Inventor · disambiguated record
Michael A. Picheny
Also filed as: PICHENY MICHAEL · PICHENY MICHAEL A · PICHENY MICHAEL ALAN
68 granted patents·6 pending applications·5,649 citations·filing 1984–2020
99Inventor score
Top patents by PatentIndex Score
74 records- 0198US5649060AAutomatic indexing and aligning of audio and text using speech recognitionIBM·Filed 1995·Granted Jul 15, 1997·752 cites·8 claims
- 0297US7475015B2Semantic language modeling and confidence measurementIBM·Filed 2003·Granted Jan 6, 2009·289 cites·20 claims
- 0396US6219638B1Telephone messaging and editing systemIBM·Filed 1998·Granted Apr 17, 2001·302 cites·23 claims
- 0496US4819271AConstructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segmentsIBM·Filed 1987·Granted Apr 4, 1989·285 cites·18 claims
- 0594US6615170B1Model-based voice activity detection system and method using a log-likelihood ratio and pitchIBM·Filed 2000·Granted Sep 2, 2003·155 cites·18 claims
- 0694US5995590AMethod and apparatus for a communication device for use by a hearing impaired/mute or deaf person or in silent environmentsIBM·Filed 1998·Granted Nov 30, 1999·282 cites·6 claims
- 0794US5165007AFeneme-based Markov models for wordsIBM·Filed 1989·Granted Nov 17, 1992·238 cites·2 claims
- 0894US4833712AAutomatic generation of simple Markov model stunted baseforms for words in a vocabularyIBM·Filed 1985·Granted May 23, 1989·262 cites·24 claims
- 0993US7996211B2Method and apparatus for fast semi-automatic semantic annotationNUANCE COMMUNICATIONS INC·Filed 2008·Granted Aug 9, 2011·31 cites·26 claims
- 1093US5333236ASpeech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic modelsIBM·Filed 1992·Granted Jul 26, 1994·247 cites·31 claims
- 1193US5072452AAutomatic determination of labels and Markov word models in a speech recognition systemIBM·Filed 1989·Granted Dec 10, 1991·288 cites·21 claims
- 1292US8856004B2Text processing using natural language understandingBASSON SARA H·Filed 2011·Granted Oct 7, 2014·13 cites·25 claims
- 1392US6925154B2Methods and apparatus for conversational name dialing systemsIBM·Filed 2002·Granted Aug 2, 2005·88 cites·19 claims
- 1492US6556972B1Method and apparatus for time-synchronized translation and synthesis of natural-language speechIBM·Filed 2000·Granted Apr 29, 2003·87 cites·57 claims
- 1592US5864805AMethod and apparatus for error correction in a continuous dictation systemIBM·Filed 1996·Granted Jan 26, 1999·243 cites·24 claims
- 1691US6493667B1Enhanced likelihood computation using regression in a speech recognition systemIBM·Filed 1999·Granted Dec 10, 2002·187 cites·15 claims
- 1791US5806021AAutomatic segmentation of continuous text using statistical approachesIBM·Filed 1996·Granted Sep 8, 1998·192 cites·9 claims
- 1891US5233681AContext-dependent speech recognizer using estimated next word contextIBM·Filed 1992·Granted Aug 3, 1993·82 cites·31 claims
- 1991US5222146ASpeech recognition apparatus having a speech coder outputting acoustic prototype ranksIBM·Filed 1991·Granted Jun 22, 1993·260 cites·27 claims
- 2090US7490042B2Methods and apparatus for adapting output speech in accordance with context of communicationIBM·Filed 2005·Granted Feb 10, 2009·27 cites·10 claims
- 2189US10546575B2Using recurrent neural network for partitioning of audio data into segments that each correspond to a speech feature cluster identifierIBM·Filed 2016·Granted Jan 28, 2020·9 cites·20 claims
- 2289US5195167AApparatus and method of grouping utterances of a phoneme into context-dependent categories based on sound-similarity for automatic speech recognitionIBM·Filed 1992·Granted Mar 16, 1993·197 cites·10 claims
- 2388US10249292B2Using long short-term memory recurrent neural network for speaker diarization segmentationIBM·Filed 2016·Granted Apr 2, 2019·9 cites·20 claims
- 2488US6073096ASpeaker adaptation system and method based on class-specific pre-clustering training speakersIBM·Filed 1998·Granted Jun 6, 2000·144 cites·42 claims
- 2587US10510348B1Smart medical room optimization of speech recognition systemsIBM·Filed 2018·Granted Dec 17, 2019·5 cites·20 claims
