Telephonic communications – Audio message storage – retrieval – or synthesis – Voice activation or recognition
Reexamination Certificate
2002-08-20
2004-09-21
Tsang, Fan (Department: 2645)
Telephonic communications
Audio message storage, retrieval, or synthesis
Voice activation or recognition
C704S275000
Reexamination Certificate
active
06795533
ABSTRACT:
This application claims priority of UK application No. 0120672.1 filed Aug. 24, 2001. That application is incorporated herein by reference.
FIELD OF THE INVENTION
The present invention relates in general to voice recognition systems for telephony, and more specifically to a method and apparatus for providing voice and tone detection prior to allocation of a speech recognition engine to a call.
BACKGROUND OF THE INVENTION
The integration of speech recognition into modern day PBX systems provides new user interface capabilities to augment traditional telephone device DTMF tones and ‘feature’ keys for call control. Speech recognition capabilities may be provided through the allocation of speech recognition engines (SREs) to a call in progress. For example, PBX systems manufactured by Mitel Networks Corporation may be configured with a number of ports for allocating Speak@Ease™ SRE resources. Each SRE resource is a general purpose “device” which provides all speech recognition and related capabilities (which may be composed of one or more processes). These capabilities include, but are not limited to, voice detection, DTMF detection, voice recognition, and application processing.
As speech recognition becomes more common, it is anticipated that a much larger number of SRE resources will be required to accommodate increased utilization. The provisioning of additional SRE resources to meet anticipated usage increases the overall cost of a PBX installation. As a result, the potential penetration of speech recognition applications is subject to cost considerations and is limited except where cost justified.
According to the existing state-of-the-art, SRE resources are associated with a call whenever there is a potential need for speech recognition, regardless of whether speech recognition is actually invoked during the call. Consequently, PBX systems are now configured with a plurality of SRE resources that are dedicated to servicing one or more speech recognition applications, in a PBX network. When all of the SRE resources are in use, subsequent requests for the supported speech recognition applications are denied or deferred until an SRE resource becomes available. When the SRE is servicing a user, all capabilities are provided, regardless of utilization. For example, if a user initiates a request for which an SRE is allocated and simply dials digits at the telephone device (i.e. dialing the destination number rather than speaking the name) then the full capabilities of the SRE are underutilized. However, as indicated above call control allocates the SRE resource whenever speech recognition may be required, regardless of actual utilization.
SUMMARY OF THE INVENTION
According to the present invention, a voice and DTMF detector resource (VDD) is allocated to a call prior to allocating an SRE resource. The SRE resource is only allocated when speech recognition capabilities are required. The Voice and DTMF detector resource (VDD) is a limited capability digital signal processor that can be provided in volume at relatively low cost (using existing Digital Signal Processing (DSP) technology). The presence or absence of the Voice and DTMF detector resource (VDD) does not impact the SRE resource.
REFERENCES:
patent: 4742534 (1988-05-01), Verbeek et al.
patent: 5459781 (1995-10-01), Kaplan et al.
patent: 6160877 (2000-12-01), Tatchell et al.
patent: 6292675 (2001-09-01), Nilsson
patent: 6405033 (2002-06-01), Kennedy et al.
patent: 2 323 114 (1999-02-01), None
patent: 6-303320 (1994-10-01), None
patent: WO 00/49790 (2000-08-01), None
WO 00/49790, A. Kurganov, Speech-recognition-based phone numbering plan, Aug. 24, 2000.*
Search Report EP 02 25 5290, Feb. 4, 2003, Hague.
Erb Paul Andrew
Schulz Dieter
Chow Ming
Fulwider Patton Lee & Utecht LLP
Mitel Knowledge Corporation
Tsang Fan
LandOfFree
Intermediate voice and DTMF detector device for improved... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Intermediate voice and DTMF detector device for improved..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Intermediate voice and DTMF detector device for improved... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3205615