Most people today—whether they are your customers or employees—want intuitive, frictionless experiences when they use your voice-driven solutions.
Automatic Speech Recognition (ASR) can help you save time, ramp up efficiency and scale services in your contact center and many other scenarios. However, not all ASR solutions can deliver experiences that measure up to customer expectations. Those that are too slow, too limited or riddled with inaccuracies can negatively impact purchasing decisions, erode customer trust, and discredit your brand.
It is therefore critical that you get speech automation right. And if you don’t, someone else will: Experts predict that voice commerce will grow to become an $80 billion industry by 2023.
That said, there are many hurdles in this advancing technology field. One of the key complexities is managing and expanding different dialects within a single language model. Even when two users speak the same first language, their dialects (US English vs. UK English, for example) must be managed as two completely separate languages by conventional ASR engines. These models must rely on dialect-specific lexicons and phonetic training, which can be resource-intensive, and quite expensive, especially if you serve a diverse and/or global audience.
To address this and numerous other issues, LumenVox has upgraded our ASR capabilities to bring you a new ASR engine with Transcription that is more accurate, efficient, and scalable—so you can maximize your return on investment.
Build world-class customer experiences with the LumenVox Automated Speech Recognition engine
At LumenVox, we have spent over two decades advancing our speech recognition capabilities through the development of our ASR engine. With state-of-the art transcription capabilities that are built on the foundations of Artificial Intelligence and Deep Neural Networks (DNN), LumenVox’s newly updated ASR engine offers several benefits that will help you offer seamless, accurate, super-scalable voice-enabled solutions.
With LumenVox, you can create user experiences that raise the bar—via your IVR (Interactive Voice Response), chatbot or virtual assistant.
Improved accuracy Our new ASR engine offers a low word error rate (compared with competitors), for exceptional reliability and accuracy. That means you can build high-performance applications time and time again.
Incredible scalability While other ASR engines on the market treat each dialect as a separate language, LumenVox supports multiple dialects with one language model. Take English as an example: where conventional solutions recognize US English and UK English as two separate languages, our ASR engine supports multiple dialects (including US, UK, Australian, South African and Indian) within one “universal” English language model. The same approach is true for Spanish (Castilian vs. Latin American), French (European vs. Canadian vs. Haitian), Portuguese (European vs. Brazilian), and other languages.
The ability to understand various dialects with one model means you can serve a diverse base of customers with a high level of accuracy, faster and for less cost than alternative ASR products. LumenVox uses an end-to-end DNN transcription process when building its language models so there is no need for a phonetic lexicon to understand various dialects for a given language. This speeds up the process of adding new models and when updating existing models with new language data. Your customers can also easily extend and adapt the default language models for their own needs, without having to deal with phonetic spellings and lexicons.
Greater efficiency With a high compression ratio of words and phrases known as ‘n-grams’, our ASR engine allows a greater number of word/phrase combinations to be simultaneously matched to the speaker conversation. This means that an accurate match can be identified in real time. As a result, users will experience little or no latency when interacting with your applications.
More flexibility With a selection of licensing and entitlement options to choose from, it is easy to deploy our ASR engine for any monetization model. Options include monthly subscription and usage based. This offers a refreshing alternative to competitor licensing models, which “lock” licensing entitlement to a single monetization framework.
Designed for simple implementation and management, LumenVox does not require costly professional services for delivery, installation, upgrades, or maintenance. Additionally, it fits in any network architecture, including premise-based installations, multi-cloud installations and hybrid prem/cloud installations.
Simplify the migration of legacy applications
LumenVox provides a streamlined way for customers to migrate off their incumbent ASR by simplifying the migration of grammars and confidence values to the new LumenVox ASR engine.
All these features work together to help you automate your customer and user experience in a more cost-efficient, reliable, and rewarding way.
Join Joe Hagan, chief product officer at LumenVox on August 24 at 11:00 a.m. PT / 2:00 p.m. ET as he discusses what is required to deliver meaningful employee and customer experiences through voice channels. Register now for the webinar.
Bots are fundamentally changing the way business and commerce work. Powered by Artificial Intelligence chatbots are now a critical part of digital strategy, automating customer interactions, with instant customer gratification. As voice technology becomes more popular and widely used, there are two chatbot options: text-based chatbots and voice-enabled chatbots. Which is the future?
What is a Chatbot?
A chatbot is a software application used to conduct an on-line chat conversation via text or text-to-speech, in lieu of providing direct contact with a live human agent. What makes a chatbot powerful, is its ability to answer queries. Natural Language Processing (NLP) extracts intent from utterances. NLP is what makes chatbots intelligent. It’s the artificial intelligence (AI) which powers their ability to learn and provide the most relevant information to each unique query.
How Text-Based Chatbots Work
As the name suggests, a text-based chatbot is the one that interacts and communicates through text or messaging. Text-based chatbots are amazingly effective and efficient because they quickly sense the need of the users and provide them with immediate outcomes. In addition, chatbots assist in gathering feedback and keeping the customers engaged by solving queries quickly.
