2200 Powell Street, Suite 1010, Emeryville, CA 94608 contactus@pinpointresearch.com 800.776.7265

Improved ASR Technology Makes Speech-to-Text an Essential Resource for Call Centers

Call center customer experience (CX) continues to be a critical component for both customer retention and brand advocacy. To improve customer service, call center operations continue to focus on acquiring and analyzing voice data to measure the CX experience, drive agent coaching, and improve call center operations. The customer’s voice has become even more powerful in shaping CX thanks to improvements in ASR (Automated Speech Recognition) technology.

ASR is shaping CX and call center operations, providing immediate speech-to-text auto-transcriptions that are more accurate than ever before. Using today’s ASR technology, we can collect and process voice data with a base accuracy between 84 and 90 percent using an untuned model, and even greater accuracy with a tuned model. And with ASR technology, voice transcriptions are delivered in near real time, as opposed to multiple days, and the cost of auto-transcription is a fraction of manual transcription.

Consider the possibilities of having a real-time call transcript at your fingertips. Integrating auto-transcription with text analytics gives you a new layer of qualitative data that can be mined in various ways.

For example, real-time text analytics allow you to code and analyze voice data enabling post call review and closed loop escalation of call data and open-ends to respond to critical customer needs. You also have new potential applications for improving call center operations, including auto-transcribing call survey open-ends and the auto-transcription of agent customer call center recordings for training and coaching. Accurate call transcripts powered by the latest ASR platform provides a rich store of qualitative data for agent coaching and case management response review, as well as CX analytics.

It’s clear that speech-to-text has become an essential tool for every progressive call center.

The goal of every company is to improve CX, and for many customers call center interactions are the most influential experience, a defining experience within their journey. Using voice data and transcribed text together provides call center operations and CX practitioners with a new and powerful set of tools to drive innovation and improve CX.

Want to learn more about how speech-to-text technology can improve your call center operations? We recently completed a study assessing the effectiveness of voice-to-text for qualitative analysis and will be happy to discuss our results. I look forward to our discussion, contact me

Wanted: Better Qualitative Data

If you want to understand the customer experience (CX), you need both quantitative and qualitative data. Quantitative research is certainly valuable, especially leveraging rating systems like Net Promoter Score (NPS) where metrics can be tied to revenue growth. However, to get to the “why” of customer behavior you need more, and better qualitative data.

As CX expert Bruce Temkin points out, to understand the customer experience you have to ask the customer directly. You can’t take the human experience and translate it into numbers. Once you convert CX into numbers you have lost what the customer is feeling, which means you cannot design an experience that connects with customers. You need to use voice, video, and other means to capture the qualitative customer experience and apply it to CX.

IVR Surveys Deliver More Open Ends

We have seen a growing trend from CX leaders who want to capture and analyze qualitative customer insights, which means more demand for one-on-one data capture and open-end responses in surveys. Recently, for example, we attended a CX conference supported by Forrester where the CXO of Ford Motor Company indicated that acquiring and analyzing open-ended customer data was one of his top priorities. The challenge is finding the best means to conduct those surveys and make qualitative data actionable.

IVR voicer surveys deliver more qualitative data

As shown in the graph, our research shows that IVR voice surveys outperform other survey modes including web, mobile, and SMS. IVR voice surveys not only have a higher frequency of open-ended responses, but generate more and better qualitative research data. IVR voice surveys acquired four to six times more open-ended data (based on a character count per open end) than other survey modes. This means that by using voice surveys you are getting more open-ended responses and more in-depth responses to drive insights and ideation.

From Qualitative to Actionable

Of course, gathering consumer responses is only the first step. Processing and mining this data in a timely fashion that provides near real-time insights is key to maximizing its value.

The fastest and most cost-effective technique to make voice open ended data actionable is using real-time transcription. Using ASR speech-to-text auto transcription provides written text that can readily be analyzed for sentiment using key words and phrases. Using real-time auto-transcription also can generate alerts for closed-loop response; an ideal solution for customer service call centers.

