News Archive (1999-2012) | 2013-current at LinuxGizmos | Current Tech News Portal |    About   

Continuous-speech recognition ported to Alchemy SOC

Sep 17, 2001 — by LinuxDevices Staff — from the LinuxDevices Archive — views

Austin, TX — (press release excerpt) — Alchemy Semiconductor, Inc. announced an agreement with Philips Speech Processing to port Philips' VoCon continuous-speech recognizer for embedded systems to Alchemy's family of microprocessors. This integration will allow OEMs to integrate voice capabilities into products being developed with Alchemy's family of MIPS32 ISA compatible processors. The initial port will target Microsoft Windows CE, with Embedded Linux to follow later this year.

The VoCon software package is a noise-robust, fast, and highly accurate continuous-speech recognition solution specifically designed for embedded devices such as the ones targeted by Alchemy in the Internet Device market. VoCon enables a variety of voice-controlled applications, including command and control, name and continuous-digit dialing, natural number dialing, address book management, and menu navigation. Features include speaker-independent and/or speaker-dependent recognition in isolated or continuous speech. In addition, VoCon offers advanced features such as whole-word or phoneme-based recognition, word spotting, and enhanced noise and acoustic signal cancellation. VoCon is available in several languages including US and UK English, French, German, Spanish, Portuguese, Dutch, Italian, and more.

Availability will begin in Q4 2001 and the VoCon speech recognizer will be licensed directly from Philips Speech Processing.



 
This article was originally published on LinuxDevices.com and has been donated to the open source community by QuinStreet Inc. Please visit LinuxToday.com for up-to-date news and articles about Linux and open source.



Comments are closed.