Text-based chatbots are extremely efficient when programed to accurately sense the need of the user and can provide immediate outcomes. In addition, chatbots also gather valuable feedback and ensure customers are engaged quickly. Text-based chatbots are primarily used to handle customer interactions and are often merged with messaging apps, social media, SMS and other channels.
But here’s the thing, chatbots are text-based which means they require typing, pressing, handling by the customer.
How Voice-Enabled Chatbots Are Changing the Game
A voice-enabled chatbot uses pre-recorded answers and text-to-speech to address customer queries. There are two ways to program these:
Users command the chatbots in either oral or written form, and then reply with their voice.
These “voicebots” are quite fluid, leveraging Conversational UI, or user interfaces based on human speech, written, or spoken. Instead of buttons, links or graphics, the customer uses spoken words to guide the conversation. What’s really neat is that as these bots continue to evolve, they can mix conversational UI with graphical UI; combining the intuitive nature of speech with the immediate gratification of graphics.
Voice-Enabled Chatbots vs. Text-Based Chatbots
The key to the decision between Voice-enabled chatbots vs. Text-based chatbots is to understand the preferences of your customers. According to a recent PricewaterhouseCoopers survey, approximately 71 percent of consumers prefer to use voice searches to conduct a query over the traditional method of typing. Recent reports estimate that 112 million people in the US will use a voice assistant at least monthly, up 10% from the previous year.
Driving Customer Engagement with Voice
Voice use is particularly relevant to people who are multitasking and need answers quickly, without having to put down what they’re doing and type or press a button. Voice-enabled chatbots are that next step forward for continuous, relevant customer engagement. They can be available 24/7 online and ready to serve anyone, anywhere, hands-free.
Give Your Chatbot a Voice
LumenVox Automated Speech Recognizer and NLU Gateway can give your chatbot a voice, boosting your CX strategy and increasing operational efficiency. To learn more, contact us here.
A successful outbound call campaign is a powerful weapon to add to your sales arsenal. In today’s world of marketing emails and robocalls, a personalized phone call can be a breath of fresh air.
To ensure that your customers and leads receive calls that are relevant to them, follow these 4 tips.
4 Tips for Designing an Effective Outbound Call Campaign
1) Use an Open Call Script
The success of scripted outbound sales calls can be hit-or-miss. On the one hand, new reps can massively benefit from a script, particularly in terms of following compliance requirements.
On the other hand, overly scripted phone calls can come across as rigid. As such, you can lose the personalized, human touch of a phone call.
The compromise here is to develop an open call script. These kinds of scripts are loosely structured. They provide the agent with pointers rather than lines that they need to rehearse.
Loose scripts ensure that your agents cover all the important points (while remaining compliant) and yet still allow them to build on natural conversations.
2) Collect and Analyze Relevant Call Data
To build an effective call campaign, you need to have a good understanding of your target market. A successful campaign requires extensive research to build a library of data that reps can refer to before making calls.
Data shouldn’t purely focus on industry and location, but should also try to answer these questions:
Who am I talking to?
Why would they need my product?
3) Employ an Effective Training Program
Training programs help prepare new reps for real-world calls. This will help them remain confident and compliant every step of the way.
Training programs can include the following:
Call recordings that reps can analyze and critique
Group role-playing activities to help reps learn to think on their feet
Lessons on how to identify the key factors comprising a successful call (e.g. tone of voice)
4) Use Key Performance Indicators (KPIs)
KPIs are useful metrics for monitoring sales rep performance. It is important to first identify which KPIs your business wants to place the most emphasis on. Examples of common KPIs include:
Average handle time
Conversions rate (number of calls resulting in successful sales)
Make sure that employees learn and understand the importance of these metrics. Teach them how to maximize their KPI scores through the training program.
Finally, use KPIs to identify weak reps who might require further training, as well as strong reps that should be recognized and possibly rewarded to encourage good work!
Personalized outbound calls, when done right, can be an incredibly effective sales strategy. Be sure to invest time into carefully designing an outbound call campaign strategy to maximize your center’s success.
And, while you focus on training the human side of the campaign, let LumenVox take care of all your automated contact center needs. Request a demo or contact us today so that we can help you maximize your company’s efficiency so that you can focus on spending your time on more important things.
Speech-enabled automated attendants are a must-have for any customer service strategy. In the age of Siri and Alexa, customers have come to expect automated, speech-based service. ComScore reports that more than half of all smartphone users are engaging with voice search technology in 2020.
Enhances Branding and Corporate Image The biggest brands in the world use speech attendants. Why? Their customers value speech recognition capability, which produces automated, yet natural communication with the end-user. This elevates the branding of any organization, large or small.
Automates Routine Operator Tasks A virtual speech attendant takes on tasks that would otherwise be completed by an operator, allowing callers to speak the name of a person, department, service, or location and be automatically transferred. This removes the need for manual time and labor of operators answering inbound calls, searching for phone numbers, and connecting customers to their destinations. The web-based administration interface included with ISA simplifies the configuration of nicknames and aliases, department and location-based transfers, business hours logic, alert messaging, and more.