- 2687US7610191B2Method for fast semi-automatic semantic annotationNUANCE COMMUNICATIONS INC·Filed 2004·Granted Oct 27, 2009·44 cites·1 claims
- 2785US6859778B1Method and apparatus for translating natural-language speech using multiple output phrasesIBM·Filed 2000·Granted Feb 22, 2005·53 cites·35 claims
- 2883US8924210B2Text processing using natural language understandingNUANCE COMMUNICATIONS INC·Filed 2014·Granted Dec 30, 2014·7 cites·20 claims
- 2983US7054810B2Feature vector-based apparatus and method for robust pattern recognitionIBM·Filed 2001·Granted May 30, 2006·40 cites·44 claims
- 3081US9195650B2Translating between spoken and written languageNUANCE COMMUNICATIONS INC·Filed 2014·Granted Nov 24, 2015·4 cites·18 claims
- 3180US11250872B2Using closed captions as parallel training data for customization of closed captioning systemsIBM·Filed 2019·Granted Feb 15, 2022·2 cites·20 claims
- 3280US7716052B2Method, apparatus and computer program providing a multi-speaker database for concatenative text-to-speech synthesisNUANCE COMMUNICATIONS INC·Filed 2005·Granted May 11, 2010·14 cites·17 claims
- 3380US6754625B2Augmentation of alternate word lists by acoustic confusability criterionIBM·Filed 2000·Granted Jun 22, 2004·34 cites·22 claims
- 3476US10726844B2Smart medical room optimization of speech recognition systemsIBM·Filed 2019·Granted Jul 28, 2020·2 cites·20 claims
- 3574US7702510B2System and method for dynamically selecting among TTS systemsNUANCE COMMUNICATIONS INC·Filed 2007·Granted Apr 20, 2010·8 cites·17 claims
- 3673US4977599ASpeech recognition employing a set of Markov models that includes Markov models representing transitions to and from silenceIBM·Filed 1988·Granted Dec 11, 1990·56 cites·19 claims
- 3772US11183194B2Detecting and recovering out-of-vocabulary words in voice-to-text transcription systemsIBM·Filed 2019·Granted Nov 23, 2021·2 cites·13 claims
- 3872US11094322B2Optimizing speech to text conversion and text summarization using a medical provider workflow modelIBM·Filed 2019·Granted Aug 17, 2021·2 cites·20 claims
- 3972US4759068AConstructing Markov models of words from multiple utterancesIBM·Filed 1985·Granted Jul 19, 1988·53 cites·13 claims
- 4071US9704482B2Method and system for order-free spoken term detectionIBM·Filed 2015·Granted Jul 11, 2017·2 cites·20 claims
- 4170US7464031B2Speech recognition utilizing multitude of speech featuresIBM·Filed 2003·Granted Dec 9, 2008·17 cites·12 claims
- 4269US10902843B2Using recurrent neural network for partitioning of audio data into segments that each correspond to a speech feature cluster identifierIBM·Filed 2019·Granted Jan 26, 2021·1 cites·20 claims
- 4369US7043432B2Method and system for text-to-speech cachingIBM·Filed 2001·Granted May 9, 2006·19 cites·29 claims
- 4469US6275801B1Non-leaf node penalty score assignment system and method for improving acoustic fast match speed in large vocabulary systemsIBM·Filed 1998·Granted Aug 14, 2001·61 cites·10 claims
- 4567US11158303B2Soft-forgetting for connectionist temporal classification based automatic speech recognitionIBM·Filed 2019·Granted Oct 26, 2021·1 cites·19 claims
- 4666US5278942ASpeech coding apparatus having speaker dependent prototypes generated from nonuser reference dataIBM·Filed 1991·Granted Jan 11, 1994·50 cites·39 claims
- 4765US4882759ASynthesizing word baseforms used in speech recognitionIBM·Filed 1986·Granted Nov 21, 1989·40 cites·19 claims
- 4864US6023673AHierarchical labeler in a speech recognition systemIBM·Filed 1997·Granted Feb 8, 2000·50 cites·23 claims
- 4963US5751905AStatistical acoustic processing method and apparatus for speech recognition using a toned phoneme systemIBM·Filed 1995·Granted May 12, 1998·42 cites·12 claims
- 5063US5455889ALabelling speech using context-dependent acoustic prototypesIBM·Filed 1993·Granted Oct 3, 1995·50 cites·14 claims
Showing the top 50 of 74 patent records by PatentIndex Score.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →