Patents by Inventor Asela J. R. Gunawardana
Asela J. R. Gunawardana has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8180640Abstract: Described is the use of acoustic data to improve grapheme-to-phoneme conversion for speech recognition, such as to more accurately recognize spoken names in a voice-dialing system. A joint model of acoustics and graphonemes (acoustic data, phonemes sequences, grapheme sequences and an alignment between phoneme sequences and grapheme sequences) is described, as is retraining by maximum likelihood training and discriminative training in adapting graphoneme model parameters using acoustic data. Also described is the unsupervised collection of grapheme labels for received acoustic data, thereby automatically obtaining a substantial number of actual samples that may be used in retraining. Speech input that does not meet a confidence threshold may be filtered out so as to not be used by the retrained model.Type: GrantFiled: June 20, 2011Date of Patent: May 15, 2012Assignee: Microsoft CorporationInventors: Xiao Li, Asela J. R. Gunawardana, Alejandro Acero, Jr.
-
Publication number: 20110251844Abstract: Described is the use of acoustic data to improve grapheme-to-phoneme conversion for speech recognition, such as to more accurately recognize spoken names in a voice-dialing system. A joint model of acoustics and graphonemes (acoustic data, phonemes sequences, grapheme sequences and an alignment between phoneme sequences and grapheme sequences) is described, as is retraining by maximum likelihood training and discriminative training in adapting graphoneme model parameters using acoustic data. Also described is the unsupervised collection of grapheme labels for received acoustic data, thereby automatically obtaining a substantial number of actual samples that may be used in retraining. Speech input that does not meet a confidence threshold may be filtered out so as to not be used by the retrained model.Type: ApplicationFiled: June 20, 2011Publication date: October 13, 2011Applicant: MICROSOFT CORPORATIONInventors: Xiao Li, Asela J. R. Gunawardana, Alejandro Acero
-
Patent number: 7991615Abstract: Described is the use of acoustic data to improve grapheme-to-phoneme conversion for speech recognition, such as to more accurately recognize spoken names in a voice-dialing system. A joint model of acoustics and graphonemes (acoustic data, phonemes sequences, grapheme sequences and an alignment between phoneme sequences and grapheme sequences) is described, as is retraining by maximum likelihood training and discriminative training in adapting graphoneme model parameters using acoustic data. Also described is the unsupervised collection of grapheme labels for received acoustic data, thereby automatically obtaining a substantial number of actual samples that may be used in retraining. Speech input that does not meet a confidence threshold may be filtered out so as to not be used by the retrained model.Type: GrantFiled: December 7, 2007Date of Patent: August 2, 2011Assignee: Microsoft CorporationInventors: Xiao Li, Asela J. R. Gunawardana, Alejandro Acero
-
Publication number: 20090150153Abstract: Described is the use of acoustic data to improve grapheme-to-phoneme conversion for speech recognition, such as to more accurately recognize spoken names in a voice-dialing system. A joint model of acoustics and graphonemes (acoustic data, phonemes sequences, grapheme sequences and an alignment between phoneme sequences and grapheme sequences) is described, as is retraining by maximum likelihood training and discriminative training in adapting graphoneme model parameters using acoustic data. Also described is the unsupervised collection of grapheme labels for received acoustic data, thereby automatically obtaining a substantial number of actual samples that may be used in retraining. Speech input that does not meet a confidence threshold may be filtered out so as to not be used by the retrained model.Type: ApplicationFiled: December 7, 2007Publication date: June 11, 2009Applicant: MICROSOFT CORPORATIONInventors: Xiao Li, Asela J. R. Gunawardana, Alejandro Acero
-
Patent number: 7206741Abstract: A speech signal is decoded by determining a production-related value for a current state based on an optimal production-related value at the end of a preceding state, the optimal production-related value being selected from a set of continuous values. The production-related value is used to determine a likelihood of a phone being represented by a set of observation vectors that are aligned with a path between the preceding state and the current state. The likelihood of the phone is combined with a score from the preceding state to determine a score for the current state, the score from the preceding state being associated with a discrete class of production-related values wherein the class matches the class of the optimal production-related value.Type: GrantFiled: December 6, 2005Date of Patent: April 17, 2007Assignee: Microsoft CorporationInventors: Li Deng, Jian-lai Zhou, Frank Torsten Bernd Seide, Asela J. R. Gunawardana, Hagai Attias, Alejandro Acero, Xuedong Huang
-
