answers faster. And the faster you can help customers the happier they tend to be.

This is what we mean when we talk about balancing high automation with high customer satisfaction: the former leads directly to the latter.

Discover how Plum Voice IVR can help you do more by setting up a demo today.


Publish Date: October 17, 2017

How to Get More From Your IVR with Artificial Intelligence

How AI Delivers Better IVR

When you hear artificial intelligence (AI) and interactive voice response (IVR) in the same breath you may scratch your head and wonder, “how does that work?” Using an AI engine, like IBM’s Watson, with an IVR system creates smarter self-service applications and delivers better customer experiences.

With IVR callers have two different ways to input information: 1. using the keypad, or 2. speaking into the phone (assuming the IVR in question supports automatic speech recognition [ASR]). AI makes it easier for applications to process natural speech input intelligently. The result is an application that understands caller intent.

This means that you can ask open-ended questions with your voice self-service applications and provide conversational IVR that is also efficient and customer-friendly. With AI, users can input information without using DTMF and developers don’t need to build and manage custom grammars like they did for traditional ASR.

A chatbot is essentially a natural language intent system, and integrating AI into your IVR can create a chatbot that works in real-time with your voice channel.

AI at Work

Artificial intelligence is a broad technology category. When applied to a business process the idea is to have a machine learn how to mimic human behavior.

For example, let’s assume that a given process has four different triage levels. The sequence of actions required to resolve the issue depends on where the problem falls in triage. When an agent talks to a customer that agent should be able to triage the problem quickly and initiate the resolution process.

A critical step in this process is understanding where to initially slot an issue and then figuring out what the next steps are based on that initial assessment. In other words, agents need to understand the intent behind the customer’s request.

The whole idea with AI is that not only can technology make the same decisions that a person can, but it can also teach itself better decision-making.

Let’s say, for example, that an insurance company has AI working in the backend of its IVR. When a customer calls for the third time to check on their claim status, the AI can recognize that request, infer that the customer really wants an update, and can escalate the call as necessary.

One goal for AI is to build applications that can determine caller needs and what course of action to take to meet those needs more effectively than a person can.

Better Customer Service

You can use AI any place in your IVR where you used ASR before, or where you would like to use natural language understanding. An AI engine like IBM’s Watson comes with pre-built knowledge domains. These are like the individual speech grammars used with ASR, but they’re more comprehensive and most of the legwork has already been done. Watson also lets users build/define custom domains.

Watson AI isn’t completely self-sustaining, and still requires a bit of administrative management, but it is much easier and more cost-effective than the old method of building custom grammars.

AI offers incremental and in some cases significant value to companies that use IVR by delivering smoother, faster, and more efficient customer interactions, while at the same time reducing the time and costs necessary to implement these solutions.

Want to learn more about how Plum Voice and AI can help your business? Contact us today.


Publish Date: September 28, 2017

Improving IVR with Artificial Intelligence

A Place for AI

When most people hear Artificial Intelligence, they tend to think in terms of Hollywood and famous AI characters like HAL9000 and Skynet. Business applications of AI are nowhere near that sexy, but, on the bright side, that also means that our robotic overlords aren’t looming on the horizon just yet.

The reality of AI at this point revolves less around machine self-awareness and more around predicting outcomes by harnessing incredible computing power. Business processes and communications all stand to benefit from the continued evolution of AI. Interactive voice response (IVR) definitely belongs on that list of beneficiaries.

Before diving into specific processes that can make the most out of AI, it’s worth having some additional context in order to understand why AI is going to make a splash in the world of voice automation.

A New Understanding

IBM’s Watson is synonymous with artificial intelligence these days–and it’s not just because Watson cleaned up on Jeopardy! In the voice communications space, Watson’s ability to handle natural language is a big reason why a lot of people, including the engineers at Plum, are excited for the possibilities Watson integrations hold.

We’ve discussed the time and money that goes into natural language speech recognition software, like Siri, Alexa, and Cortana, in these pages before. The reason behind this is that automatic speech recognition (ASR) and natural language understanding are built on two different assumptions.

ASR is all about expected answers. This means asking specific questions and anticipating, not only what people will say in response, but also all the different ways in which they can say that. Think of how many ways there are to say “yes”– yup, yeah, sure, uh huh, ya, you bet – these are just a few of the dozens of ways to indicate agreement or assent. When you consider an entire phrase, the workload increases exponentially.