Open-ended voice response can give you a more accurate barometer to assess customer sentiment. Voice-driven IVRs have been shown to give deliver substantially higher response rates, which indicates deeper consumer engagement. And technology such as real-time speech-to-text transcription can make that qualitative data actionable, flagging problems for immediate attention and providing meta data that creates emotion and sentiment scores for each response.

If you need more qualitative consumer data and really want to listen to your customers, consider using open-ended voice IVRs. They are your best tool to gather more accurate emotional response data, and you can readily convert voice to text for a more accurate picture of sentiment analysis.

If you want a copy of our latest research showing the performance of different types of qualitative research tools, just drop us a line and we’ll be happy to share the results.

Measurement Becomes Useless When You Set Targets

Customer satisfaction surveys have become an essential part of marketing. Many online sales, telephone support call, and customer exchange is followed by a customer satisfaction survey, and most of those surveys are absolutely useless. When the customer satisfaction ratings become targets, then the insight from customer feedback disappears. To be effective, customer surveys need to be open, unbiased, and untargeted to get authentic customer views; insights that are actionable. That’s why we are seeing more call center clients adopting voice-driven research™ leveraging voice open ends increasing the quality and quantity of qualitative open end response data.

The value of customer satisfaction research has been demonstrated again and again. According to a recent survey by The Temkin Group, 87 percent of customers surveys indicated that their 2016 investment in customer experience (CX) research has a positive impact on business, as opposed to 79 percent in 2015. As a result, 66 percent of companies are increasing spending on CX studies, including a nine-fold increase in headcount. Most of that spending is going into voice of the customer (VoC) software, predictive analytics, and experience design.

Customer satisfaction surveys can help fuel CX research, but only if they gather unbiased results that reflect the true voice of the customer.

Stacking the Deck with Scored Surveys

What’s wrong with customer satisfaction surveys is they become self-fulfilling prophecy. Too often, a company uses customer surveys as a means to gauge call center or service performance, using a score as a target threshold. Surveys become a “shop, rate, reward” system integrated into customer interaction and designed to generate a miss the targetscore, or target.

This type of metric is flawed when gauging true customer experience. Goodhart’s Law, developed by British economist Charles Goodhart, states that once a measure becomes a target, it can no longer be used for valid measurement. By way of example, Goodhart points to soviet factories producing nails according to a target. If the target is to produce a specific number of nails, the factory produces more tiny nails to meet the target. If the target is based on weight, the same factory retools to producer fewer, heavier nails. In both cases, the target doesn’t reflect true value.

Now consider the same truth as it relates to customer satisfaction surveys. If a survey follows a support call or customer call, the call center representative will ask for a favorable rating which will skew the results:

Rep: “Did I address all of your concerns, Mr Jones?”
Customer: “Yes, thank you.”
Rep: “Great, then can I count on you for a 10 out of 10 score on our customer satisfaction survey?
Customer: “Yeah, okay.”

In general, everyone wants to be helpful so you will consistently get survey results that skew positive. In fact, many companies assess call center performance using post-call surveys and anything less than a 10 out of 10 is considered unsatisfactory.

To get true customer sentiment and honest customer feedback, you have to separate the survey from employee scoring.

The Value of Self Expression

The best approach for accurate, actionable insight is to avoid scoring altogether and opt for open ends, where customers get to share their true opinion.

Open-ended questions offer a number of advantages, especially if you are seeking to gather actionable data. For example:

  1. You get answers you don’t expect. Open ends allow customers to offer observations, not just responses, so you are likely to uncover hidden problems, such as long wait times, problems with your phone menu, and other annoyances. Removing impediments to better customer service means better returns
  2. Complete responses to complex questions. Open ends allow customer to explain. This has at least two benefits: 1) it provides a more comprehensive response to the questions and 2) it cements customer relations by giving the caller a chance to be heard.
  3. It tells you how customers think.

