All items tagged with voice recognition and beamforming (24)

DSP Concepts Optimizes Voice Control for the KT Genie TV All-in-One Soundbar

June 19, 2023 by Joao Martins

DSP Concepts Optimizes Voice Control for the KT Genie TV All-in-One Soundbar

DSP Concepts announced its collaboration with South Korea telecom KT Corporation to bring smart voice control to KT's latest set-top box, the Genie TV All-in-One Soundbar. This 2023 Red Dot Product Design winning-product features the GiGA Genie AI voice assistant, combined with powerful sound tuning features. With the Genie TV, KT delivers premium immersive sound combined with precision far-field voice recognition enabled with TalkTo from DSP Concepts.

AES Audio Product Education Institute Webinar Helps Demystify Beamforming for Voice Applications

July 6, 2022 by Audio Engineering_Society

AES Audio Product Education Institute Webinar Helps Demystify Beamforming for Voice Applications

The Audio Product Education Institute (APEI), an Audio Engineering Society initiative, is promoting a webinar exploring application and optimization of microphone beamforming techniques, and the latest optimizations for voice recognition platforms. The knowledge-sharing online session features presentations from DSP Concepts, Soundskrit, and Fluent.ai, with presentation by Dave Lindberg from DB Enterprises in Hong Kong.

NXP Semiconductors Completes Acquisition of Retune DSP

August 30, 2021 by Joao Martins

NXP Semiconductors Completes Acquisition of Retune DSP

NXP expanded its already broad portfolio of voice enablement solutions with the acquisition of Retune DSP, the Denmark-based provider of Digital Signal Processing (DSP) software and algorithms for voice control and communication applications. Announced in July and now confirmed, the acquisition of Retune DSP adds three powerful voice DSP software products that will merge with NXP’s voice solutions. The combination with NXP’s broad customer base, global footprint and scale, promises to expand breakthrough voice solutions through combined R&D, sales force and customer support teams.

Alexa? Techniques to Pull Clear Speech from Noise – Part II

August 25, 2021 by Ofer Shahen-Tov

Alexa? Techniques to Pull Clear Speech from Noise – Part II

Great voice recognition can only start with great voice pickup. If cost is no object, of course you can build a great solution. Just use high-end voice activity detection, many-microphone beamforming and echo cancellation and you’ll have a premium product for high-end markets. But can you also satisfy mid-range markets with attractive pricing? This article discusses techniques to offer solutions for both markets.

ArkX Labs EveryWord Far-Field Reference Design Kit Receives Amazon AVS Qualification

November 13, 2020 by audioXpress Staff

ArkX Labs EveryWord Far-Field Reference Design Kit Receives Amazon AVS Qualification

ArkX Laboratories, a joint venture between hardware design and development firm Surfaceink and consumer electronics manufacturing company Ark USA, announced its EveryWord Ultra Far-Field Reference Design Kit has been qualified by Amazon AVS. The advanced far-field development kit features Cirrus Logic SoundClear Technology and NXP i.MX 8 host processor technology and is a powerful solution for manufacturers dealing with noisy environments, different mic array geometry challenges, and the need to support 3 or 5 channels for surround use cases.

Alango Far-Field Voice Enhancement Package Now Available on NXP RT600 Processor

November 13, 2019 by audioXpress Staff

Alango Far-Field Voice Enhancement Package Now Available on NXP RT600 Processor

DSP processing software specialist firm, Alango has been working to port the company's Voice Enhancement Package (VEP) to the NXP i.MX RT600 cross-over processor family, which is optimized for 32-bit immersive audio applications combining a high-performance Cadence Tensilica Hi-Fi 4 audio DSP core with a next-generation Cortex-M33 core. VEP is a set of Alango proprietary far-field voice enhancement technologies developed to improve human to machine interaction in a variety of applications.

New TI Burr-Brown Audio Quad-Channel ADC Captures Voice at Four Time Larger Distances

November 5, 2019 by audioXpress Staff

New TI Burr-Brown Audio Quad-Channel ADC Captures Voice at Four Time Larger Distances

No more yelling at smart speakers. Texas Instruments (TI) introduced a new audio analog-to-digital converter (ADC) capable of capturing clear audio up to four times farther away than competing devices. The new TI Burr-Brown TLV320ADC5140 audio ADC enables far-field voice capture and achieves a 120-dB dynamic range for clear, high-fidelity audio in smart home applications. The TLV320ADC5140 is the industry’s smallest quad-channel audio ADC with this level of performance.

NXP Announces New Dual-Core Arm Cortex-M Based GHz Crossover Microcontroller for Advanced Machine Learning Applications

October 4, 2019 by audioXpress Staff

NXP Announces New Dual-Core Arm Cortex-M Based GHz Crossover Microcontroller for Advanced Machine Learning Applications

NXP Semiconductors announced the i.MX RT1170 family of crossover MCUs that combines unprecedented levels of performance, reliability, and integration to propel industrial, automotive and consumer machine learning applications. The NXP i.MX RT1170 family reinforces NXP’s commitment to advance edge computing with its EdgeVerse portfolio of solutions and marks a technology breakthrough with MCUs that run up to 1GHz while maintaining low-power efficiency.

Qualcomm Launches AI-Enabled Highly Integrated SoCs and Dedicated Smart Speaker Platform

March 19, 2019 by audioXpress Staff

Qualcomm Launches AI-Enabled Highly Integrated SoCs and Dedicated Smart Speaker Platform

Qualcomm made two important announcements for audio developers, both bound to significantly impact the fast-growing market of smart speakers and new generation whole-home audio systems. The San Diego company announced the new QCS400 family of audio SoCs and the Smart Audio Platform 400 development kit, bringing smart speakers high-performance processing, Qualcomm AI Engine, superior connectivity, and multiple advanced audio and visual display capabilities in a single, power-optimized chip architecture.

QuickLogic Announces Time Series EOS S3AI Development Platform for Endpoint AI and Machine Learning Applications

March 18, 2019 by audioXpress Staff

QuickLogic Announces Time Series EOS S3AI Development Platform for Endpoint AI and Machine Learning Applications

QuickLogic, the developer of ultra-low power multi-core voice-enabled SoCs, embedded FPGA IP, and Endpoint AI solutions, announced the launch of its EOS S3AI platform for endpoint Artificial Intelligence (AI) and Machine Learning (ML) applications. The new AI platform provides all the hardware blocks needed to enable low power AI at the connected device endpoint. It comes with time-series (continuous) sensors, including accelerometer / gyroscope / magnetometer motion sensors and two digital microphones (PDMs).

«
1
2
3
»