Voice biometrics and analysis capabilities demoed at CES 2020

voice-biometrics

Sensory will provide its voice biometrics and other innovations in collaboration with voice technology company Aiquido to develop comprehensive solutions to be white-labelled for voice services and assistants.

Wake word (TrulyHandsfree) and natural language recognition technologies will also be provided by Sensory, in addition to its TrulySecure voice ID capability, while Aiquido provides multilingual intent understanding and action execution capabilities, according to a joint announcement.

Intended applications include integrations with autos, as well as mobile apps, smart home, and wearable devices.

“Voice adoption continues to grow rapidly, and brands are always exploring ways to streamline the process of integrating a convenient voice UX into their products,” says Todd Mozer, Sensory’s CEO. “Working with Aiqudo allows our two companies to provide the industry a turn-key solution for integrating powerful voice assistants into their products that feature brand-specific wake words and are capable of recognizing who is speaking.”

“Brands increasingly want to create their own branded voice experiences for their customers,” states John Foster, CEO of Aiqudo. “Working with Sensory, we have created the easiest and fastest way for brands to bring the power and convenience of voice to their customers. We are excited to integrate our areas of practice and expertise to deliver a comprehensive solution.”

Ceva and Novatek partner for TV SoC

Ceva has announced that Novatek Microelectronics, a fabless chip designer, has licensed and deployed its voice front-end software and speech recognition software for always-on far-field voice wakeup and control functions in its lineup of multi microphone-enabled System-on-Chip lineup for smart TVs.

Technology licensed by Novatek includes CEVA-X2 Audio DSP, ClearVox, and WhisPro software. The high-performance CEVA-X2 DSP uses 5-way VLIW micro-architecture and offers parallel processing with dual scalar compute engines, support for Single Instruction Multiple Data (SIMD), and optional floating points for high accuracy algorithms, according to the announcement. WhisPro and ClearVox operate in tandem to provide a speech recognition solution for always-listening devices like smart TVs, smart speakers, smartphones, and Bluetooth earbuds, and are optimized to be used with CEVA-X2 for smart home, mobile, and auto applications.

“We are excited to expand our partnership with Novatek and bring the power of the voice user interface to their smart TV SoCs,” said Ceva Vice President of Marketing Moshe Sheier. “Our CEVA-X2 DSP together with our ClearVox and WhisPro voice software packages allow Novatek to add new features that create a unique and tailored multilingual voice experience for their customers.”

QuickLogic showcases edge voice products

QuickLogic, like Sensory, is showcasing its voice products at CES 2020, Embedded Computing Design reports. QuickLogic’s AI-based voice control for endpoint IoT, hearable, and wearable applications will be demonstrated, and its EOS S3 Voice and Sensor Processing Platform highlighted.

Always-on voice, Always-on sound, and sensor processing capabilities, as well as SensiML Analytics Toolkit and OEM products will be shown by the company. QuickLogic says its EOS S3 Platform provides wake word capabilities with one-tenth of the power consumption for MCU-based devices for TWS earbuds compatible with Amazon Alexa, as well as for remote controls, wearables, and smartphone applications.

QuickLogic will also demonstrate AI-enabled consumer use cases with the Infineon Integrated Alarm System.

Related Posts

Article Topics

 |   |   |   |   |   |   |   | 

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Research

Biometrics White Papers

Biometrics Events

Explaining Biometrics