How you administer open end questions also has an impact on the quality of response. You can use written surveys, which will give you genuine feedback that is easy to add to your database for data search. However, given the rising degree of survey fatigue, consumers are losing patience with answering surveys, and written surveys may not generate the response rate you want.

Voice capture adds another layer of authenticity to feedback surveys. Mobile phones in particular have become a popular tool for IVR surveys. Two-thirds of Americans own smartphones and use them for online data access as well as telephone calls, so targeting smartphone users gives them options on how to take the survey. We have found that most consumers prefer voice response surveys because they are faster and easier, which is an advantage for call centers since voice responses capture the true voice of the customer.

With new speech-to-text transcription technologies, companies are seeing an error rate of 7 percent or less for transcriptions. This makes transcribed voice response accurate and incredibly useful for call centers. Transcriptions can be generated in near real-time, making it easy to search algorithms that can flag customer issues that need immediate attention. And the original voice file can be preserved for tone and deeper insight. The result is customer satisfaction response that is easy to capture, more accurate, and most importantly, immediately actionable.

Targeting customer satisfaction provides a false positive that will lead your company in the wrong direction. If you truly want to gauge satisfaction, don’t lead your customers, just ask them what they think. If you provide a forthright and easy way to respond, such as voice response, then you will get more accurate results that will lead to better business decisions.

What Do We Mean by Voice of the Customer?

With the evolution of consumer marketing and customer research terms change their meaning. One term that continues to be bandied about to the point it is no longer clearly defines is Voice of the Customer (VoC). VoC is an essential part of customer research, but the term has become a catch-all for any type of customer experience or interaction. There are parameters around how to define and think about VoC that are important to appreciate to develop an effective customer research program.

The Voice of the Customer is an old concept. Organizations have been taking the pulse of the people for generations. Steve Allen started the concept of the Man on the Street interview for the old Tonight Show back in the 1950s, doing impromptu interviews to hear the vox populi. Getting people’s opinions can be powerful and provide valuable insight into the perception of your brand or product.VoC rshc quote

VoC actually began as a means to gather information as part of product development. The goal was to gather information from target consumers to determine their wants and needs. VoC was a means of capturing insight about customer requirements in a hierarchical manner in order to make the information actionable, i.e. give the product team an understanding of how to develop the right features and functions.

What has happened over time is that the definition of “voice of the customer” has expanded beyond its original, narrow definition to support market research. VoC assessment has become part of consumer research methodology and is used to identify customer needs, trends, behaviors, and patterns.

What’s important to remember is that VoC research is designed to address the customer experience BEFORE there is physical interaction with the product or brand. Once the customer has had the product experience, then you move into a different phase or research based around customer feedback.

So what are the objectives of a solid VoC program? Consider these:

  1.  Strive to understand the customers’ expectations from the brand as part of your research.
    2. Understand how VoC helps shape a brand’s product or service to align with the customers’ needs.
    3. Understand how the brand can address the demands of the customers, as opposed to how the customer perceives the product or service.
    4. How can VoC expectations be applied to bring about strategic changes across the organization.

VoC research is designed specifically to learn more about customers’ likes, dislikes, preferences, and patterns. By its nature, VoC research is anticipatory, and requires interviewees to project themselves into the brand experience and voice their expectations. An IVR surveys can be an invaluable tool for VoC research if it is applied properly. This is especially true of newer VoC systems that integrate voice driven IVR surveys that actually capture and auto transcribe the open-end responses of customers, giving researchers detailed qualitative information about customer attitudes and emotions.

Not all customer research touchpoints fall into the category of VoC, but if you are using customer research to assess customer expectations or acceptance of a new product or brand experience then you should plan your VoC research accordingly.

Our next blog entry will offer a list of considerations when developing your next VoC survey.

Omni-channel CX is Incomplete Without IVR

Can you have a successful omni-channel customer experience without IVR?

The short answer is No.

I recently attended a large CX conference and it surprised me how many companies believed they have mechanisms in place to monitor their omni-channel customer experience. Many of these companies have call centers that field hundreds of thousands of calls a year and they have never considered IVR surveys to measure their customers’ call center experience (although many use email surveys to measure the call center or agent). I will be the first to admit that IVR research has the stigma of being old fashioned – my company has been doing it for almost 30 years – but that doesn’t mean IVRs can be ignored or that there aren’t some exciting new things happening with IVR surveys.

call centerThere are exciting innovations in the IVR world. Speech-to-Text has come a long way in recent years. We now have an 88-90% accuracy rate using an out of the box survey model and it can get higher with tuning. Why is this important? Well IVR open-end comments are the longest compared to other methodologies. Some studies show that they are seven times longer and more comprehensive than web and SMS comments. This means richer comments, more insights and more data to feed into your text analytics.

There also is an increased need for redaction technology. We are seeing our customers in the Finance, Healthcare and other regulated fields using redaction software to remove Social Security Numbers, Banking Number and any other PII (personally identifiable information) from the transcription and open-ends. This means companies can be sure of security compliance since employees can listen and read transcribed open-ends without having to worry about uncovering sensitive personal information.

Another innovation is that IVRs now include a sentiment score that measures the emotion of the respondent when he or she left the open-end response. This score is another data point to help you decide which comments to listen to and how to setup alert.

However, one of the most exciting innovations in applying IVR to measure omni-channel CX is the ability to present real-time feedback. Consider this example. A customer requires a service call at their home. After the installation the technician leaves and the customer receives a phone call using a voice-enabled IVR with a short survey about the installation experience. If the customer leaves an open-end response that there was an issue with the service call, the Speech-to-Text transcription technology and IVR analytics can pick up on the customer’s dissatisfaction and issue an alert. A Customer Service Representative can then look up the customer’s information based on the generated alert, call the customer immediately and resolve their issue. With real-time sampling and reporting customer response time can be reduced to less than 30 minutes.

Without the right IVR system in place to gain customer feedback, the customer journey is incomplete. You need to learn as much as you can about the customer experience to make omni-channel marketing truly pay off.

Is Voice Driven Data Capture Part of Your CX Strategy?

Customer Experience (CX) research has been experiencing dramatic evolution in the last decade. In recent years customer satisfaction research has been turned upside down by the rapid evolution of the digital customer experience. The historical norm of siloed customer satisfaction survey projects reported on a monthly or quarterly basis has evolved into real-time omni channel data collection spanning the entire customer journey, from acquisition to long-term client retention and value growth. Further, there is a new demand to integrate all employees into CX reporting and motivation. Every employee in the company has an opportunity to enhance the customer experience, which has driven CX vendor to deliver multi-level reporting that integrates analytics spanning survey, social data, operational data, etc.Customer Response

The goal today is not to simply report on a customer satisfaction metric, rather it is to make customer satisfaction an integral component to company strategy and employee motivation.

To achieve this goal, CX vendors must look for best of breed solutions throughout the customer journey. One such solution is the Voice Driven Data Collection™. Voice Driven Data Collection utilizes telephone and mobile devices to maximize the opportunity to capture both quantitative and qualitative data within a omni channel environment by converting voice response into actionable data.

The premiere survey methodology for capturing voice driven data is IVR surveys. IVR offers a flexible survey methodology for mobile consumer enabling voice and keystroke-driven input. Statistics show that IVR surveys tend to provide the highest response rates in outbound survey methodologies, and they offer the ability to gain insight immediately after a consumer interaction with a call center. What this means is that a broad demographic population can provide survey data response that reflects a more accurate representation of the consumer’s experience with rich quantitative and qualitative data.

More importantly, IVR surveys uniquely enable an ability to capture responses through open ends, the actual voice of the customer, providing actionable attitudinal and ideation insights to understand the “why” of consumer CX measurement. This ability to capture consumer voice is particularity important when considering the dramatic decline in open ended data associated with web, mobile, and text surveys.

Integrating IVR survey data collection is a key component to making the Voice of the Customer actionable in today’s CX strategy.

Four keys to better measure call center CX

Customer support call centers continue to be one of the most influential customer experience touch points in your customers’ journey. Designing and executing customer experience feedback systems at the call center should be one of the highest priorities in any enterprise CEM solution. Unfortunately, for many brands a one-size-fits-all methodology has been used to develop survey and feedback systems to interview customers about their experience following call center interactions. Our experience suggests that the survey methodology and system design needs to align to the unique aspects of customer care call center management.

Here is a list of four key considerations to keep in mind when designing call center survey feedback systems:

1. Acquire customer experience quickly. The best data from customer care and call center service interactions need to be acquired within minutes after the termination of the call. Best of breed solutions use an instantaneous, event-triggered system to engage a consumer who has opted in to a survey. This event triggered surveys offer the highest response rates and the most concise feedback on call center experience.

2. Sentiment data is king. Consumer sentiment is recognized as a key indicator of customer experience and an important metric for customer care. Many vendors wait to measure sentiment in post engagement text analytics processing. Voice driven data collection systems using IVR and speech-to-text models can measure consumer sentiment scores in real time and monitor for keywords and phrases enabling alerts to be delivered for direct intervention by customer care representatives.

3. Integrate operational and research data. Strong analytics are key to managing agents’ performance and making insights actionable. One way of enhancing call analytics that is often overlooked is integrating survey data with operational data. The seamless integration of survey and operational data, including agent ID, is critical to generating comprehensive analytics that can render actionable insight. Survey data system should integrate through API into the call center data allowing seamless integration on the front-end rather than requiring post survey manual integration of operational data.

4. Open-ends are critical to making NPS actionable to the brand. Qualitative insights drive ideation that enables the brand to take action to make measurable improvement in NPS scores. Unfortunately, mobile and text survey have had a direct negative impact on the quantity and frequency of consumer open ends. The only survey methodology that has consistently delivered rich open end data is IVR surveys. Consumers tend to give open end responses that are 3-7 times longer than other survey methods. In addition, with speech-to-text technology these voice open ends are more actionable and cost effective than ever.

Why IVR surveying of call center customers is on the rise

Market pundits have predicted the decline of call centers as a critical component of consumer care.  In reality, call centers continue to be the single most important component of consumer care in the digital age. Research shows 69 percent of consumers are more satisfied using the phone to acquire support across most industries.  Further, at a cost of $1.00 per minute, Call Centers represent the single most expensive customer care system cost by a large margin.call center operator

Because of the volume of consumer contacts and their relative impact on consumer satisfaction, call centers have always been considered a critical touch point in the customer journey for all customer experience CX research.  Further, multi-modal surveys have been used for post call center surveying, but IVR surveys have been the dominant and preferred survey method. New trends in customer research will further expand the use of IVR surveys for post call center customer care.

Call center operations are beginning to integrate speech to text technology as a scalable method to review and analyze the performance of agents, and coaching agents to enhance success metrics. Speech to text captures the customer exchange and transcribes it to make it easier to analyze and dissect call outcomes to assess agent performance. This technology will enable call center management to better understand the causes of successful and failed customer care calls.

What the technology of transcribing actual consumer call recordings will not provide is a clear understanding of the impact customer care and service call successes and failures have on the customer’s relationship to the brand. This can only be achieved by an effective and broad-based post contact survey methodology.

IVR surveys continue to offer the preferred survey methodology because it offers nearly instantaneous post call or service contact, extremely high participation rates, a mobile friendly platform, and the ability to gather quantitative and qualitative feedback, including insight into brand affinity. The qualitative data acquired by IVR surveys has dramatically improved and is more cost effective with the integration of similar speech to text technology. Now you can transcribe survey open ends and integrate such data for text analysis and ideation research in near real-time a fraction of the cost of manual transcription.

As call center innovation grows so does the ability for customer experience research to measure the attitude of consumers and score their experience to measure the impact on consumer brand affinity.

 We can help you get more from speech to text IVR surveys – learn more.