In a couple of recent blog posts (here and here) we looked into variation between individual speakers and several factors contributing to it, but an important aspect worth diving deeper into in the human language is dialect.
So what is a dialect? A tricky question to answer that can get you into political trouble in some areas of the world! In the past, central authorities were often skeptical of communities that claimed to have its own (regional) language, preferring to rather speak of a mere “dialect.” In the reverse, smaller countries with a big neighbor often insisted they spoke its own language, not just a dialect of the neighbor’s language. Luckily linguistic variation today is often seen as a precious treasure of cultural heritage, but in many places Max Weinreich’s summary that “a language is a dialect with an army and navy” is still valid. Avoiding those issues, I will use “dialect” in a pragmatic way, also encompassing regional languages and accents.
Looking back over the more than 20 years I have spoken to customers and others about Automatic Speech Recognition (ASR) the most frequently asked question definitely was, “Do your systems speak dialect X?”, where “X” may have been Bavarian, Scottish English, Swiss German, Canadian French – and many other examples.
After many centuries of authorities trying to discourage the use of dialects, today many people are actually proud of their ability to speak a dialect. Recall when during a trip to an exotic place you recognized somebody coming from the place you were born in just by listening to how they speak – it’s a welcome feeling. Even governments exploit this today: the German state of Baden-Württemberg (which prides itself of being the birth place of many inventors and scientists, like Carl Benz, Johann Kepler, Albert Einstein; AND is also the home of the Nuance Ulm office) coined the slogan: “We can do everything. Except [speak] High German.” Obviously the slogan is not quite true in that most speakers of dialects also speak the “standard” form of their language and apply what linguists call “code switching.” Depending on the social setting, speakers switch between standard language (in a formal setting) to dialect (at home or with friends) and back. Dialect, similarly, can be a tool with which you can signal to somebody they are welcome in your home or that they will remain a stranger, as they don’t speak your dialect. The same mechanism may be at work in those numerous radio spots or YouTube videos where people make fun of ASR, which supposedly does not speak a dialect, see for example here and here.
The second reason why people may have doubts about ASR working well with dialect may also be related to the long history of dialects not being an acceptable language to use in school (at least in some countries). Clearly dialects deviate from the rules of the standard language, as codified in the grammar book, so that somehow encouraged the myth that dialects do not have any rules, are “irregular” and necessarily difficult to capture in a machine. But from a linguistic viewpoint, that is really just a myth: granted, dialects sometimes don’t have a written form, but for linguists spoken language is more important anyways, written language only being a secondary derivation. And in the spoken form dialects are as regular as any other language, they are neither worse or nor more difficult, nor better or easier than “standard” languages.
Machine Learning, especially Deep Learning based on Neural Nets, can deal with the variety of having several dialects and a standard form in one population. As long as you make sure all dialects are reflected in your training data (and we make sure it is, e.g. for the UK we use more than 20 defined dialect regions) the resulting models will reflect all those ways of pronouncing the phonemes (or sounds) of a language. We make sure to include words that are special to a dialect (again using the UK as an example different areas refer to a bread roll as a cob, a barm cake or a bun) and where pronunciation differences go beyond isolated phonemes, we reflect that in the pronunciation dictionary.
For instance, our UK English language pack recognizes 52 different pronunciations of the word “Heathrow” so our airline customers can cater to those whose first language isn’t English. When differences become too big, we create separate models in some cases. Users of Dragon speech recognition software can choose between variations of English and between Flemish (for Belgium) and Dutch (for the Netherlands).
Occasionally this is done “under the hood,” so to speak. Even in the Dragon US English version, there are several dialect models. We use a classifier (another application of Machine learning) to detect which “package” fits best to the user’s dialect and use that for recognizing (if you are interested in a more academic text on how to do this, this PhD thesis is an in depth study of how to deal with Arabic dialects). We also verify that it works by measuring accuracy gains per variant, e.g. Dragon Professional Individual English has an accuracy improvement (over the previous version) of 22.5% error reduction for speakers of English with a Hispanic accent, 16.5% for southern (US) dialects, 13.5% for Australian English, 18.8% for UK English, 17.4% for Indian English and 17.4% for Southeast Asian speakers of English.
Finally, as I mentioned in this blog post we have adaptation to help us with the challenge: dictation software like Dragon will adapt overtime to a user’s specific dialect. When the usage deviates from how we thought it would be used during training, ASR may not work for every dialect at every time. However, speech recognition’s accuracy across a number of languages has risen considerably by upwards of 99%, and is evidenced by the broad and global integration of our cloud based ASR and NLU, used by thousands of apps in cars, IoT devices, smart phones etc.
Have a look at the heat map above, showing where there are people who use our technology successfully. This also holds when we drill deeper into Scotland vs. England.
Linguistic variety is as important to us as it is important to you; which is why we support more than 80 languages (including regional languages like Catalan and Basque, which we developed in cooperation with regional governments ), and as we have seen in this blog post we do a lot more to cover variation and dialects beyond that number. So, we welcome the challenge of dialect – even if in the form of a YouTube spoof.
