Video: How to Leverage Text-Independent Biometrics
Learn more about voice authentication at the next SpeechTEK conference.
Interested in attending a SpeechTEK event? Visit SpeechTEK.com to sign up for conference alerts, discounts, and more.
Read the complete transcript of this clip:
Roanne Levitt: There are two types of voice biometrics: text-dependent and text independent. Text-dependent is a self-service modality where the customer will enroll using a specific phrase. "My voice is my password" is a very common one that in our particular organization we have very sophisticated background models trained on that, so it's quite accurate. There's really not much to say about that model.
We ask for three utterances--"My voice is my password" three times--and with that we can create a very accurate voice print, and then with one utterance coming back for the verification, it's usually sufficient.
So that system is quite mature. It's been around for a long time. The accuracy is well over 99%, so it works in most applications.
Text-independent is free form speech. This is conversational speech. What we like to recommend, is on the very first call with your customer, after you've accumulated 45 seconds of net speech, so you remove all the silences, and 45 seconds of their voice speaking, that produces, for us, a very, very accurate voice print for them.
The technology has evolved significantly in the last few years with deep learning. Around 2015 was the first time we introduced a deep neural networks. That was our first generation. Before that we had I-vectors, before that it was infector analysis, but deep neural networks were in our fourth generation, and this last generation is very, very exciting, because this last generation is called, it's something called embeddings and what that does is it gives us the ability to recognize an individual using unstructured speech, freeform speech, within less than a second of net speech.
So what does that mean? That means that if you're developing an IVR application, and you're using a voice IVR, as soon as the customer says a few things, like, I'd like the balance on my account, that would be sufficient to verify them using this new technology. So it's very, very exciting.
In the call center, of course, right now we do chunking in three seconds. Every three seconds we take the audio and we do a test, and usually in the first chunk, assuming that we have some audio, we can do a verification. Almost always by the second chunk, we can greenlight a customer. So it's very exciting the advances in speech technologies.
Allstate Conversational Designer Katie Lower outlines working models for assessing the viability of a conversational interface with multiple teams within an organization in this clip from her presentation at SpeechTEK 2019.
Allstate Conversational Designer Katie Lower defines the customer journey map as a visualization of the customer's process and explains why it's valuable in this clip from her presentation at SpeechTEK 2019.
Grand Studio Lead Designer Diana Deibel discusses the ethical implications of speech UIs and remaining cognizant of the inherent human elements of speech and conversation in this clip from her presentation at SpeechTEK 2019.
Grand Studio Lead Designer Diana Deibel discusses multiple approaches to making VUI design transparent--the Google vs. Alexa, system-initiated vs. user-initiated--in this clip from her presentation at SpeechTEK 2019.
Pindrop Director of Product Marketing Ben Cunningham discusses best practices for voice authentication in IVR design in this clip from his panel at SpeechTEK 2019.
Gridspace Co-Founder and Co-Head of Engineering Anthony Scodary demonstrates Grace, Gridspace's new automonous call center agent, in this clip from his keynote at SpeechTEK 2019.
Orion Labs Head of Product Ellen Juhlin and Voicea CMO Cory Treffiletti discuss persisting challenges in speech-to-text, AI identifying intent, user expectations, and more in enterprise speech tech applications in this clip from their panel at SpeechTEK 2019.
451 Research Senior Analyst Raul Castanon discusses new findings of a recent survey on speech technology adoption in the enterprise and how adoption of devices in the consumer space have impacted enterprise adoption in this clip from his panel at SpeechTEK 2019.
Grand Studio Lead Designer Diana Deibel discusses best practices for culturally inclusive access in voice UI design in this clip from her presentation at SpeechTEK 2019.
Gridspace Co-Founder and Co-Head of Engineering Anthony Scodary discusses the transactional nature of speech and how that understanding impacts effective, AI-driven call center analytics in this clip from his keynote at SpeechTEK 2019.
Conversational Technologies Principal Deborah Dahl lays out a plan for making more virtual assistants more effective in this clip from her keynote at SpeechTEK 2019.
Conversational Technologies Principal Deborah Dahl discusses the state of the art for the three pillars of conversational systems in this clip from her keynote at SpeechTEK 2019.
Conversational Technologies Principal Deborah Dahl explains how more targeted enterprise knowledge could make VAs more effective in organizations in this clip from her keynote at SpeechTEK 2019.