All items tagged with voice processing (24)

audioXpress October 2023 Speaker Builder Issue Is Now Available!

September 11, 2023 by audioXpress Staff

audioXpress October 2023 Speaker Builder Issue Is Now Available!

In the October 2023 issue of audioXpress, Jan Didden visits Dutch & Dutch, Reinhold Lutz shares a practical way to measure loudspeakers in any room with his AudioChiemgau Mode-Compensator, which is tested by Rens Tellers. We have two DIY open baffle projects from Perry Marshall and Charlie Laub, Richard Honeycutt writes about the Western Electric 91E, and Ethan Winer shares his Popping P Filter circuit. In the Sound Control column, Honeycutt explores Passive Variable Acoustics, and Chuck Hansen concludes his article series on Power Transformers. audioXpress October 2023 is now available in print, digital, and online.

Dolphin Design Unveils Innovative IP for Sound Classification Reducing Power Requirements by 99%

June 27, 2023 by audioXpress Staff

Dolphin Design Unveils Innovative IP for Sound Classification Reducing Power Requirements by 99%

Dolphin Design, a semiconductor designer of power management, audio, and processing devices with in-house ASIC design services, announced the launch of WhisperExtractor, a mixed-signal technology for voice and audio-enabled SoCs, enabling voice and sound classification at a record µW level power budget. The new technology paves the way to breakthrough always-on voice user interface, real time speech-to-text, and always-on sound detection.

Syntiant Partners with Telink and Murata to Present New Edge AI Audio Solutions at CES 2023

December 26, 2022 by Joao Martins

Syntiant Partners with Telink and Murata to Present New Edge AI Audio Solutions at CES 2023

Syntiant is heading to CES 2023 with an exciting range of announcements and presentations of end-to-end edge AI solutions for always-on applications. The company will unveil a new reference design created in partnership with Telink that will enable ODMs and OEMs to easily and quickly deploy complete, ultra-low-power, deep learning voice processing applications in remote controls. Another major announcement is the launch of the Murata Type2DA neural decision processor module for edge AI audio and sensor applications.

Unique Speakers, Parts, and Concepts in Voice Coil September 2022

August 30, 2022 by audioXpress Staff

Unique Speakers, Parts, and Concepts in Voice Coil September 2022

Voice Coil September 2022 offers an article about solutions for Smart Speakers and Voice Processing by Mike Klasco, and an updated directory of Magnet Vendors and Distributors for 2022. James Croft reviews a recent patent awarded to Tymphany for a new Coaxial Loudspeaker design, and Vance Dickason characterizes two very original drivers in Test Bench. The HF1460 compression driver from Faital Pro and the Tang band the W4-2356 4" full-range woofer with an off-centered voice coil.

Vesper Launches 2nd Generation Smart Piezoelectric Voice Accelerometer with ZeroPower Sensing

March 28, 2022 by Joao Martins

Vesper Launches 2nd Generation Smart Piezoelectric Voice Accelerometer with ZeroPower Sensing

Vesper continues to redefine its range of MEMS solutions for voice applications with the launch of the VA1210, Vesper’s 2nd generation analog piezoelectric smart voice accelerometer. The VA1210 offers higher sensitivity (+17 dB) and higher (+6 dB) SNR than the 1st generation VA1200 in voice pickup. Additionally, new intelligent features of Wake-on-Voice (WoV) and hardware voice activity detection (HVAD), introduced into the VA1210, enable a drastic improvement of voice quality True Wireless Stereo (TWS) earbuds.

Voice for True Wireless Earbuds, GaN, and More Exciting Audio Frontiers in audioXpress April 2022

March 11, 2022 by audioXpress Staff

Voice for True Wireless Earbuds, GaN, and More Exciting Audio Frontiers in audioXpress April 2022

The April 2022 issue of audioXpress offers an overview of voice for true wireless stereo earbuds with contributed articles from Knowles and Fluent.ai. Stuart Yaniger reviews the possibilities with GaN amplifiers, and Steve Temme explains the evolution of Rub & Buzz measurements and the latest perceptual algorithms. Ethan Winer designs a sample & hold circuit for a guitar-controlled, all-analog synthesizer project, Richard Honeycutt explores the meaning of “frequency response” as applied to rooms, and Mark Driedger explains why and how to test tubes.

Picovoice Announces Speech-to-Text 2.0: Better, Faster, Stronger

March 9, 2022 by Joao Martins

Picovoice Announces Speech-to-Text 2.0: Better, Faster, Stronger

Picovoice announced a new speech-to-text engine that they believe will be able to disrupt the $30B transcription market. The young Canadian company focused earlier on its own wake word (Porcupine), speech-to-text, and speech-to-intent engines. To prove its latest Speech-to-Text solution, Picovoice is offering 100 hours of free transcription per month to showcase that cloud-level accuracy can be achieved without sacrificing privacy, reliability, and affordability.

Mackie Announces M•Caster Live Compact Audio Streaming Mixer

January 21, 2022 by audioXpress Staff

Mackie Announces M•Caster Live Compact Audio Streaming Mixer

Mackie, the professional audio manufacturer founded in 1988 by Greg Mackie and now the main brand of LOUD Technologies, announced the M•Caster Live Portable Live Streaming Mixer. Not just another repurposed live sound mixer, M•Caster Live was designed from the ground up for content creators and their unique needs. It combines audio interface, audio mixing, voice and processing effects and even RGB lights, targeting social streamers, gamers and podcasters.

Syntiant Announces Voice-Enabled Ultra-Low-Power Reference Design for TWS Earbud Applications

January 7, 2022 by Joao Martins

Syntiant Announces Voice-Enabled Ultra-Low-Power Reference Design for TWS Earbud Applications

Syntiant, the company focused on making edge AI a reality for always-on applications, announced a new reference design that will enable ODMs and OEMs to easily and quickly deploy ultra-low-power, edge AI voice processing applications in true wireless earbuds. The solution enables multi-lingual custom wake words and speech commands, supported by data training and modeling, providing a complete, end-to-end solution for edge AI processing.

Audeze Announces Filter Planar Magnetic Speakerphone On Indiegogo

November 17, 2021 by audioXpress Staff

Audeze Announces Filter Planar Magnetic Speakerphone On Indiegogo

Audeze continues to surprise with new cutting-edge development efforts, having in common the use of planar magnetic technology. Following a very successful entry in gaming and spatial audio, followed by an advanced medical noise-cancelling product, Audeze now unveiled Filter, a portable conference speakerphone equipped with intelligent voice processing that connects to virtually any digital source device over Bluetooth or USB and can be used with all conferencing software.

«
1
2
3
»