Publish Date: January 26, 2017 5:00 AM
CardBoard: Real-time data, shows the most important KPI’s in your Contact Center.
Built for data | Designed for business | Empowers teams
|2.)||Acqueon Technologies Inc.|
Acqueon's AI-driven conversational engagement software enables sales, marketing and service organizations to engage in emotionally connected dialogs with customers via their channel of choice for significantly improved results. The Acqueon suite adds multichannel campaign management, contact center analytics, desktop, and CRM connectors for your contact center software of choice, including Amazon Connect, Cisco, Nice inContact, and Twilio. Acqueon conversational engagement software leverages the Acqueon IQ platform to aggregate data from the various applications, assemble rich customer contexts, and drive next-best-action using powerful statistical and predictive models.
PH: +1 888-946-6878
|3.)||Call Tracking Metrics|
Automate insights from all your customer communications
There's no better way to get to know your customer than through their own communications with your brand. Gain a strategic advantage and a thorough understanding of your customer's full journey with a complete suite of conversation intelligence tools and features. Measure customer sentiment, automatically identify and score qualified conversations, and give strategists everything they need to knock their campaigns out of the park.
Use conversation analytics to:
• Build your ideal customer profile
• Optimize your sales and customer service processes
• Maximize your resources to focus on quality conversations
• Identify trends and customer sentiment in real-time
CallFinder speech analytics
CallFinder® is a leading provider of cloud-based SaaS speech analytics, automated call scoring, and speech-to-text transcription technology with sentiment analysis. Our easy-to-use solution is designed to help businesses and contact centers automate quality monitoring to improve agent performance and provide a superior customer experience.
With CallFinder, you get…
100% visibility into agent-customer interactions
100% monitoring of interactions, up from only 5-10%
Scalability of QA reviews with the same size QA team
CallFinder isn’t just your average speech analytics provider. When you work with us, you get unparalleled, continuous support through our MyAnalyst managed client servic...
CCube for Business Intelligence
CCube by Comsys is a business intelligence application, developed for enterprise contact centers. It delivers powerful, and dynamic reporting that enable managers to gain insight into their business. CCube is natively compatible with Aspect Unified IP and Cisco Unified Contact Center (UCCE/UCCX) platforms
Comsys is a provider of οmnichannel customer engagement solutions that assist companies around the world in delivering unique customer experiences. For the last 15 years, Comsys designs and implements complex projects for clients from the outsourcing, financial services, telecommunications, and retail sectors. Comsys enjoys strategic partnerships with technology vendors like Cisco®, Aspect...
The days of ‘business as usual’ are a distant memory for most of the world. And when it comes to contact centers, balancing between contact channels, deciding which agent locations or teams are doing well, working out how your customer satisfaction is being impacted by the less-than-perfect work environments of ‘lockdown’ agents…leaders are often at a loss when trying to get such insights from their contact center data. As the technology and business landscape changes, so too must the contact center reporting and analytics solutions that power decision making and performance management. With the new release of Consilium UniInsight™, we have tried to deliver contact center reporting and op...
PH: (+61) 406 501 368
CROSSCRM.CX - CRM Dataviz Module
CROSS-CRM manages daily interconnection with your CRM tools to centralize data and analyse CX on all channels, and is able to provide deep analytics insights.
All the Kpi’S are here for precise control of your Customer Relationship : Interactions - Quality - Satisfaction - Campains forecast MyClient
Filters, Data Extraction, Custom Views, dates sheets, email subscriptions, xls Extracts, images, pdf
PLUS ! Automated extracts
for integration to third party applications.
Daisee builds technology that empowers people to solve problems by making interactions simple and smart so they can have a more significant impact, be more productive and be better at what they do. We believe incremental improvements carry huge potency and provide exponentially greater change for the better.
Genesys customers can now automate risk and quality management using Daisee’s speech and sentiment analytics and remediation workflow software. Daisee helps improve customer experience, ensure regulatory compliance, identify missed commercial opportunities & training requirements as well as provide valuable insights back to the business directly from the frontline – the true voice-of-...
Powered by AI, DialogTech’s DialogAnalytics analyzes conversations to provide marketing and sales teams a wealth of insights for smarter optimizations. With the power of conversation intelligence, you can learn which channels, ads, keywords, and webpages drive the best sales calls, if the caller converted, and more.
AI analyzes how calls are handled at locations and call centers to detect issues that negatively impact ROI. See what percentage of calls go unanswered and who is best (and worst) at converting callers to appointments and customers. Get email alerts when phone leads are mishandled at locations so those leads can be called back right away.
With DialogAnalytics, you can get a...
eGain Analytics makes it easy to measure, analyze and refine your contact center operations, knowledge and web customer experience. Create informative reports, charts and dashboards effortlessly. Slice-&-dice the data in any number of ways and use it to manage the business effectively.
1. Operational Analytics™ empowers the business to measure and manage the call center directly and without IT involvement.
