Method and apparatus to perform speech recognition over a voice channel
First Claim
Patent Images
1. A method to perform speech recognition, comprising:
- receiving a set of signals representing speech;
receiving a request for speech recognition information over a wireless voice channel in a wireless network, wherein receiving said request comprises receiving a subrogation indicator;
creating a set of speech features from said signals; and
when said subrogation indicator is detected;
replacing said set of signals representing speech with said speech features; and
communicating said speech features over said wireless voice channel in said wireless network at a lower bandwidth than a bandwidth used to send said set of signals representing said speech.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and apparatus to perform speech recognition over a voice channel is described.
18 Citations
38 Claims
-
1. A method to perform speech recognition, comprising:
-
receiving a set of signals representing speech; receiving a request for speech recognition information over a wireless voice channel in a wireless network, wherein receiving said request comprises receiving a subrogation indicator; creating a set of speech features from said signals; and when said subrogation indicator is detected; replacing said set of signals representing speech with said speech features; and communicating said speech features over said wireless voice channel in said wireless network at a lower bandwidth than a bandwidth used to send said set of signals representing said speech. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method to perform speech recognition, comprising:
-
sending a request for speech recognition information over a wireless voice channel in a wireless network, wherein said sending comprises replacing a set of signals representing speech with speech features and sending a subrogation indicator to initiate a communication of said speech features over said wireless voice channel in said wireless network at a lower bandwidth than a bandwidth used to send said set of signals representing speech when said subrogation indicator is detected; receiving said speech features over said voice channel; and recognizing speech using said speech features. - View Dependent Claims (13, 14, 15, 16)
-
-
17. A system to perform speech recognition, comprising:
-
a wireless source node to receive a subrogation indicator and to replace a set of signals representing speech with speech features and to send said speech features over a wireless voice channel at a lower bandwidth than a bandwidth used to send said set of signals representing speech when said subrogation indicator is detected; a destination node to receive said speech features and perform speech recognition; and a wireless network to communicate said speech features between said wireless source node and said destination node by overlaying said speech features on a wireless voice channel. - View Dependent Claims (18, 19, 20, 21, 22)
-
-
23. A speech recognition encoder, comprising:
-
a capabilities monitor to monitor for a request for speech recognition information, wherein said speech recognition information comprises a subrogation indicator; a vocoder to create a first stream of bits representing speech; a feature encoder to create a second stream of bits representing speech features of said speech; and a feature overlayer to overlay said first stream of bits with said second stream of bits and to communicate over a wireless voice network said second stream of bits at a lower bandwidth than a bandwidth used to communicate said first stream of bits representing said speech when said subrogation indicator is detected. - View Dependent Claims (24)
-
-
25. A speech recognition decoder, comprising:
-
a capabilities broadcaster to communicate a speech recognition request, wherein said capabilities broadcaster communicates a subrogation indicator to initiate a communication of a stream of bits having speech features over a wireless voice channel in a wireless network at a lower bandwidth than a bandwidth used to communicate a set of signals representing speech when said subrogation indicator is detected; a start monitor to monitor for a said stream of bits having speech features; a feature decoder to decode said speech features from said stream of bits; and a speech recognition module to translate said speech features into text. - View Dependent Claims (26)
-
-
27. An article comprising:
-
a storage medium; said storage medium including stored instructions that, when executed by a processor, result in performing speech recognition by receiving a set of signals representing speech, receiving a request for speech recognition information over a wireless voice channel in a wireless network, wherein receiving said request comprises receiving a subrogation indicator, creating a set of speech features from said signals, and when said subrogation indicator is detected;
replacing said set of signals representing speech with said speech features; and
communicating said speech features over said wireless voice channel in said wireless network at a lower bandwidth than a bandwidth used to send said set of signals representing said speech. - View Dependent Claims (28, 29, 30, 31, 32, 33, 34)
-
-
35. An article comprising:
-
a storage medium; said storage medium including stored instructions that, when executed by a processor, result in performing speech recognition by sending a request for speech recognition information over a wireless voice channel in a wireless network, wherein said sending comprises replacing a set of signals representing speech with speech features and sending a subrogation indicator to initiate a communication of said speech features over said wireless voice channel in said wireless network at a lower bandwidth than a bandwidth used to send said set of signals representing speech when said subrogation indicator is detected, receiving said speech features over said voice channel, and recognizing speech using said speech features. - View Dependent Claims (36, 37, 38)
-
Specification