Nuance FreeSpeech : Biometric authentication using speech
Nuance FreeSpeech authenticates a caller in as little as six seconds, just by listening to their normal conversation.
Authentication without interruption
FreeSpeech is a text-independent passive customer authentication platform used in a call center. It verifies a caller’s identity during the first few seconds of a natural conversation with a contact center agent and compares to the voiceprint that is stored in the database. It does this in seconds without interrupting the call. It can do this in any language, with any accent, and call quality regardless of the content of the call. It completely eliminates the need for PINs, passwords, and security questions when a caller is interacting with an agent in a call center.
State of the art biometrics
FreeSpeech ensures that fraudsters cannot spoof the system and voiceprints cannot be used if stolen, keeping customers secure from fraud. FreeSpeech incorporates scores of unique features to ensure that a fraudster cannot spoof the system. This system looks for anomalies in gender, liveness, and caller consistency and will generate an alert if it finds synthetic speech or a recorded voice. Even professional voice imitators cannot fool our system.
FreeSpeech continually updates voiceprints by using new audio to update existing voice templates and automated enhancement of voiceprints based on the analysis of failed authentication attempts by legitimate users. FreeSpeech maintains an accurate voiceprint even with changing background noises and voice tones that shift with age.
Nuance enterprise technology intelligent self-service solutions employ natural language understanding and speech recognition to simplify the customer experience, resulting in customer service that is easy, fast and effective. Companies around the world rely on Nuance speech enabled self-service solutions – combining innovative technologies and deep services expertise to automate a wide variety of customer interactions.
Promero will provide a free consultation with your business and discuss how Nuance technology can improve customer experience and better staff utilization. Please contact us today.
Nuance Recognizer: Speech Recognition
Nuance Recognizer delivers the industry’s highest voice recognition accuracy and enables natural, human-like conversations for more satisfying self-service interactions. With Nuance Recognizer, you’ll consistently deliver a great customer service experience while improving your self-service system’s containment rate. Nuance Recognizer is the software at the core of contact center automation solutions. Built upon years of experience across six different product lines, the Automatic Speech Recognition engine is used around the world in over 79 different languages.
Nuance Recognizer is the best-of-breed speech recognition software that dramatically increases the efficiency of your self-service solutions. Delivering high recognition accuracy and enabling more natural conversations, Nuance Recognizer allows your callers to experience more efficient and satisfying self-service interactions. Nuance Recognizer can perform well even when faced with challenges such as noisy environments, mobile phone callers, Internet-based calls, regional accents, local dialects or multiple languages. It learns from its mistakes and makes automatic adjustments to improve over time.
Deliver a Great Customer Service Experience
With Nuance Recognizer, you’ll consistently deliver a great customer service experience while improving your self-service system’s containment rate. It delivers the industry’s highest recognition accuracy as it encourages natural, human-like conversations that create more satisfying self-service interactions with your customers. Nuance Recognizer will increase the efficiency of your interactions with callers using state-of-the-art acoustic models and natural conversations that make it easier to resolve issues on the first call.
Built-in 64-bit support, load balancing, better CPU/memory utilization, multi-tenancy, and centralized logging support more efficient use of computing resources. Sensitive data management capabilities allow your solutions to be compliant with various security regulations and industry standards. Centralized server management – with operations, administration and maintenance capabilities, reporting, and other analytical functions – simplifies deployment and maintenance of your self-service solution. Nuance recognizer will increase the efficiency and scalability of your resources with load balancing, resource management, multi-tenancy, and centralized logging and monitoring services that lead to high service availability. Together, these capabilities add up to unparalleled levels of accuracy, reliability, and ease of use that will transform the way you care for your customers.
Save Money by Automating Calls
Speech-enabled self-service systems can answer inquiries, take orders and collect payments – saving you money by handling repetitive tasks. Also, speech recognition automates what touchtone can’t. Collecting names and addresses. Avoiding long lists of options. Handling hands-free callers. You can save your service representatives for customers who actually do need to talk to someone live.
Understand What Callers Mean
People say funny things when they are talking to a speech system. They forget it’s not a person on the other end. They make mistakes and correct themselves, sometimes many times. They don’t always answer the question you ask them.
Nuance Recognizer can’t handle every response but you’d be surprised at how well it interprets the wide variety of ways callers respond, thanks to natural language technologies such as SmartListener and SpeakFreely and the flows of conversation defined in our Nuance Dialog Modules.
Analyze Your Performance
Who is calling you and how can you improve the way you handle their calls? Nuance Recognizer includes reporting and analytics tools to help you get the most out of your deployment.
Automation that saves
With 35% improvement in accuracy and superior flexibility, your company can design and build robust self-service applications that save money by automating repetitive tasks.
Speech that’s natural
Recognizer can capture and interpret natural conversational speech with over 10 times the improvement in semantic interpretation performance – placing fewer constraints on application design and functionality.
Nuance Vocalizer: Text-to-Speech
Nuance Vocalizer is the leading speech output solution converting any written text into spoken output. Vocalizer generates high quality speech by seamlessly combining dynamic text-to-speech with pre-recorded audio and tuned text-to-speech segments. Nuance Vocalizer is the complete spoken output engine that can be integrated with any Unified Communication System or Telephony Environment that supports MRCP. It automates more calls by speaking information that would otherwise have required transferring the call to a customer service representative to read. Nuance Vocalizer avoids patchwork prompts by blending high quality text-to-speech with pre-recorded audio for seamless conversations with callers. With Nuance Vocalizer, you can always tell your callers what they need to hear.
Vocalizer 6 voices have unmatched expressivity and personality, which provides a more appealing customer interaction.
Faster service for customers
Vocalizer 6 can provide customers with the information they want to hear and help to route service issues to the correct departments for faster service.
Superior caller experience
Vocalizer 6 can be used to communicate using high-quality text-to-speech and/or a blend of pre-recorded audio and IVR to deliver seamless conversations.
Premium voices available
Vocalizer 6 offers premium voices, which provide the most natural IVR experience imaginable and can help enhance the customer service experience.
Avoid Unnecessary Transfers
Sometimes a caller needs to hear dynamic information that’s tough to pre-record with voice talent such as names, addresses or information from a database. Vocalizer’s text-to-speech capabilities can read back that information as part of an automated system, saving a transfer to an agent to complete the task.
Automate More Calls
Research has shown that callers are more likely to complete an automated call when they hear information such as names and addresses read clearly by a single voice. Callers who hear “patchwork prompts” of multiple voices with poorer quality text-to-speech are distracted by the mixed voices and are more likely to opt-out of automation.
Lower Implementation and Operational Costs
Simplify application development by managing recorded prompts and computer-generated speech through one unified interface