Inventor
Lalit R. Bahl
Inventor
Amawalk, NY, US
Overview
Patents· 36 as inventor
Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.
G10Lprimary
G10LSpeech analysis techniques or speech synthesis79%
G06FElectric digital data processing5%
H03MCoding5%
G06NComputing arrangements based on specific computational models2%
G06TImage data processing or generation, in general2%
H03LAutomatic control, starting, synchronisation or stabilisation of generators of electronic oscillations or pulses2%
H04LTransmission of digital information, e.g. telegraphic communication2%
H04NPictorial communication, e.g. television2%
PatentTitleYear
6,377,921'Identifying mismatches between assumed and actual pronunciations of words'20026,343,270'Method for increasing dialect precision and usability in speech recognition and text-to-speech systems'20026,260,014'Specific task composite acoustic models'20016,067,517'Transcription of speech data with segments from acoustically dissimilar environments'20006,058,205'System and method for partitioning the feature space of a classifier in a pattern classification system'20005,995,931'Method for modeling and recognizing speech including word liaisons'19995,970,239'Apparatus and method for performing model estimation utilizing a discriminant measure'19995,884,259'Method and apparatus for a time-synchronous tree-based search strategy'19995,875,426'Recognizing speech having word liaisons by adding a phoneme to reference word models'19995,787,394'State-dependent speaker clustering for speaker adaptation'19985,497,447'Speech coding apparatus having acoustic prototype vectors generated by tying to elementary models and clustering around reference vectors'19965,455,889'Labelling speech using context-dependent acoustic prototypes'19955,333,236'Speech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic models'19945,280,562'Speech coding apparatus with single-dimension acoustic prototypes for a speech recognizer'19945,278,942'Speech coding apparatus having speaker dependent prototypes generated from nonuser reference data'19945,276,766'Fast algorithm for deriving acoustic prototypes for automatic speech recognition'19945,233,681'Context-dependent speech recognizer using estimated next word context'19935,195,167'Apparatus and method of grouping utterances of a phoneme into context-dependent categories based on sound-similarity for automatic speech recognition'19935,182,773'Speaker-independent label coding apparatus'19935,165,007'Feneme-based Markov models for words'19925,129,001'Method and apparatus for modeling words with multi-arc markov models'19925,033,087'Method and apparatus for the automatic determination of phonological rules as for a continuous speech recognition system'19914,980,918'Speech recognition system with efficient storage and rapid assembly of phonological graphs'19904,977,599'Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence'19904,882,759'Synthesizing word baseforms used in speech recognition'19894,852,173'Design and construction of a binary-tree system for language modelling'19894,833,712'Automatic generation of simple Markov model stunted baseforms for words in a vocabulary'19894,827,521'Training of markov models used in a speech recognition system'19894,819,271'Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments'19894,817,156'Rapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker'19894,759,068'Constructing Markov models of words from multiple utterances'19884,748,670'Apparatus and method for determining a likely word sequence from labels generated by an acoustic processor'19884,741,036'Determination of phone weights for markov models in a speech recognition system'19884,718,094'Speech recognition system'19884,291,406'Error correction on burst channels by sequential decoding'19814,028,731'Apparatus for compression coding using cross-array correlation between two-dimensional matrices derived from two-valued digital images'1977Career & activity timeline
Assembled from patent assignee/location history and declaration credentials.
1977–2002Patents assigned to IBM (36)· patent assignee history
1977–2000Based in Amawalk, NY, US· patent location history
1991Based in Amawal, NY, US· patent location history
2001–2002Based in Port Jefferson, NY, US· patent location history
Inventor activity
Assignee and location history derived from the patent record.
Assignees
| Assignee | Patents | Span |
|---|---|---|
| IBM | 36 | 1977–2002 |
Locations
| Location | Patents | Span |
|---|---|---|
| Amawalk, New York, US | 32 | 1977–2000 |
| Port Jefferson, New York, US | 3 | 2001–2002 |
| Amawal, New York, US | 1 | 1991 |