All items tagged with smart speakers and speech recognition (10)

R&D Stories: Speaker ID Technology

April 26, 2021 by Vikrant Singh Tomar

R&D Stories: Speaker ID Technology

As part of its focus on voice convergence, in its April 2021 edition, audioXpress featured a contributed article by the founder and CEO of Fluent.ai, describing how increasing consumer demand for personalized experiences has sparked the creation of the company’s speaker ID technology, and exploring the challenges that this type of technology still faces. A valuable perspective from a company positioned right at the edge of voice recognition using AI and edge processing. This article was originally published in audioXpress, April 2021.

Kakao Enterprise and DSP Concepts Raise the Bar for Voice Performance in Mini Hexa Smart Speaker

January 20, 2021 by Joao Martins

Kakao Enterprise and DSP Concepts Raise the Bar for Voice Performance in Mini Hexa Smart Speaker

DSP Concepts announced it partnered with South Korea's Kakao Enterprise to enable the voice user interface in its latest Mini Hexa smart speaker (KE-H200). The Mini Hexa is the company’s fourth smart device to be released and uses DSP Concepts’ TalkTo audio front end to eliminate unreferenced sound for far-field voice control in noisy and unpredictable environments. The result ensures flawless speech recognition regardless of external sound for an optimal user experience.

Amazon Reimagines Echo Smart Speaker Family for 2020

September 29, 2020 by Joao Martins

Amazon Reimagines Echo Smart Speaker Family for 2020

Amazon.com introduced its all-new line-up of Echo devices, featuring completely new designs, enhanced audio, more powerful hardware, and experiences that make Alexa voice assistant more engaging, and helpful. Most of the new Amazon products will be available at the end of October 2020, and that includes an all-new Echo (4th Gen), now with better sound and integrated smart home hub; the new Echo Dot and Echo Dot Kids Edition featuring the new spherical designs and improved audio, and Echo Show 10, the smart speaker with screen.

AKM Develops Ultra-Low Power Intelligent System Wakeup ADC With Integrated Acoustic Activity Analyzer

July 21, 2020 by audioXpress Staff

AKM Develops Ultra-Low Power Intelligent System Wakeup ADC With Integrated Acoustic Activity Analyzer

Asahi Kasei Microdevices Corporation (AKM) has developed the AK5706, a high-performance 24-bit stereo A/D converter (ADC) with an integrated Acoustic Activity Analyzer (AAA) wakeup solution consuming only 30μA, audio buffer, and support for digital and high-SNR microphones. Designed for systems that must listen for specific types of audio activity while consuming very low power, the AK5706 is ideal for products such as speech recognition systems, as well as security and smart home devices.

Waves Unveils New Audio Testing Labs in Taipei

October 7, 2019 by audioXpress Staff

Waves Unveils New Audio Testing Labs in Taipei

Waves is opening a new state-of-the-art audio and voice testing labs at the company's Taipei location, establishing a commitment to support the growing market for voice-enabled connected devices. The new facilities include 4 ETSI testing labs and one custom designed anechoic chamber for precision acoustic measurements. The labs are designed for testing voice communication and automatic speech recognition technologies for smart speakers and other mobile devices.

Practical Test & Measurement: The Smart Way of Testing Smart Home Devices

June 12, 2019 by Hans W. Gierlich

Practical Test & Measurement: The Smart Way of Testing Smart Home Devices

In this article for audioXpress, Hans W. Gierlich, managing director of HEAD acoustics, explains how to test the different performance parameters of smart speakers and smart home devices under real-life conditions, how to deal with the challenges of optimizing systems for voice and audio quality, how to simulate environmental conditions, user behavior, and test the performance of the various functionalities. This article was originally published in audioXpress, January 2019.

Sensory Acquires Vocalize.ai for Speech Technology Testing Capabilities

February 14, 2019 by audioXpress Staff

Sensory Acquires Vocalize.ai for Speech Technology Testing Capabilities

Sensory Inc., a Silicon Valley company that pioneered speech recognition and AI in consumer electronics, announced the acquisition of Vocalize.ai, a software tools and services company that performs benchmarking, accuracy assessments and bias evaluations for speech technologies and natural language interfaces. As part of the acquisition, Sensory will maintain Vocalize.ai as an independently operated division.

HEAD acoustics Improves Evaluation of Voice Control Systems

May 24, 2018 by Joao Martins

HEAD acoustics Improves Evaluation of Voice Control Systems

HEAD acoustics has launched a new version of VoCAS (Voice Control Analysis System), the company’s software for evaluating voice control systems. The turnkey test solution now supports the company’s modular multi-channel labCORE front end. According to the Herzogenrath, Germany-based company, VoCAS offers manufacturers even more possibilities to test their ASR system (Automatic Speech Recognition) in vehicles, mobile phones or smart speakers objectively and reproducibly.

Ambiq Micro, DSP Concepts and Sensory Join Forces to Bring Always-On Voice Control to Portable, Battery-Operated Devices

January 12, 2018 by audioXpress Staff

Ambiq Micro, DSP Concepts and Sensory Join Forces to Bring Always-On Voice Control to Portable, Battery-Operated Devices

Ambiq Micro, the pioneer in ultra-low power solutions, announced a partnership with DSP Concepts, a global developer of embedded digital signal processing audio solutions and specialist in voice UI technologies, and Sensory, the leading provider of embedded artificial intelligence (AI) and speech recognition technologies. The collaboration aims to provide extremely power-efficient, always-listening voice control on battery-operated, intelligent devices without sacrificing quality of experience.

Infineon High SNR MEMS Microphones Complement Amazon AVS Far-Field Development Kit from XMOS

October 9, 2017 by audioXpress Staff

Infineon High SNR MEMS Microphones Complement Amazon AVS Far-Field Development Kit from XMOS

XMOS' VocalFusion 4-Mic Dev Kit for Amazon Alexa Voice Service (AVS) for far-field applications integrates Infineon’s high SNR MEMS microphones to ensure highest performance and reliability, creating the first Amazon AVS development kit with a linear mic array for far-field applications. The 4-Mic Development Kit features crystal clear voice capturing even in noisy environments. This enables commands to be accurately captured from across the room for processing by the Alexa cloud-based speech recognition system.