Claims
- 1. A method for enhancing the accuracy and efficiency of a speech recognition system which processes input frames of speech against stored templates representing speech utilizing a telephonic network, said method comprising the steps of;
- creating and storing a core library of speech templates;
- creating and storing a plurality of caller-specific libraries of speech templates which each include a vocabulary and pronunciation reflective of a specific geographic location;
- attempting to determine an identification of a caller location by utilizing a caller identification system within said telephonic network;
- processing an input speech utterance against said core library of speech templates in the event an identification of said caller location within said telephone network is not determined; and
- processing an input speech utterance against a particular one of said plurality of caller-specific libraries of speech templates in response to a determination of an identification of said caller location within said telephonic network.
- 2. The method for enhancing the accuracy and efficiency of a speech recognition system which processes input frames of speech against stored templates representing speech via a telephonic network according to claim 1, wherein said step of creating and storing a plurality of caller-specific libraries of speech templates comprises the step of creating and storing a plurality of caller-specific libraries of speech templates which are processed to reflect variations in each speech utterance which occur as a result of a transmission of each speech utterance within said telephonic network.
- 3. A system for enhancing the accuracy and efficiency of a speech recognition system which processes input frames of speech against stored templates representing speech utilizing a telephonic network, said system comprising:
- means for creating and storing a core library of speech templates;
- means for creating and storing a plurality of caller-specific libraries of speech templates which each include a vocabulary and pronunciation reflective of a specific geographical location;
- means for attempting to determine an identification of a caller location utilizing a caller identification system within said telephonic network;
- means for processing an input speech utterance against said core library of speech templates in the event an identification of said caller location within said telephone network is not determined; and
- means for processing an input speech utterance against a particular one of said plurality of caller-specific libraries of speech templates in response to a determination of an identification of said caller location within said telephonic network.
- 4. The system for enhancing the accuracy and efficiency of a speech recognition system which processes input frames of speech against stored templates representing speech via a telephonic network according to claim 5, wherein said means for creating and storing a plurality of caller-specific libraries of speech templates comprises means for creating and storing a plurality of caller-specific libraries of speech templates which are processed to reflect variations in each speech utterance which occur as a result of a transmission of each speech utterance within said telephonic network.
Parent Case Info
This is a continuation of application Ser. No. 08/175,707, filed 30 Dec., 1993 now abandoned.
US Referenced Citations (30)
Non-Patent Literature Citations (1)
Entry |
Jelinek, "Continuous speech recognition by statistical methods"; proceedings of the IEEE, vol. 64 No. 4, Apr. 1976, pp. 532-556. |
Continuations (1)
|
Number |
Date |
Country |
Parent |
175707 |
Dec 1993 |
|