Michael A. Picheny
68Patents
29h-index
83Co-inventors
91Inventor score
Filing activity: Oct 19, 1984 → Nov 10, 2020
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US5649060A | Automatic indexing and aligning of audio and text using speech recognition | Physics | 563 | Expired |
| US5072452A | Automatic determination of labels and Markov word models in a speech recognition system | Physics | 276 | Expired |
| US4819271A | Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments | Physics | 273 | Expired |
| US7475015B2 | Semantic language modeling and confidence measurement | Physics | 272 | Expired |
| US4833712A | Automatic generation of simple Markov model stunted baseforms for words in a vocabulary | Physics | 257 | Expired |
| US5222146A | Speech recognition apparatus having a speech coder outputting acoustic prototype ranks | Physics | 252 | Expired |
| US5333236A | Speech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic models | Physics | 242 | Expired |
| US5165007A | Feneme-based Markov models for words | Physics | 232 | Expired |
| US5995590A | Method and apparatus for a communication device for use by a hearing impaired/mute or deaf person or in silent environments | Physics | 229 | Expired |
| US6219638A | Telephone messaging and editing system | Electricity | 195 | Expired |
| US5195167A | Apparatus and method of grouping utterances of a phoneme into context-dependent categories based on sound-similarity for automatic speech recognition | Physics | 185 | Expired |
| US6493667B1 | Enhanced likelihood computation using regression in a speech recognition system | Physics | 177 | Expired |
| US5864805A | Method and apparatus for error correction in a continuous dictation system | Physics | 136 | Expired |
| US5806021A | Automatic segmentation of continuous text using statistical approaches | Physics | 131 | Expired |
| US6073096A | Speaker adaptation system and method based on class-specific pre-clustering training speakers | Physics | 77 | Expired |
| US6615170B1 | Model-based voice activity detection system and method using a log-likelihood ratio and pitch | Physics | 73 | Expired |
| US5233681A | Context-dependent speech recognizer using estimated next word context | Physics | 60 | Expired |
| US6925154B2 | Methods and apparatus for conversational name dialing systems | Electricity | 46 | Expired |
| US6556972B1 | Method and apparatus for time-synchronized translation and synthesis of natural-language speech | Physics | 45 | Expired |
| US4759068A | Constructing Markov models of words from multiple utterances | Physics | 45 | Expired |
| US4977599A | Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence | Physics | 44 | Expired |
| US5278942A | Speech coding apparatus having speaker dependent prototypes generated from nonuser reference data | Physics | 41 | Expired |
| US6023673A | Hierarchical labeler in a speech recognition system | Physics | 37 | Expired |
| US4882759A | Synthesizing word baseforms used in speech recognition | Physics | 35 | Expired |
| US5455889A | Labelling speech using context-dependent acoustic prototypes | Physics | 35 | Expired |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.