Gives Organizations Control of Transfers A robust speech attendant provides callers with a convenient way to reach people within an organization by acting as a single point of access to the corporate directory. ISA’s full-featured administration dashboard puts organizations in control, allowing for highly customized handling of inbound calls.
The pandemic has transformed the way businesses operate. Technologies have been adopted at lightning speed due to increased reliance upon remote workforces. There are many voice technologies that are now must-haves, such as Automatic Speech Recognition. But are businesses and organizations using these technologies to their fullest potential?
You need to start with a basic audit—what voice technologies do you already have? How are you using them? We’ll assume you are using Automatic Speech Recognition, as it is most common, and specify how you can leverage it to maximize ROI.
Are you using Automatic Speech Recognition? What are you doing with your speech data? Transcription enables visibility of this precious information. When transcription is used in conjunction with artificial intelligence, or Natural Language Processing, feeding machine-learning processes downstream, it enables customers to speak their mind, literally. This means the IVR or even chatbots can interact with customers in a more personal, efficient way, solving problems that would have required costly time with a live agent.
If you are using Automatic Speech Recognition in your IVR, how have you tackled authentication? Have you considered voice biometrics? Voice biometrics creates a secure, convenient authentication process that can either happen within the IVR or with live agents. It cuts costs by reducing handle time. It raises satisfaction levels for agents and customers by removing the need for painful, lengthy interrogation processes. There are two modes of voice biometrics: Passive & Active. Passive means customers are verified through natural conversation. Active means they are prompted to speak a specific passphrase to authenticate. Either method results in higher satisfaction and compelling ROI.
The LumenVox Technology Stack is unique in its convenient licensing and add-on capabilities. With just one installation of one of our components, such as our Automatic Speech Recognizer, you can easily add licensing to incorporate any of our other technologies. With forward-thinking and access to such a flexible stack, companies can remain competitive. Step up your game and keep your customer service at the cutting-edge.
Questions about any of the LumenVox voice technologies? Contact us.
Customer experience is often highest on the priority list for businesses. But in a post-pandemic world, organizations are looking for ways to improve the agent experience as well. By raising the importance of agent concerns to the same priority level as customer concerns, organizations can dramatically improve employee satisfaction levels, optimize the efficiency of individuals, and demonstrate best care practices. These steps can also improve agent recruitment and retention. The benefits also translate into a positive customer experience. Happy agents equal happy customers.
Here are three ways to enhance and improve the agent experience with voice technology.
Challenge 1:Authentication. A renowned technology research firm, Opus Research, has “long seen zero-effort authentication as a necessity for creating trusted links between brands and their customers.”
Solution: Voice biometrics provides a convenient and secure form of authentication for customers and an effortless task for agents. There are two types of voice biometrics, Active and Passive.
Active Voice Biometrics means that the customer enrolls by repeating a set phrase. On subsequent calls, the customer speaks their passphrase, which is compared to their stored enrollment voiceprint.
Passive Voice Biometrics means the customer is seamlessly enrolled by capturing historical or real-time audio. Enrollment is completed by recording the customer’s unique voiceprint during an initial conversation, not a specific phrase. On subsequent calls, customer’s conversational voice is compared to their stored voiceprint. A customer speaks with an agent and is transparently verified within the agent desktop.
It’s secure and effortless, turning a common pain point for agents into a seamless experience.
Challenge 2:Fraud. Right now, attackers are shifting from spoofing to using virtual call services since they are anonymous and untraceable. These fraudulent calls are legitimate calls that can be placed from many devices from anywhere in the world. This allows fraudsters to bypass spoofing detection technology with numbers unrelated to a record. Fraudsters then use social engineering on agents to grant them control over a customer’s record.
Solution: With Passive Voice Biometrics, agents themselves can help identify fraudulent activity in real-time. If a customer’s voiceprint does not match the one on file, the agent will be alerted of the voiceprint mismatch. The agent can then pass the warning signs to the fraud department to initiate investigation—while the call is still in progress. By giving these agents greater peace of mind, and the fraud department greater resources, everyone is protected and more productive.
Challenge 3: Containment. With greater reliance upon the contact center to solve customer issues, the workload of agents rises daily. Without intelligent proactive outbound communication and robust Automatic Speech Recognition and Text-to-Speech technology, customers route to agents for menial tasks to mine information that could be accessible ahead of the need/ask.
Solution: LumenVox’ Automatic Speech Recognition and Text-to-Speech enable automated yet dynamic and personalized interactions with customers within the IVR. This improves containment and reduces Agent Handle Time, as customers gain immediate access to relevant information, often removing the need for a live agent. With the use of Call Progress Analysis, agents’ time can be spent solely on live interactions with customers. Call Progress Analysis is a novel predictive dialer technology which uses Voice Activity Detection (VAD) to quickly and accurately classify whether calls were answered by a human or a machine. With this technology as well as statistical analysis, adjustments and feedback, agents can achieve optimal performance.
Voice technology can be leveraged in a variety of ways to shave valuable minutes from each agent’s workload. This translates into benefits for the business, for the agents themselves and for customers.