1
Peter F Brown, John Cocke, Stephen A Della Pietra, Vincent J Della Pietra, Frederick Jelinek, Jennifer C Lai, Robert L Mercer: Method and system for natural language translation. International Business Machines, Robert P Tassinari, Sterne Kessler Goldstein & Fox, December 19, 1995: US05477451 (385 worldwide citation)

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 fi ...


2
Lalit R Bahl, Peter V deSouza, Steven V DeGennaro, Robert L Mercer: Speech recognition system. International Business Machines, Marc A Block, January 5, 1988: US04718094 (198 worldwide citation)

Speech words are recognized by first recognizing each spectral vector identified by a label (feneme), then identifying the word by matching the string of labels against phones using simplified phone machines based on label and transition probabilities and Merkov chains. In one embodiment, a detailed ...


3
Lalit R Bahl, Peter V DeSouza, Robert L Mercer, Michael A Picheny: Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments. International Business Machines Corporation, Marc A Block, April 4, 1989: US04819271 (179 worldwide citation)

The present invention relates to apparatus and method for segmenting multiple utterances of a vocabulary word in a consistent and coherent manner and determining a Markov model sequence for each segment. A fenemic Markov model corresponds to each label.


4
Lalit R Bahl, Peter F Brown, Peter V DeSouza, Robert L Mercer: Method and apparatus for the automatic determination of phonological rules as for a continuous speech recognition system. International Business Machines, Ratner & Prestia, July 16, 1991: US05033087 (178 worldwide citation)

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 t ...


5
Peter F Brown, Stephen A Della Pietra, Vincent J Della Pietra, Robert L Mercer, Philip S Resnik, Stanley S Chen: Speech recognition apparatus which predicts word classes from context and words from word classes. International Business Machines Corporation, Marc D Schechter, November 30, 1993: US05267345 (178 worldwide citation)

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 comp ...


6
Adam L Berger, Peter F Brown, Stephen A Della Pietra, Vincent J Della Pietra, Andrew S Kehler, Robert L Mercer: Language translation apparatus and method using context-based translation models. International Business Machines Corporation, Marc D Schechter, Robert P Tassinari, April 23, 1996: US05510981 (170 worldwide citation)

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 ...


7
Lalit R Bahl, Peter V DeSouza, Robert L Mercer, Michael A Picheny: Automatic generation of simple Markov model stunted baseforms for words in a vocabulary. International Business Machines Corporation, Marc A Block, Marc D Schechter, May 23, 1989: US04833712 (163 worldwide citation)

In a system that (i) defines each word in a vocabulary by a fenemic baseform of fenemic phones, (ii) defines an alphabet of composite phones each of which corresponds to at least one fenemic phone, and (iii) generates a string of fenemes in response to speech input, the method provides for convertin ...


8
Lalit R Bahl, Peter V DeSouza, Robert L Mercer, Michael A Picheny: Feneme-based Markov models for words. International Business Machines Corporation, Marc D Schechter, November 17, 1992: US05165007 (141 worldwide citation)

In a speech recognition system, apparatus and method for modelling words with label-based Markov models is disclosed. The modelling includes: entering a first speech input, corresponding to words in a vocabulary, into an acoustic processor which converts each spoken word into a sequence of standard ...


9
Peter F Brown, Stephen A Della Pietra, Vincent J Della Pietra, Frederick Jelinek, Robert L Mercer: Speech recognition system for natural language translation. International Business Machines Corporation, Marc D Schechter, March 8, 1994: US05293584 (90 worldwide citation)

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 ...


10
Robert L Mercer: Dishwasher system. General Motors Corporation, Frederick M Ritchie, November 2, 1976: US03989054 (74 worldwide citation)

A dishwasher has upper and lower spray arms, a telescoping spray tower and a filtering system which includes a frusto-conical screen cage, the outside of which connects to a dishwasher sump by way of a tangential channel including a drain opening therefrom. The inside of the cage connects to the inl ...