NXP Advances AI Audio processing with SAF9xxx Audio DSPs
The new NXP SAF9xxx family introduces the latest-generation automotive, AI and machine learning (ML) capable audio DSP technology, integrating a neural network engine and hardware-based accelerators
image for illustrative purpose
Hyderabad: NXP® Semiconductors today announced the SAF9xxx family, bringing AI audio capabilities to automotive infotainment and marking a significant improvement in automotive audio processing technology. The new audio digital signal processing (DSP) solution is designed to support the ever-increasing demand for AI-based audio in software-defined vehicles (SDVs). Using Cadence’s latest generation high-performance Tensilica HiFi 5 DSPs, combined with dedicated neural-network engines, the SAF9xxx enables efficient implementation of next-generation, high-quality, self-learning audio and speech applications, a media release here says.
Additionally, the SAF9xxx family comes with a software-defined radio option with up to 5 integrated tuners, covering all major global broadcast radio use cases, including DAB, HD-Radio, DRM, CDR, and AM/FM—making this a truly one-chip device supporting audio and radio applications with easy scalability in mind.
Audio performance is a major differentiator for automotive infotainment, providing OEMs with new ways to make mid-range and high-end vehicles stand out. The SAF9xxx’s machine learning capabilities with neural network integration opens up a new world of functionalities. For example, this can be used to recognise and distinguish the driver from passengers by identifying their voice pitches and accents. Emergency vehicle sirens can be detected with machine learning algorithms, and used to provide drivers with audiovisual information about the location and movement of an emergency vehicle.
John van den Braak, Senior Vice President and General Manager for Audio Systems at NXP, explains: “The NXP SAF9xxx DSP is a ready-made infotainment solution. Designed with AI/ML processing capability in mind, it provides more functionality, better performance, and more features to support the demanding audio and radio requirements of both current and future software-defined vehicles. And its scalable architecture makes it simpler and more affordable for OEMs to deploy in their vehicle design.”
The SAF9xxx family is optimised for low-latency audio applications, enabling real-time active cancellations of engine, road, wind, and tire noise.
Gigahertz-DSP performance is complemented by a large, fast-access onboard memory and a comprehensive set of analogue and digital I/Os that support demanding audio features.
Gigabit-Ethernet supports fast and direct connection to the vehicle network.
A large audio IP partner ecosystem is ready to kickstart new audio developments on SAF9xxx with an extensive range of audio software and algorithms.
SAF9xxx availability and enablement The SAF9xxx family is set to debut at the Audio Engineering Society 5th International Conference on Automotive Audio from June 26-28, 2024.
