All items tagged with voice recognition (313)
Challenges to Building Voice-Enabled Products
April 2, 2020 by Chin Beckmann

Challenges to Building Voice-Enabled Products

Voice-enabled devices are quickly becoming commonplace in nearly every region and for every consumer demographic. Whether making cloud-connected or offline products, OEMs need to understand what’s driving this demand for voice. Unlike some new product features, adding a voice interface requires product architects to make a number of highly-impactful, interconnected design decisions. Development teams don’t have it easy either, as integrating microphones in a product introduces another layer of complexity.
Read more...
XMOS and Plumerai Partner To Bring Binarized Neural Networks to the Edge
April 2, 2020 by audioXpress Staff

XMOS and Plumerai Partner To Bring Binarized Neural Networks to the Edge

British technology companies XMOS and Plumerai have agreed a new strategic partnership that will support the development of binarized neural network (BNN) capabilities that enable AI to be embedded in a wide range of everyday devices efficiently at low power and at low cost. XMOS and Plumerai will bring together their deep learning expertise across chip design and algorithms in a binarized neural network capability, advancing the deployment of intelligence at the edge.
Read more...
Delightfully Disruptive Huawei Sound X Wireless Speaker Co-Designed with Devialet
March 27, 2020 by Joao Martins

Delightfully Disruptive Huawei Sound X Wireless Speaker Co-Designed with Devialet

With China resuming production capabilities and companies back to work, the barrage of products that had been scheduled to be unveiled or launched at MWC Barcelona 2020 are now being announced. Chinese telecommunications giant Huawei unveiled its latest smartphone together with a new wireless speaker, co-designed with French audio company Devialet. Announced to the world during an "online product release event," the all-new Huawei-Devialet joint wireless speaker stands-out for the electro-acoustic design and the patently intent to copy the Apple HomePod.
Read more...
CEVA Announces DSP and Voice Neural Networks Integration for Power-Efficient Edge Processors
March 25, 2020 by audioXpress Staff

CEVA Announces DSP and Voice Neural Networks Integration for Power-Efficient Edge Processors

CEVA announced that its CEVA-BX DSP cores and WhisPro speech recognition software now also support TensorFlow Lite for Microcontrollers, a production ready, cross-platform framework for deploying tiny machine learning on power-efficient processors in edge devices. WhisPro is CEVA's speech recognition software for voice wake words and custom command models. TensorFlow Lite for Microcontrollers is a solution from Google for implementing machine learning at the edge, already optimized and available for CEVA-BX DSP cores.
Read more...
Ambiq Micro Licenses CEVA’s Bluetooth Low Energy IP for Next-Generation SPOT Platforms
March 11, 2020 by audioXpress Staff

Ambiq Micro Licenses CEVA’s Bluetooth Low Energy IP for Next-Generation SPOT Platforms

CEVA announced that Ambiq Micro has licensed CEVA’s RivieraWaves Bluetooth low energy IP for use in its next-generation Subthreshold Power-Optimized Technology (SPOT) platforms integrating Bluetooth connectivity. CEVA’s Bluetooth low energy (BLE) IP is already powering Ambiq Micro’s Apollo3 Blue Family Wireless System-on-Chip (SoC), used in applications requiring intelligence everywhere, from wearables to animal trackers to smart home devices.
Read more...
Essential Updates on Headphones, TWS, Hearables, Voice and More in audioXpress April 2020
March 9, 2020 by audioXpress Staff

Essential Updates on Headphones, TWS, Hearables, Voice and More in audioXpress April 2020

The April 2020 edition of audioXpress is now available and features two essential Market Updates, one focusing on the industry transition to active headphone and earphone designs, and another on how to leverage the latest voice capture and processing technologies. The issue also explains how to evaluate listening effort, and Stuart Yaniger puts the Linear Audio Autoranger Mk II Interface to the test, while Ed Simon writes about AC Power Rectification. Another issue to read and use as reference.
Read more...
Fraunhofer IIS Licenses Comprehensive MPEG Audio Codec Suite to NXP Semiconductors
March 2, 2020 by Joao Martins

Fraunhofer IIS Licenses Comprehensive MPEG Audio Codec Suite to NXP Semiconductors

Fraunhofer Institute for Integrated Circuits IIS, the inventor of mp3 and primary developer of the xHE-AAC and MPEG-H Audio standards, announced that NXP Semiconductors has licensed Fraunhofer’s MPEG audio SDK. The complete software package covers four generations of audio codecs, from legacy MPEG Layer-1/2/3 to the next-generation MPEG-H 3D Audio standard and the AAC codec family, including xHE-AAC. NXP will incorporate these codecs in home entertainment product development, from set-top boxes and soundbars to smart speakers.
Read more...
NXP Announces Far-Field Offline Voice Control Solution In Collaboration with Sonos
February 26, 2020 by audioXpress Staff

NXP Announces Far-Field Offline Voice Control Solution In Collaboration with Sonos

NXP Semiconductors announced availability of its voice solution, SLN-LOCAL-IOT, a fully integrated development platform for offline voice control. The solution consists of a full hardware module design and associated software required to implement far-field voice control with a customizable wake word and local commands. NXP also announced market availability of the i.MX RT600 crossover microcontroller (MCU) family, ideal for ultra-low power audio and voice applications.
Read more...
SoundHound Partners With Wcities to Bring Extensive Location and Event Data to Houndify’s Voice AI Platform
February 17, 2020 by audioXpress Staff

SoundHound Partners With Wcities to Bring Extensive Location and Event Data to Houndify’s Voice AI Platform

SoundHound, the voice-enabled AI and conversational intelligence technology company, announced a partnership with Wcities, a travel and entertainment content publisher specializing in city guides and event aggregators, to bring location-based events data to the Houndify voice AI platform. This new collaboration will provide developers using Houndify with information on more than 3 million events worldwide to include in voice-enabled apps and services via Wcities’ eventseeker APIs.
Read more...
Brüel & Kjær Recommendations for Smart Speaker Testing
February 3, 2020 by audioXpress Staff

Brüel & Kjær Recommendations for Smart Speaker Testing

Brüel & Kjær Sound & Vibration Measurement is promoting a set of recommendations for smart speaker testing, putting focus on the importance of realistic testing when developing and incorporating voice recognition functionalities into consumer products. The Danish sound and vibration specialist recommends the use of its high-frequency HATS Type 5218 and Mouth Simulator Type 4227 systems with human voice characteristics for realistic speech and sound testing of voice-operated devices.
Read more...