Inventor

PICHENY MICHAEL A

US36 patents

⚠️ This page may combine multiple inventors who share the name “PICHENY MICHAEL A”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

PICHENY MICHAEL A

IBM

Speech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic models

Apparatus and method of grouping utterances of a phoneme into context-dependent categories based on sound-similarity for automatic speech recognition

Feneme-based Markov models for words

Automatic generation of simple Markov model stunted baseforms for words in a vocabulary

Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments

Semantic language modeling and confidence measurement

Model-based voice activity detection system and method using a log-likelihood ratio and pitch

Methods and apparatus for conversational name dialing systems

Context-dependent speech recognizer using estimated next word context

Speech recognition apparatus having a speech coder outputting acoustic prototype ranks

Automatic determination of labels and Markov word models in a speech recognition system

Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence

Feature vector-based apparatus and method for robust pattern recognition

Normalization of speech signals

System and method for sampling rate transformation in speech recognition

Speech coding apparatus and method using classification rules

Speech coding apparatus with single-dimension acoustic prototypes for a speech recognizer

Speech coding apparatus having speaker dependent prototypes generated from nonuser reference data

Speaker-independent label coding apparatus

Synthesizing word baseforms used in speech recognition

Constructing Markov models of words from multiple utterances

Speech coding apparatus having acoustic prototype vectors generated by tying to elementary models and clustering around reference vectors

Speech recognition using dynamic features

Labelling speech using context-dependent acoustic prototypes

Method and system for text-to-speech caching

Fast algorithm for deriving acoustic prototypes for automatic speech recognition

Method and apparatus for modeling words with multi-arc markov models

Speech coding apparatus and method for generating acoustic feature vector component values by combining values of the same features for multiple time intervals

Smart medical room optimization of speech recognition systems

Smart medical room optimization of speech recognition systems

Method and system for order-free spoken term detection

Using closed captions as parallel training data for customization of closed captioning systems

Method and system for order-free spoken term detection

NUANCE COMMUNICATIONS INC

Method, apparatus and computer program providing a multi-speaker database for concatenative text-to-speech synthesis

System and method for dynamically selecting among TTS systems

Translating between spoken and written language