1
Erik B Hedin, Gregor I Jonsson, Lars E Olsson, Mohammad A Sanamrad, Sven O G Westling: Natural language analyzing apparatus and method. International Business Machines Corporation, Marc D Schechter, Robert P Tassinari Jr, January 31, 1995: US05386556 (410 worldwide citation)

A natural language (NL) analyzing system is provided with the capability to analyze NL expressions and to resolve ambiguities and present them to the user for verification of correct interpretation. A conceptual model of the system, relevant to the application in which the invention is implemented, ...


2
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 ...


3
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 ...


4
Seraphin B Calo, Krishnamurthi Kannan, Suk S Soo, Thomas G Burket, John W Wiley Jr: Electronic system for accessing graphical and textual information. International Business Machines Corporation, Thomas P Dowd, Marc D Schechter, February 14, 1989: US04805134 (170 worldwide citation)

An architecture for the implementation of an information utility for accessing information and executing transactions on an interactive basis between Videotex databases and individual end user terminals, some or all of which may be remotely located with respect to each other. The utility may be asso ...


5
Peter K Bachmann: Method of manufacturing fluorine-doped optical fibers. U S Philips Corporation, Marc D Schechter, August 28, 1984: US04468413 (167 worldwide citation)

Doped silica glass can be manufactured by reacting gaseous vapors of silica-forming compounds and dopant-forming compounds. Increased fluorine dopant can be provided with less fluorine dopant-forming compound, when the fluorine dopant-forming compound is hexafluoroethane (C.sub.2 F.sub.6).


6
Masafumi Nishimura: Speech recognition system using Markov models having independent label output sets. International Business Machines Corporation, Marc D Schechter, July 9, 1991: US05031217 (167 worldwide citation)

A speech recognition system measures the values of at least two classes of features of an utterance: (1) a first class whose value is related to the frequency spectrum of the utterance, and (2) a second class whose value is related to the variation with time of the "first class" value of the utteran ...


7
Peter F Brown, Peter V De Souza, David Nahomoo, Michael A Picheny: Automatic determination of labels and Markov word models in a speech recognition system. International Business Machines Corporation, Marc D Schechter, December 10, 1991: US05072452 (166 worldwide citation)

In a Markov model speech recognition system, an acoustic processor generates one label after another selected from an alphabet of labels. Each vocabulary word is represented as a baseform constructed of a sequence of Markov models. Each Markov model is stored in a computer memory as (a) a plurality ...


8
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 ...


9
Latit R Bahl, Peter V De Souza, Ponani S Gopalakrishnan, Michael A Picheny: Speech recognition apparatus having a speech coder outputting acoustic prototype ranks. International Business Machines Corporation, Marc D Schechter, June 22, 1993: US05222146 (162 worldwide citation)

A speech coding and speech recognition apparatus. The value of at least one feature of an utterance is measured over each of a series of successive time intervals to produce a series of feature vector signals. The closeness of the feature value of each feature vector signal to the parameter value of ...


10
Masafumi Nishimura, Masaaki Okochi: Speech recognition by concatenating fenonic allophone hidden Markov models in parallel among subwords. International Business Machines Corporation, Marc D Schechter, Robert P Tassinari Jr, March 26, 1996: US05502791 (155 worldwide citation)

Analysis of a word input from a speech input device 1 for its features is made by a feature extractor 4 to obtain a feature vector sequence corresponding to said word, or to obtain a label sequence by applying a further transformation in a labeler 8. Fenonic hidden Markov models for speech transform ...