Conexant AudioSmart Speech Processing Optimized for Cadence Tensilica HiFi DSPs

Cadence Design Systems and Conexant Systems announced that Conexant's AudioSmart software has been optimized for the Cadence Tensilica HiFi digital signal processor (DSP) family.

Conexant's AudioSmart software provides clear voice quality, eliminates noise from the microphone input signal during VoIP calls, and improves automatic speech recognition (ASR) system performance. The result is a superior audio experience for the end user, with excellent listening performance and voice quality in noisy, real-world conditions.

"Whether conducting calls in a noisy environment or giving verbal commands to an always-on device, the AudioSmart software addresses challenges with background noise and competing sounds," said Larry Przywara, group director of audio/voice IP marketing, Cadence, in a statement. "After seeing this software demonstrated, we're very excited that Conexant selected the Tensilica HiFi DSP for their first port to a DSP IP core. This technology should be very useful in a variety of markets, including automotive, computing, and consumer electronics."

Conexant's AudioSmart software is based on its proprietary Smart Source Pickup (SSP) noise suppression algorithm. Unlike traditional technologies, such as beamforming, SSP is a blind source separation technology that uses spatial representation of target speech and noise sources to reduce interference. For example, SSP is extremely effective at reducing keystroke noise distractions during conference calls and other computer-based voice communications.

With SSP, speech and noise can arrive at any angle relative to the microphones; SSP even reduces noise when it comes from the same direction as desired speech, and when the speaker is up to five meters away from the target device. In addition, AudioSmart allows users to experience excellent voice quality independent of device orientation or the user's position (angle) relative to the device.

"By porting our solution to the Tensilica HiFi architecture, we are bringing the Conexant audio experience to licensees of the most popular audio IP core architecture," said Saleel Awsare, Conexant vice president and general manager, in a statement. "In addition, our software greatly improves the performance of other technologies also running on the Tensilica core. Technologies that make use of speech recognition, such as an always-on voice engine, can benefit from crystal clear audio facilitated by AudioSmart."

The Tensilica HiFi DSP, based on the Xtensa processor platform, is the most widely used and licensable audio/voice DSP IP family, with support for over 150 proven audio/voice software packages and over 70 software partners. 

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues
Related Articles

Conexant AudioSmart Certified for Skype for Business

Conexant offers a Microsoft-certified Skype for Business group speakerphone PC.

Qualcomm to Integrate Conexant AudioSmart into Hexagon DSPs

Conexant will bring its far-field microphone processing software to Qualcomm Hexagon digital signal processors.

LG Turns to Conexant for Voice Control of Smart Home Devices

Conexant's CX2092x chips will power the voice interface for LG's tvG Woofer set top box and IoT Hub.

Conexant Releases New Voice Control Processors

The CX20924 and CX20926 systems both feature far-field pick-up and low-power consumption for voice-enabled devices.

DSP Concepts Enhances Audio Weaver to Support Cadence Tensilica HiFi DSPs

DSP's Audio Weaver development environment has been optimized for Cadence's Tensilica HiFi Audiuo/Voice processors.