2. Knowledge Analytics™ provides insight for eGain’s knowledge and AI applications.
3. Digital Analytics™ measures contact center performance within eGain’s digital channel applications.
4. Journey Analytics™ captures customer behavior on the website—identify the churn points and cre...
ethosAnalytics leverages data to provide business intelligence to enhance the customer experience and beyond. The analytics dashboards are customized based on client needs. ethosAnalytics enables data-driven decisions in seconds or minutes - not days or weeks.
|12.)||Lieber & Associates|
Contact center Analytics and Metrics
Lieber & Associates provides services to develop, interpret, and improve contact center metrics and analytics. The firm's experience spans forecasting, customer service, order-taking, lead-qualification, sales, segmentation, media-source-tracking, and testing design. L&A's president pioneered segmentation for telephone scripts and the tri-level service level metric. He brings broad analytics experience to contact centers.
Turn business insights into actionable intelligence. Noble’s IQsolutions provide you with rich and robust customer data that can transform your business. Automate decision making and campaign management and refine the quality of interactions with precision and efficiency. We have developed proprietary and patented tools to help you make sense of data on your current operations and then help you make strategic decisions to improve performance and efficiency. Identify who your best customers and prospects are and the ideal methods to reach them. Understand what types of campaigns work best for your business and how to optimize underperforming campaigns. And nake real-time decisions rather than looking back to see what went wrong.
PH: +61 (0) 3.9008.1700
With OpsTel VIEW™, you are able to monitor and immediately audit your agent profile data for accuracy and compliance across the entire contact center solution stack.
*OpsTel VIEW™ tracks down unused stale profile licenses and provides clients with detailed audits explaining their location, current and historical status
*Comprehensive audit across the enterprise, it only takes 10 minute
*Provides a view in to the data accuracy of agent profiles across multiple applications
*Drastically speeds up audit and validation processes
*Validates actions to implement for profile data integrity issues across multiple applications
*Can also assist in ensuring access level compliance...
SIP-Trunk Demarc Monitor
Analyzes SIP signalling and RTP audio stream of every call passing through the network demarcation point. Provide a real time 24/7/365 network baseline database that contains the IP bandwidth, call traffic of up to 128 voice groups, Call Detail Record (CDR), call blockage and MOS voice quality. All information are displayed in SIP-Trunk dashboards and are used in many applications, such as Telco collaboration, UC/CC analytics, Work Force Optimization (WFO) and caller identification.
Social Media Analytics
Social media analytics is the practice of gathering data from blogs and social media websites and analyzing that data to make business decisions.
Typical objectives of Social Media include increasing revenues, reducing customer service costs, getting feedback on products and services and improving public opinion of a particular product or business division.
Key the activities involved:
Analyzing net sentiment score
Qualitative and quantitative of sentiment analysis
Measure the emotions (6 Emotions) of the consumers
Mapping out all potential advocates
Measuring a nationwide consumer sentiment
Unlimited data extraction & cleaning
Customized positive and negative keywords
Qualitative and quantitative insights & report writing
Measuring the consumer sentiment
QPC provides realtime unstructured and structured data analytics solutions and services to contact centres globally.
We provide a complete end-to-end customer integrated offering powered by a Multichannel Intelligence Gateway which collects and inter-relates all customer interactions, from each and every customer contact across an entire contact centre ecosystem, all in real-time.
We also provide solutions for conversational and interaction analytics with solutions from our specialist portfolio.
Tethr is a cloud-based conversation intelligence platform that combines AI, machine learning and over a decade of customer experience and sales best-practice research to surface contextual insights from phone calls, chats, emails and other customer interactions. Companies use Tethr to turn large amounts of unstructured voice of customer conversation data into insights they can deploy to improve their customer experience.
Imagine for a moment that you are a call center manager responsible for generating revenue through signing new customers or up-selling to existing ones. Imagine that your KPI is telling you you have an abandonment rate of 5% and someone comes along and says "No, your abandonment rate or dropped call rate is 13%." .." How do I know? AcutuCall VoIP software application can show you the dropped call data including, originating number and whether it was a network or equipment failure." Now imagine you can see your calls in progress on a mobile app, take your dashboard where ever you go! "What is a lost call worth to you?"
PH: +1 613-521-1639
|Customer Success: 6 steps to make your customer touchpoints count||September 12, 2019 5:00 AM|
|How Apple Business Chat can help enterprises with their call deflection goals||September 10, 2019 5:00 AM|
|Hear the Call for Help! How Siren Detection Can Make Your Car a Force for Good.||September 9, 2019 5:00 AM|
|Nuance IQ is back for the summer||August 26, 2019 5:00 AM|
|Meet your patients where they are with 24/7/365 answers to their portal questions||August 21, 2019 5:00 AM|
|Contact center transformation pitfalls (and how to avoid them)||August 8, 2019 5:00 AM|
|Robots here, there and everywhere, and now in the office||February 14, 2019 5:00 AM|
|3 ways speech recognition helps in police incident reporting||January 22, 2019 5:00 AM|
|Building trust with a virtual assistant voice||January 22, 2019 5:00 AM|
|Television viewing is no longer a one-way street||November 15, 2018 5:00 AM|