Network Computingwww.networkcomputing.com

SpeechSC and MRCPv2

Posted by Mike DeMaria on January 19, 2007

Tags: MRCP,  Michael J DeMaria,  SpeechSC and MRCPv2,  TTS,  speaker verification,  speech,  speech processing,  voice,  voice applications,  Emerging specifications,  IP PBX,  Other,  Telephony,  Unified Communications & VoIP,  VoIP,  standards

Channel: Other, UC & VoIP

SpeechSC and MRCPv2 is a vendor-neutral standard designed to enable distributed speech processing with a consistent API between processing engines. Speech recognition, speaker verification and text-to-speech services can be made available to media processing devices without modifying existing multimedia protocols.. Cisco and Cantana are the chairs of the SpeechSC working group. Several speech processing vendors, such as Nuance Communications and Voxpilot, are also contributors. Missing from the list of SpeechSC members are big IP-PBX vendors that already offer VoIP and speech support, such as Avaya and Siemens. Microsoft has not taken a position yet. The SpeechSC framework and MRCPv2 will be beneficial to small speech-processing vendors and integrators. IP-PBX vendors that do not have robust speech-processing capabilities will be able to more easily integrate third-party products, and speech application developers will have a fixed and predictable method of processing audio streams. Not requiring modification to the existing SIP and RTP standards was a wise move by the working group and should help ease adoption of MRCPv2.

Anyone who develops, deploys or uses a voice application knows the benefits of speech processing; the technology enables functions such as sending e-mail or instant messages over the corporate PBX with a cell phone using TTS (text-to-speech) technology. However, setting up these capabilities isn't easy, and a standard method of processing and controlling audio streams across network resources has been conspicuously absent.

The IETF's SpeechSC (Speech Services Control) working group is out to fix that problem with MRCP (Media Resource Control Protocol) version 2. The specification will allow any voice application to control network-based media resources, such as speech synthesizers and recognizers. The working group's ultimate goal is to encourage the development of--and lower the financial bar to--new speech-enabled applications.

Speech-processing vendors such as Nuance Communications and Voxpilot are on board, as is Cisco Systems, and MRCPv2 speech engines are already coming out, despite the standard still being in development.

However, the standard is getting the cold shoulder from some significant players. Microsoft hasn't taken an official position on it, and it's one of the few heavyweights with a stake in the speech-processing market not to commit. Most major PBX vendors haven't committed to the standard either, though we suspect that MRCPv2 will quietly gain support from PBX vendors through their relationships with speech-processing vendors.