Patent number: 7117153Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.Type: GrantFiled: February 13, 2003Date of Patent: October 3, 2006Assignee: Microsoft CorporationInventors: Milind Mahajan, Yonggang Deng, Alejandro Acero, Asela J. R. Gunawardana, Ciprian Chelba
-
Patent number: 7103544Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.Type: GrantFiled: June 6, 2005Date of Patent: September 5, 2006Assignee: Microsoft CorporationInventors: Milind Mahajan, Yonggang Deng, Alejandro Acero, Asela J. R. Gunawardana, Ciprian Chelba
-
Patent number: 7050975Abstract: A method of speech recognition is provided that identifies a production-related dynamics value by performing a linear interpolation between a production-related dynamics value at a previous time and a production-related target using a time-dependent interpolation weight. The hidden production-related dynamics value is used to compute a predicted value that is compared to an observed value of acoustics to determine the likelihood of the observed acoustics given a sequence of hidden phonological units. In some embodiments, the production-related dynamics value at the previous time is selected from a set of continuous values. In addition, the likelihood of the observed acoustics given a sequence of hidden phonological units is combined with a score associated with a discrete class of production-related dynamic values at the previous time to determine a score for a current phonological state.Type: GrantFiled: October 9, 2002Date of Patent: May 23, 2006Assignee: Microsoft CorporationInventors: Li Deng, Jian-Iai Zhou, Frank Torsten Bernd Seide, Asela J. R. Gunawardana, Hagai Attias, Alejandro Acero, Xuedong Huang
-
Publication number: 20040162730Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.Type: ApplicationFiled: February 13, 2003Publication date: August 19, 2004Applicant: Microsoft CorporationInventors: Milind Mahajan, Yonggang Deng, Alejandro Acero, Asela J.R. Gunawardana, Ciprian Chelba
-
Publication number: 20040019483Abstract: A method of speech recognition is provided that identifies a production-related dynamics value by performing a linear interpolation between a production-related dynamics value at a previous time and a production-related target using a time-dependent interpolation weight. The hidden production-related dynamics value is used to compute a predicted value that is compared to an observed value of acoustics to determine the likelihood of the observed acoustics given a sequence of hidden phonological units. In some embodiments, the production-related dynamics value at the previous time is selected from a set of continuous values. In addition, the likelihood of the observed acoustics given a sequence of hidden phonological units is combined with a score associated with a discrete class of production-related dynamic values at the previous time to determine a score for a current phonological state.Type: ApplicationFiled: October 9, 2002Publication date: January 29, 2004Inventors: Li Deng, Jian-Iai Zhou, Frank Torsten Bernd Seide, Asela J.R. Gunawardana, Hagai Attias, Alejandro Acero, Xuedong Huang
-
Patent number: 6571210Abstract: A method and system of performing confidence measure in a speech recognition system includes receiving an utterance of input speech and creating a near-miss pattern or a near-miss list of possible word entries for the utterance. Each word entry includes an associated value of probability that the utterance corresponds to the word entry. The near-miss list of possible word entries is compared with corresponding stored near-miss confidence templates. Each word in the vocabulary (or keyword list) of near-miss confidence template, which includes a list of word entries and each word entry in each list includes an associated value. Confidence measure for a particular hypothesis word is performed based on the comparison of the values in the near-miss list of possible word entries with the values of the corresponding near-miss confidence template.Type: GrantFiled: November 13, 1998Date of Patent: May 27, 2003Assignee: Microsoft CorporationInventors: Hsiao-Wuen Hon, Asela J. R. Gunawardana
-
Publication number: 20010018654Abstract: A method and system of performing confidence measure in a speech recognition system includes receiving an utterance of input speech and creating a near-miss pattern or a near-miss list of possible word entries for the utterance. Each word entry includes an associated value of probability that the utterance corresponds to the word entry. The near-miss list of possible word entries is compared with corresponding stored near-miss confidence templates. Each word in the vocabulary (or keyword list) of near-miss confidence template, which includes a list of word entries and each word entry in each list includes an associated value. Confidence measure for a particular hypothesis word is performed based on the comparison of the values in the near-miss list of possible word entries with the values of the corresponding near-miss confidence template.Type: ApplicationFiled: November 13, 1998Publication date: August 30, 2001Inventors: HSIAO-WUEN HON, ASELA J.R. GUNAWARDANA