The collection of expected responses constitute a grammar. It’s necessary to constantly tune grammars to ensure they catch every possible utterance variation. The more variances the software encounters, the more it must process. It’s not hard to see how this can quickly become time and cost-intensive work.

With AI and natural language understanding, the software focuses less on expected answers and attempts to determine the intent of what is said. Therefore, it’s possible to do a whole lot more with live voice communications without the insane costs associated with compiling and tuning grammars.

IBM’s Watson provides API access to its natural language understanding technology and companies can quickly and easily tap into a machine learning capabilities.

The Road Ahead

The ability to discern intent without involving a human opens up all kinds of possibilities for business communications (whether that’s internally with employees or externally with customers) and customer service. Incorporating Watson technology into IVR applications combines the best aspects of self-service in the digital realm with the immediacy of real-time voice communications.

Now that we’ve established a bit of context for what AI like Watson can do for voice communications we’ll turn to some examples of how companies might actually use that technology. Stay tuned for more information and ideas in these pages.


Publish Date: September 21, 2017

Case Study: Second To None Expands Voice of the Customer Offerings with Plum Voice

As the old adage goes, the customer is always right. For Second To None, a customer experience research and analytics agency serving leading brands across North America, one of its clients wanted to add telephone surveys to their Voice of the Customer program.

At the time, Second To None lacked a voice option for this type of survey and immediately began researching their options. With the clock ticking and their client waiting, Second To None needed a solution that they could build and deploy quickly.

Initially, Second To None opted for an on-premises system. This offered the reliability that the company wanted, but as their business grew and more clients took advantage of telephone surveys, the need to scale along with client demand became increasingly important.

At that point, Second To None switched from an on-site system to Plum’s cloud IVR. The switch was almost effortless. The entire switchover process, which included making a few changes to their application’s code and RESPORGing their phone numbers to Plum, took about an hour in actual man-hours.

Dynamic scaling with Plum’s cloud IVR not only allowed Second To None to meet the needs of their clients, but the success they experienced led the company to expand the number of voice features they offered clients. This included call recording and SMS messaging.

Using Plum Voice technology allowed Second To None to provide new, reliable solutions to their clients. Second To None’s CTO noted that Plum’s technology not only expanded their offerings portfolio but did so in a cost-effective way that didn’t require them to sink a ton of money into IT resources. Second To None caters to a number of retail and healthcare clients, so Plum’s PCI and HIPAA compliance meant that they could meet the specific needs of those customers without having to reinvent the wheel when it came to IVR applications.

To learn more about Second To None and how the company innovated with Plum technology, read the full case study.


Publish Date: July 20, 2017

How to Reduce the Risk of Fraud with Your IVR

“You are what you are and you ain’t what you ain’t” – Dear Abby, John Prine

“Basic” Security Isn’t Enough

When it comes to fraud prevention, this line from a John Prine song pretty much explains what it is fraud prevention technology tries to figure out. Preventing fraud over voice communications channels has its own challenges. Most companies have security measures in place to protect personal customer information.

There is a whole host of different secure authentication practices, something we’ve covered in this space before. For the voice channel, it’s common for companies, like banks and other financial services firms, to use automatic number identification (ANI) to validate customer identity.

The problem with this as a single layer of security is that the device doesn’t define the person or vice versa. Most people rely on mobile phones nowadays and while those devices certainly offer all kinds of convenience, they can also easily be lost or stolen. This raises the question: How do you know that the person on the other end of the phone is who it should be?

As a result, fraud experts suggest that companies treat these types of interactions as “person not present” cases. That term simply creates a distinction between a situation where a person is physically present and presents a card to complete a transaction versus one where the payer and the payee are in different physical locations. It’s the same idea as “card not present” in the payments industry.

Anti-Fraud Tech and IVR

Combining interactive voice response applications with additional fraud prevention technology mitigates these challenges. Fortunately, Plum’s cloud-based IVR technology makes it easy to use APIs to connect to these anti-fraud solutions.

Different fraud prevention services offer different solutions, but the realm of possibility is broad. For example, with location services enabled on a mobile device, fraud prevention technology can establish user location trends. This makes it possible to detect, based on the caller’s physical location, when someone is calling from home, work, the gym, or any other frequently visited location.

So, one option for fraud defense is to not only validate phone numbers against customer data but to also check to see if the caller’s current location matches one of the ‘frequent places’ associated with that particular customer.

