AKM Starts Sampling AK7749 DSP-Integrated CODEC for In-Vehicle Voice Applications

Asahi Kasei Microdevices Corporation (AKM) has developed and started the release of samples of the AK7749, an in-vehicle DSP-integrated CODEC with an automatic mode switching function to support voice applications, and a full range of digital and analog input/output interfaces. The AK7749 is a RAM based, highly integrated, programmable digital signal processor, with 4 channel ADCs, 2 channel DACs, a MIC gain amplifier, a line-out amplifier, 4 channel SRCs, and digital audio I/F, all in a space saving small 48-pin QFN package.

Voice processing and recognition leading to the development of voice-based personal assistants is one of the decade’s greatest achievements and provides a unique opportunity for the audio industry. Leveraging those sophisticated technologies now available to the consumer electronics industry makes the investment on new designs much more exciting. In this article, Mike Klasco provides an introduction to the voice capture, signal processing and voice recognition challenges. This article was originally published in audioXpress, December 2018.

In previous editorials, I have highlighted the important role of smart speakers in promoting the user case for voice personal assistants (VPAs) and voice recognition applications - given the ideal combination of far-field microphone arrays with a complete audio ecosystem that encompasses digital signal processing, acoustic echo cancelation, noise cancellation, and many other technologies. This opens significant opportunities for the audio industry, given we understand the challenges.

Cirrus Logic introduced a development kit for Alexa Voice Service (AVS), optimized for smart speakers and smart home applications including voice controlled devices, hands-free portable speakers and networked speakers. With the Cirrus Logic IC and software design, the Voice Capture Development Kit for Amazon AVS helps manufacturers quickly get to market with new Alexa-enabled products that feature high-accuracy wake-word triggering and command interpretation even in noisy environments and during music playback.

According to the latest report from SAR Insight & Consulting, strong growth is expected for all voice software, driven by its inclusion in increasing numbers of voice-enabled devices and by the increased use of digital assistants. “SAR has repeatedly discussed the scale and opportunity of the voice tech market,” says Peter Cooney, principal analyst at SAR. “Voice will be the main interface technology for many devices and the opportunities for hardware and software vendors will be huge.”