Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
2000-07-28
2003-07-29
McFadden, Susan (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S275000, C379S088180
Reexamination Certificate
active
06601031
ABSTRACT:
TECHNICAL FIELD
This invention relates to a speech recognition system and more particularly to a speech recognition system that provides control information to a further system, such as a voice mail system.
BACKGROUND OF THE INVENTION
Voice mail systems, also known as voice messaging systems, have been in use for decades. They are so well known and so useful that voice mail systems are found almost everywhere. Voice mail system (VMS)
5
shown in
FIG. 1
is such a system. Examples for VMSs for commercial use are the Sierra system originally from Octel, now from Lucent Technologies, 600 Mountain Avenue, Murray Hill, N.J. Such systems are not only found in businesses, but now commercial counterparts are also in found in private homes where individuals can subscribe to voice mail boxes or buy answering machines. Historically both voice mail systems and answering machines have been controlled by DTMF signals generated from a touch button keypad and sent over a network. These DTMF signals control playback, delete, skip, forward, reply, change greetings, help, and similar voice mail system control functions. The trouble of using a push button key pad and keeping all the numbers straight has left many subscribers/users with a desire for something better and easier to use.
There is growing interest in providing speech recognition control to VMSs. This interest may be due to competition in the voice mail market or due to the growing need for “hands-free” services to mobile users. Though there may be a strong desire to provide speech recognition, it must also be recognized that many companies have a significant investment in their legacy VMSs. These companies are not interested in discarding their present systems. Nor are many of them rushing out to make even more significant investments in next generation VMSs, such as voice mail system
5
′ shown in
FIG. 2
, which has speech recognition hardware and software built in. These companies would rather use speech recognition as an enhanced service offering paid for by a service provider, but want the service at a reasonable price.
Besides adding speech recognition to the information left at a voice mail system, improvements to the interface to the Voice Mail system might be possible through a control link of some kind. Such a control link might tie the voice mail system to a Speech Recognition System through voice and control links. Presently, it is difficult to interface to existing voice mail systems at the control level beyond the DTMF level. Existing voice mail systems generally provide proprietary internal software and hardware interfaces that would be technically difficult to interface to. Interfacing through these existing voice mail interfaces would require significant development, require control and data interfaces to the voice mail system, and the end result would be a questionable service probably with delays. Therefore, it is desirable to provide a method and apparatus that would do away with the control interface issue.
SUMMARY OF THE INVENTION
Briefly stated in accordance with one aspect of the invention, the aforementioned long felt needs are addressed by providing a speech recognition system (SRS) that is used as a front end to an attached voice mail system. This SRS provides a speech recognition control using a speech recognition proxy with a hairpin connection arrangement. When a subscriber calls the Voice Mail system, the subscriber gets connected to the SRS. The SRS automatically calls the Voice Mail system, thereby forming a hairpin connection. This hairpin connection is different, though, because the SRS has control over the voice paths to and from the subscriber and the Voice Mail system. Additionally, the SRS listens to the subscriber's line for speech or DTMF. When recognized, the SRS outputs to the Voice Mail system a DTMF equivalent response to the speech or DTMF received from the subscriber's line. This operation is why this method and apparatus is referred to as a speech recognition proxy.
REFERENCES:
patent: 5757806 (1998-05-01), Koyama et al.
patent: 5915001 (1999-06-01), Uppaluru
patent: 6088428 (2000-07-01), Trandal et al.
patent: 6094476 (2000-07-01), Hunt et al.
patent: 6208959 (2001-03-01), Jonsson et al.
patent: 6304573 (2001-10-01), Hicks, III
patent: 6308062 (2001-10-01), Chien et al.
patent: 6366669 (2002-04-01), Meynekhdrun
patent: 6370238 (2002-04-01), Samsone et al.
patent: 6370506 (2002-04-01), Ahluwalia
patent: 6377662 (2002-04-01), Hunt et al.
patent: 6377825 (2002-04-01), Kennedy et al.
patent: 6385304 (2002-05-01), Hunt et al.
patent: 6385585 (2002-05-01), Jonsson et al.
patent: 6396909 (2002-05-01), Reksten et al.
patent: 6459774 (2002-10-01), Ball et al.
Lucent Technologies - Inc.
McFadden Susan
LandOfFree
Speech recognition front end controller to voice mail systems does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Speech recognition front end controller to voice mail systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition front end controller to voice mail systems will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3095959