If the caller’s location is outside the threshold established around their ‘frequent places’ then the system throws an error. At that point, you can decide what action to take, whether that involves locking an account, requiring additional security information, or something else altogether.

The point is that this type of technology delivers an added layer of protection, for companies and customers alike, by identifying potential issues in real-time before fraudsters can access customer data and wreak havoc.

To learn more how Plum’s IVR technology can help you reduce fraud threats, contact us today!


Publish Date: June 29, 2017

Case Study: Mobile Software Company Improves Customer Service with Plum IVR

A leading mobile software company (MSC) in Canada uses Plum products to power their customer service offerings. As a company that offers an array of digital products with over 100 million users all over the globe, MSC needed a solution that had multi-language support.

As a company that deals with digital products in its own right, MSC wanted a solution that was easy to implement. They wanted to keep control of their customer service in-house, but that also meant that they needed something that didn’t require them to take engineers off core product development.

MSC considered a number of different IVR vendors but chose Plum’s Fuse platform because it did everything they wanted it to do, and more. Fuse’s drag-and-drop interface meant that MSC could assign IVR development to non-developer team members because it was so easy to use.

Fuse’s cloning feature was also a huge boon to MSC. As a company that has a significant global presence, MSC needs multi-language support to be effective with their customer service efforts. One-click cloning in Fuse meant that MSC could build one application, and then clone it, change the language, and re-deploy the same application to a phone number in a different part of the world.

Fuse’s built-in analytics helped MSC optimize their Spanish-language application. When the company expanded into Latin America they noticed that a lot of their Spanish-speaking customers were opting out of the IVR to talk with an agent. Thanks to VoiceTrends analytics, MSC identified the issue and quickly added a new message in the IVR that drastically improved containment rates.

With the help of Plum Fuse, MSC has been able to easily harness and control their customer self-service offerings, providing better customer experiences across the board.

To learn more about MSC and how its self-service benefitted from Plum Fuse, read the full case study.


Publish Date: June 27, 2017

Case Study: InMoment Uses Plum IVR to Power Innovative VoC Platform

When it comes to customer feedback, it’s no secret that the best time to get someone’s opinion is right after a transaction takes place because everything is still fresh in their mind. InMoment, which specializes in customer experience optimization, wanted to augment its voice of the customer platform with something more immediate, like voice.

Embracing voice was a logical step for InMoment. After all, pretty much everyone carries a mobile phone with them these days, making it easier for InMoment to deliver post-transaction surveys and for customers to access them.

When InMoment was building their VoC platform, they knew that they needed something flexible to handle the telephony aspects. This is where Plum’s platform, which is VoiceXML-based, came into play. Plum provided InMoment with the features and flexibility they needed to deliver the service and experience their customers expected.

Using Plum’s IVR platform, InMoment was able to create surveys that dynamically chose the right questions to ask customers based on their previous input. This allowed InMoment to deliver better, more accurate data about customer experiences when compared to a standard, linear survey that asks everyone the same questions.

Not only did Plum’s technology put InMoment in a position to succeed, according to John Sperry, InMoment’s CEO, but Plum’s customer service played a vital role in his company’s ability to get their applications up and running in a timely manner. Plum engineers helped them troubleshoot different aspects of their application, and the business development team ensure that InMoment had the information and resources they needed to be effective across the globe.

With Plum’s IVR technology serving as the telephony backbone for InMoment’s platform, the company now fields over 200,000 calls per month. Plum’s cloud platform scales dynamically to meet customer needs, which means that InMoment doesn’t need to worry about spikes in customer usage.

To learn more about InMoment and how the company used Plum technology to become a leader and innovator in the customer experience space, read the full case study.


Publish Date: June 20, 2017

Page: 1 | 2 | 3



Centralised Healthcare System Managed By The Contact Center - Assistt (Turkey)
Jul 12

About us - in 60 seconds!

Submit Event

Upcoming Events

The 17th Annual Best Practices Conferences are here! Meeting Point for the World's Best Contact Center & CX Companies Read More...
Showing 1 - 1 of 3 items

Newsletter Registration

Please check to agree to be placed on the eNewsletter mailing list.

Latest Americas Newsletter
both ids empty
session userid =
session UserTempID =
session adminlevel =
session blnTempHelpChatShow =
session cookie set = True
session page-view-total = 1
session page-view-total = 1
applicaiton blnAwardsClosed = True
session blnCompletedAwardInterestPopup = False
session blnCheckNewsletterInterestPopup =
session blnCompletedNewsletterInterestPopup =