Tensilica Supports Adaptive Multi-Rate Speech Codec On Its Xtensa HiFi Audio Engine

Update: Cadence Completes Acquisition of Tensilica (Apr 24, 2013)

Enables Rapid Deployment of 3GPP-Compliant Cellular Phones with Advanced Speech Capabilities

SANTA CLARA, Calif., August 16, 2004 – Tensilica, Inc., today announced it has added support for the Adaptive Multi-Rate (AMR) speech codec to its comprehensive offering of audio solutions for the Xtensa® HiFi Audio Engine. A mandatory requirement in the 3GPP (3G Partnership Project) specification, high-performance AMR functionality will enable companies to rapidly develop application-specific processors that are in compliance with both the narrowband and wideband versions. Moreover, availability on Tensilica’s unique Xtensa microprocessor platform enables designers to optimize their devices for the unique power, size and performance requirements of 3G cellular phones. 

“As cellular phones become increasingly feature-rich, handset manufacturers must support a multitude of audio formats without sacrificing battery life or form factor,” said Larry Przywara, director of strategic alliances for Tensilica. “Traditional microprocessor and DSP cores limit the designer’s ability to meet these requirements because the devices often must be coupled with custom logic in order to support new features.  Tensilica’s platform gives designers the tools they need to easily and automatically add this functionality directly into the processor, along with their own custom features, so that they can rapidly deploy optimized, differentiated 3G cellular phone solutions.”

Tensilica’s new AMR codec allows customers to add support for both narrowband and wideband speech, a requirement of the 3GPP specification for 3G GSM cellular phones. The speech codec is designed to bring significant improvements in terms of interoperability, easier implementation, and improved quality for voice applications and services across a wide range of communication systems and platforms.

Tensilica has added support for the AMR speech codec to its Xtensa HiFi Audo Engine, a 24-bit embedded audio processor that offers inherent advantages over the industry-standard, 16-bit audio processors in use today. The Xtensa HiFi Audio Engine is an add-on package for Tensilica’s proven Xtensa processor core.  The engine provides superior sound quality of compressed files due to the increased precision available for intermediate calculations in the compression and decompression algorithms. 

One-Stop Shop for all Audio Needs

The availability of the AMR speech codec on the Xtensa processor platform means that customers now have a one-stop shop for all of their audio needs. Tensilica’s comprehensive support for the industry’s most pervasive audio and speech codecs includes Dolby Digital AC-3 decode, Dolby Digital AC-3 consumer encode, MP3 decode, MP3 encode, MPEG-2 AAC decode, MPEG-4 AAC decode, MPEG-4 AAC encode, and WMA decode. It also supports G723-1 and G729AB speech codecs for highly optimized, multi-standard, voice-over-IP (VoIP) SOC designs. One Xtensa HiFi Audio Engine can run all of these codecs because it’s fully programmable.

All audio packages have been fully optimized to take advantage of Tensilica’s industry leading microprocessor performance.  All were designed to minimize the amount of external ROM and RAM required, making them ideal for low-cost, battery driven applications. The entire Xtensa audio solution (Xtensa V processor plus Xtensa HiFi Audio Engine) consumes only about 100,000 gates, which represents a small portion of today’s multi-million gate SOC designs.  In addition, the solution enables very low power consumption, measured at just 0.4 milliwatts per MHz in a 0.13-micron process.

Development Partner – CuTe Solutions

As with Tensilica’s previous audio solutions, Tensilica’s AMR speech codec was designed and developed by CuTe Solutions. CuTe Solutions’ is a recognized expert in the development of advanced audio algorithms, and the associated optimized TIE instructions.

Pricing and Availability

The AMR speech codec is available by licensing Tensilica’s Xtensa HiFi Audio Engine. Pricing for the engine and one audio decoder is as low as $38,000 and requires an Xtensa processor license. The AMR speech codec software is available now.

About Tensilica

Tensilica was founded in July 1997 to address the growing need for optimized, application-specific microprocessor solutions in high-volume embedded applications. With the Xtensa and Xtensa LX configurable and extensible microprocessor cores, Tensilica is the only company that has automated and patented the time-consuming process of generating a customized microprocessor core along with a complete software development tool environment, producing new configurations in a matter of hours. These customized processors rival hand-coded RTL in performance and add a needed level of programmability. For more information, visit www.tensilica.com.

# # #

Editors’ Notes:

• “Tensilica” and “Xtensa” are registered trademarks belonging to Tensilica Inc. All other trademarks are the property of their respective holders.
• Tensilica’s announced licensees are Agilent, ALPS, AMCC (JNI Corporation), Astute Networks, Avision, Bay Microsystems, Berkeley Wireless Research Center, Broadcom, Cisco Systems, Conexant Systems, Crimson Microsystems, Cypress, ETRI, FUJIFILM Microdevices, Fujitsu Ltd., Hudson Soft, Hughes Network Systems, Ikanos Communications, LG Electronics, Marvell, Mindspeed Technologies, National Semiconductor, NEC Laboratories America, NEC Corporation, NetEffect, Nippon Telephone and Telegraph (NTT), Olympus Optical Co. Ltd., S2io, Sony, Solid State Systems, STMicroelectronics, TranSwitch Corporation, and Victor Company of Japan (JVC).