Patent №
US 8,843,370
Granted
2014-09-23
Filed 2007
Owner
NUANCE COMMUNICATIONS, INC.
Lab
—
AI components
5
ml · nlp · vision · speech · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
11945048
Adjusting model parameters is described for a speech recognition system that combines recognition outputs from multiple speech recognition processes. Discriminative adjustments are made to model parameters of at least one acoustic model based on a joint discriminative criterion over multiple complementary acoustic models to lower recognition word error rate in the system.
AI classification
Speech1.00
Machine learning1.00
Natural language1.00
AI hardware0.98
Vision0.73
Knowledge representation0.28
Planning0.00
Evolutionary computation0.00
Ownership
NUANCE COMMUNICATIONS, INC.
assignment · 202750865
Assignors
WILLETT, DANIEL, HE, CHUANG
On an employer assignment, the assignors are typically the inventors.
From the same owner
GESTURAL PROMPTING BASED ON CONVERSATIONAL ARTIFICIAL INTELLIGENCEUS 12,444,410 · 2025AMBIENT LISTENING SYSTEM FOR SALES ASSISTANCEUS 12,314,990 · 2025CROSS-ATTENTION BETWEEN SPARSE EXTERNAL FEATURES AND CONTEXTUAL WORD EMBEDDINGS TO IMPROVE TEXT CLASSIFICATIONUS 12,277,391 · 2025END-TO-END AUTOMATIC SPEECH RECOGNITION SYSTEM FOR BOTH CONVERSATIONAL AND COMMAND-AND-CONTROL SPEECHUS 12,223,953 · 2025System and Method for Secure Training of Speech Processing SystemsUS 12,190,888 · 2025SYSTEM AND METHOD FOR REVIEW OF AUTOMATED CLINICAL DOCUMENTATION FROM RECORDED AUDIOUS 12,176,080 · 2024SYSTEM AND METHOD FOR DYNAMIC FACIAL FEATURES FOR SPEAKER RECOGNITIONUS 12,080,295 · 2024SYSTEM AND METHOD FOR PERFORMING AUTOMATIC SPEECH RECOGNITION SYSTEM PARAMETER ADJUSTMENT VIA MACHINE LEARNINGUS 11,972,753 · 2024