Robert S Mercer

US Patent:

58058320, Sep 8, 1998

Filed:

Jun 2, 1995

Appl. No.:

8/459454

Inventors:

Peter Fitzhugh Brown - New York NY
John Cocke - Bedford NY
Stephen Andrew Della Pietra - Pearl River NY
Vincent Joseph Della Pietra - Blauvelt NY
Frederick Jelinek - Briarcliff Manor NY
Jennifer Ceil Lai - Garrison NY
Robert Leroy Mercer - Yorktown Heights NY

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 1728

US Classification:

395752

Abstract:

The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language.

US Patent:

57686033, Jun 16, 1998

Filed:

Jun 2, 1995

Appl. No.:

8/459698

Inventors:

Peter Fitzhugh Brown - New York NY
John Cocke - Bedford NY
Stephen Andrew Della Pietra - Pearl River NY
Vincent Joseph Della Pietra - Blauvelt NY
Frederick Jelinek - Briarcliff Manor NY
Jennifer Ceil Lai - Garrison NY
Robert Leroy Mercer - Yorktown Heights NY

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 1728
G06F 1720

US Classification:

395759

Abstract:

The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language.

US Patent:

54774519, Dec 19, 1995

Filed:

Jul 25, 1991

Appl. No.:

7/736278

Inventors:

Peter F. Brown - New York NY
John Cocke - Bedford NY
Stephen A. Della Pietra - Pearl River NY
Vincent J. Della Pietra - Blauvelt NY
Frederick Jelinek - Briarcliff Manor NY
Jennifer C. Lai - Garrison NY
Robert L. Mercer - Yorktown Heights NY

Assignee:

International Business Machines Corp. - Yorktown Heights NY

International Classification:

G06F 1720
G06F 1727

US Classification:

36441908

Abstract:

The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language.

US Patent:

52935841, Mar 8, 1994

Filed:

May 21, 1992

Appl. No.:

7/887205

Inventors:

Peter F. Brown - New York NY
Stephen A. Della Pietra - Pearl River NY
Vincent J. Della Pietra - Blauvelt NY
Frederick Jelinek - Briarcliff Manor NY
Robert L. Mercer - Yorktown Heights NY

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G10L 500

US Classification:

395 286

Abstract:

A speech recognition system displays a source text of one or more words in a source language. The system has an acoustic processor for generating a sequence of coded representations of an utterance to be recognized. The utterance comprises a series of one or more words in a target language different from the source language. A set of one or more speech hypotheses, each comprising one or more words from the target language, are produced. Each speech hypothesis is modeled with an acoustic model. An acoustic match score for each speech hypothesis comprises an estimate of the closeness of a match between the acoustic model of the speech hypothesis and the sequence of coded representations of the utterance. A translation match score for each speech hypothesis comprises an estimate of the probability of occurrence of the speech hypothesis given the occurrence of the source text. A hypothesis score for each hypothesis comprises a combination of the acoustic match score and the translation match score.

US Patent:

55109810, Apr 23, 1996

Filed:

Oct 28, 1993

Appl. No.:

8/144913

Inventors:

Adam L. Berger - New York NY
Peter F. Brown - New York NY
Stephen A. Della Pietra - Pearl River NY
Vincent J. Della Pietra - Blauvelt NY
Andrew S. Kehler - Somerville MA
Robert L. Mercer - Yorktown Heights NY

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 1728

US Classification:

36441902

Abstract:

An apparatus for translating a series of source words in a first language to a series of target words in a second language. For an input series of source words, at least two target hypotheses, each including a series of target words, are generated. Each target word has a context comprising at least one other word in the target hypothesis. For each target hypothesis, a language model match score including an estimate of the probability of occurrence of the series of words in the target hypothesis. At least one alignment connecting each source word with at least one target word in the target hypothesis is identified. For each source word and each target hypothesis, a word match score including an estimate of the conditional probability of occurrence of the source word, given the target word in the target hypothesis which is connected to the source word and given the context in the target hypothesis of the target word which is connected to the source word. For each target hypothesis, a translation match score including a combination of the word match scores for the target hypothesis and the source words in the input series of source words. A target hypothesis match score including a combination of the language model match score for the target hypothesis and the translation match score for the target hypothesis.

US Patent:

52673456, Nov 30, 1993

Filed:

Feb 10, 1992

Appl. No.:

7/834063

Inventors:

Peter F. Brown - New York NY
Stephen A. Della Pietra - Pearl River NY
Vincent J. Della Pietra - Blauvelt NY
Robert L. Mercer - Yorktown Heights NY
Philip S. Resnik - Philadelphia PA
Stanley S. Chen - Cambridge MA

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G10L 900

US Classification:

395 264

Abstract:

A language generator for a speech recognition apparatus scores a word-series hypothesis by combining individual scores for each word in the hypothesis. The hypothesis score for a single word comprises a combination of the estimated conditional probability of occurrence of a first class of words comprising the word being scored, given the occurrence of a context comprising the words in the word-series hypothesis other than the word being scored, and the estimated conditional probability of occurrence of the word being scored given the occurrence of the first class of words, and given the occurrence of the context. An apparatus and method are provided for classifying multiple series of words for the purpose of obtaining useful hypothesis scores in the language generator and speech recognition apparatus.

US Patent:

50330870, Jul 16, 1991

Filed:

Mar 14, 1989

Appl. No.:

7/323479

Inventors:

Lalit R. Bahl - Amawal NY
Peter F. Brown - New York NY
Peter V. DeSouza - Yorktown Heights NY
Robert L. Mercer - Yorktown Heights NY

Assignee:

International Business Machines Corp. - Armonk NY

International Classification:

G01L 708

US Classification:

381 43

Abstract:

A continuous speech recognition system includes an automatic phonological rules generator which determines variations in the pronunciation of phonemes based on the context in which they occur. This phonological rules generator associates sequences of labels derived from vocalizations of a training text with respective phonemes inferred from the training text. These sequences are then annotated with their pheneme context from the training text and clustered into groups representing similar pronunciations of each phoneme. A decision tree is generated using the context information of the sequences to predict the clusters to which the sequences belong. The training data is processed by the decision tree to divide the sequences into leaf-groups representing similar pronunciations of each phoneme. The sequences in each leaf-group are clustered into sub-groups representing respectively different pronunciations of their corresponding phoneme in a give context. A Markov model is generated for each sub-group.