US5724481A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for automatic speech recognition of arbitrary spoken words
Assignee: Nokia of America Corp
•
Filing: 1995-03-30
•
Granted: 1998-03-03
•
Expires: 2015-03-30
Abstract
Abstract A method and system for allowing an automatic speech recognition (ASR) system to recognize arbitrary words, by accessing information in a supplemental data base. A supplemental data base is accessed to retrieve supplementary textual information, such as a proper name. A text-to-speech means is used to generate a phoneme transcription of the text retrieved from the supplemental data base, so that the transcription may be used as a speaker independent template by the ASR system for recognizing a spoken word.
Inventors
- 👤 Roger Borgan Garberg
- 👤 Michael Allen Yudkowsky
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-06 22:02
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/06; G10L15/063; H; H04; H04M; H04M3/00; H04M3/38; H04M3/382; H04M3/42; H04M3/42204; H04Q; H04Q3/00; H04Q3/42; H04M2201/00; H04M2201/40; H04M2201/60; H04M2242/00; H04M2242/22; H04M3/385; H04M3/42025; H04M3/42034; H04M3/42059; H04M3/487; H04M3/493; H04M3/4931; H04Q3/72
Claims Analysis
Total Claims: 18
Claim 1
Independent Claim
120 words
In an automatic speech recognition (ASR) system having a first data base that stores word models and correlation data on which word recognition decisions are at least partially based, a method of utilizing information stored in a supplemental second data base to enhance capability of the ASR system, the method comprising: receiving a first spoken input from a user; the ASR system recognizing the first spoken input from the user; identifying and retrieving text stored in the supplemental data base using the first spoken input, wherein the retrieved text is not a representation of the first spoken input; creating a template of the text retrieved from the supplemental data base; and using the template to recognize a second spoken input.
Claim 2
Dependent Claim
120 words
In an automatic speech recognition (ASR) system having a first data base that stores word models and correlation data on which word recognition decisions are at least partially based, a method of utilizing information stored in a supplemental second data base to enhance capability of the ASR system, the method comprising: receiving a first spoken input from a user; the ASR system recognizing the first spoken input from the user; identifying and retrieving text stored in the supplemental data base using the first spoken input, wherein the retrieved text is not a representation of the first spoken input; creating a template of the text retrieved from the supplemental data base; and using the template to recognize a second spoken input.
Claim 3
Dependent Claim
26 words
The method of claim 1 wherein the step of receiving a first spoken input from a user comprises the step of receiving a spoken telephone number.
Claim 4
Dependent Claim
27 words
The method of claim 2 wherein the step of using the template to recognize a second spoken input comprises the step of using a speech recognition algorithm.
Claim 5
Dependent Claim
28 words
The method of claim 1 wherein the step of creating a template of the text comprises the step of using a text-to-speech system to generate a phoneme transcription.
Claim 6
Dependent Claim
112 words
In a telephone network, a method of using a supplemental data base associated with an automatic speech recognition (ASR) system to enhance the capability of the ASR system, the method comprising the steps of: receiving an incoming call from a caller; prompting the caller for an utterance; recognizing the utterance spoken by the caller; retrieving stored in a supplemental data base using the utterance as an index wherein the text is not a representation of the utterance; creating a speaker independent template of the text as retrieved from the supplemental data base; and using the speaker independent template to recognize another utterance corresponding to the text retrieved from the supplemental data base.
Claim 7
Dependent Claim
112 words
In a telephone network, a method of using a supplemental data base associated with an automatic speech recognition (ASR) system to enhance the capability of the ASR system, the method comprising the steps of: receiving an incoming call from a caller; prompting the caller for an utterance; recognizing the utterance spoken by the caller; retrieving stored in a supplemental data base using the utterance as an index wherein the text is not a representation of the utterance; creating a speaker independent template of the text as retrieved from the supplemental data base; and using the speaker independent template to recognize another utterance corresponding to the text retrieved from the supplemental data base.
Claim 8
Dependent Claim
22 words
The method of claim 5 wherein creating a template comprises using a text-to-speech system to generate a phoneme transcription of the text.
Claim 9
Dependent Claim
20 words
The method of claim 5 wherein recognizing the other utterance comprises using a speech recognition algorithm and models of phonemes.
Claim 10
Dependent Claim
119 words
An automatic speech recognition (ASR) system for use in conjunction with a telephone network, the ASR system comprising: a calling station served by a switching service point; means for receiving spoken input; a telephone line interface unit for delivering the spoken input received from the calling station to a random access memory of a host computer; a central processing unit in the host computer for retrieving information from a supplemental data base using the spoken input wherein the information received is not a representation of the spoken input; a text-to-speech means for creating a phoneme transcription of the information retrieved from the supplemental data base; and a speech recognition means for recognizing an utterance associated with the supplemental information.
Claim 11
Dependent Claim
119 words
An automatic speech recognition (ASR) system for use in conjunction with a telephone network, the ASR system comprising: a calling station served by a switching service point; means for receiving spoken input; a telephone line interface unit for delivering the spoken input received from the calling station to a random access memory of a host computer; a central processing unit in the host computer for retrieving information from a supplemental data base using the spoken input wherein the information received is not a representation of the spoken input; a text-to-speech means for creating a phoneme transcription of the information retrieved from the supplemental data base; and a speech recognition means for recognizing an utterance associated with the supplemental information.
Claim 12
Dependent Claim
18 words
The ASR system of claim 8 wherein the supplemental data base is maintained by a data service provider.
Claim 13
Dependent Claim
16 words
The ASR system of claim 8 wherein the supplemental data base is stored in a CD-ROM.
Claim 14
Dependent Claim
17 words
The ASR system of claim 8 wherein the supplemental information is retrieved from a local area network.
Claim 15
Dependent Claim
17 words
The ASR system of claim 8 wherein the phoneme transcription is used as a speaker independent template.
Claim 16
Dependent Claim
18 words
The ASR system of claim 8 wherein the means for receiving an input is a caller ID service.
Claim 17
Dependent Claim
19 words
The ASR system of claim 8 wherein the means for receiving an input is a touch tone entry means.
Claim 18
Dependent Claim
21 words
The ASR system of claim 8 wherein the speech recognition means comprises an algorithm for comparing model phonemes to spoken utterances.
References Cited (Backward Citations)
US5125022A
Cited
US5127043A
Cited
US5303299A
Cited
US5165095A
Cited
US5212730A
Cited
US5329608A
Cited
US5297183A
Cited
US5479489A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-03-02 | 2001-09-01 | 2002-03-03 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-03-02 | 2005-09-01 | 2006-03-03 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-03-02 | 2009-09-01 | 2010-03-03 | $7700.00 | Window Closed / Lapsed |