MWC 2016: Audio framework for HiFi DSP processors

25th February 2016

Mick Elliott

0 0

An audio software framework that provides OEMs and application developers faster time to market when integrating Tensilica HiFi DSP-based systems on chip (SoCs) into their products has been introduced by Cadence. The announcement also includes the availability of the first hardware integration into the Android Studio development platform.

Cadence demonstrated the “OK Google” voice trigger and audio playback integration with Android Studio and the Realtek ALC5677 at the Mobile World Congress in Barcelona.

The HiFi Integrator Studio provides a standard operating-system (OS)-agnostic software framework to interface audio, voice and sensor functions running on the HiFi DSP to higher level applications such as media players or recorders.

It enables high-level application programmers using Java/C++ to leverage the power-savings and acceleration benefits of the HiFi DSP without having to understand the low-level programming details of a real-time DSP.

The HiFi Integrator Studio currently supports two main use cases, with additional ones in development.

The first use case is targeted at SoCs where the HiFi DSP is the main processor, such as in a Bluetooth headset.

The second use case is targeted at systems where a host application processor (AP) offloads audio and/or voice tasks to the HiFi DSP processor.

Examples include using the HiFi DSP as part of the AP SoC and/or in codec chips for ultra-low-power, glitch-free audio playback, and noise suppression and echo cancellation for superior voice experience.

The Android OS version demonstrates a complete end-to-end application from Java applications at the top, to Android Marshmallow-based middleware, to offloaded code running on the HiFi DSP—all in the Android Studio development environment.