APPARATUS AND METHOD FOR DISTINGUISHING SIMILAR-SOUNDING UTTERANCES SPEECH RECOGNITION
Patent №
US 6,487,532
Granted
2002-11-26
Filed 1998
Owner
LERNOUT & HAUSPIE SPEECH PRODUCTS N.V.
Lab
—
AI components
3
ml · nlp · speech
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
09159838
Speaker-specified hints are used to establish conditions for a speech recognition system to select a recognition result for a previously provided utterance from among various possible homophones. The hints may characterize the utterance by a linguistic property, such as an orthographic, morphological, or semantic property.
AI classification
Natural language1.00
Speech1.00
Machine learning0.96
AI hardware0.27
Knowledge representation0.03
Vision0.00
Evolutionary computation0.00
Planning0.00
Ownership
LERNOUT & HAUSPIE SPEECH PRODUCTS N.V.
assignment · 98360524
Assignors
SCHOOFS, KOEN, GALLOPYN, GUIDO
On an employer assignment, the assignors are typically the inventors.
From the same owner
CORPUS-BASED PROSODY TRANSLATION SYSTEMUS 7,069,216 · 2006FAST WAVEFORM SYNCHRONIZATION FOR CONCENTRATION AND TIME-SCALE MODIFICATION OF SPEECHUS 7,058,569 · 2006ATTRIBUTE-BASED WORD MODELINGUS 6,963,837 · 2005NOISE-LEVEL ADAPTIVE RESIDUAL ECHO SUPPRESSORUS 6,959,167 · 2005RECURSIVELY EXCITED LINEAR PREDICTION SPEECH CODERUS 6,704,703 · 2004SPEECH SYNTHESIS USING CONCATENATION OF SPEECH WAVEFORMSUS 6,665,641 · 2003WORD BOUNDARY ACOUSTIC UNITSUS 6,606,594 · 2003METHOD AND SYSTEM FOR GENERATING SEMI-LITERAL TRANSCRIPTS FOR SPEECH RECOGNITION SYSTEMSUS 6,535,849 · 2003