MULTI-CHANNEL CODEBOOK DEPENDENT COMPENSATION

Patent №

US 8,041,561

Granted

2011-10-18

Filed 2007

Owner

—

Lab

—

AI components

ml · nlp · speech · planning · evo

Assignment

None on record

Dataset

AIPD

2023_r1 edition

Application

11930822

View graph

Methods and apparatus, in the context of speech recognition, for compensating in the cepstral domain for the effect of an interfering signal by using a reference signal.

Machine learning Natural language Speech Planning Evolutionary computationG10L 15/20G10L 25/24G10L 2021/02163

Google Patents

AI classification

Speech1.00

Machine learning1.00

Natural language1.00

Evolutionary computation0.73

Planning0.68

AI hardware0.31

Vision0.00

Knowledge representation0.00

Cites (13)

MULTI-CHANNEL CODEBOOK DEPENDENT COMPENSATIONUS 7,319,954 · 2008 ADAPTIVE FILTERING SYSTEM AND METHODUS 6,487,295 · 2002 ADAPTIVE CEPSTRAL PROCESS AND DEVICE FOR BLIND EQUALIZATION OF A TRANSMISSION CHANNEL ON A DIGITAL SPEECH SIGNALUS 6,157,909 · 2000 SPEECH PROCESSING APPARATUS AND METHOD USING A NOISE-ADAPTIVE PMC MODELUS 5,956,679 · 1999 ENVIRONMENTLY COMPENSATED SPEECH PROCESSINGUS 5,924,065 · 1999 METHOD AND SYSTEM FOR COMPENSATING SPEECH SIGNALS USING VECTOR QUANTIZATION CODEBOOK ADAPTATIONUS 5,745,872 · 1998 METHOD AND APPARATUS INCLUDING MICROPHONE ARRAYS AND NEURAL NETWORKS FOR SPEECH/SPEAKER RECOGNITION SYSTEMSUS 5,737,485 · 1998 CEPSTRAL CORRECTION VECTOR QUANTIZER FOR SPEECH RECOGNITIONUS 5,598,505 · 1997 SPEECH PROCESSING SYSTEM AND METHOD FOR ENHANCING A SPEECH SIGNAL IN A NOISY ENVIRONMENTUS 5,590,241 · 1996 SIGNAL BIAS REMOVAL FOR ROBUST TELEPHONE SPEECH RECOGNITIONUS 5,590,242 · 1996 MULTI-CHANNEL SIGNAL SEPARATION USING CROSS-POLYSPECTRAUS 5,539,832 · 1996 SPEECH PATTERN MATCHING IN NON-WHITE NOISEUS 5,487,129 · 1996 Patent US 5,781,883US 5,781,883

Cited by (2)

Method and System for Dynamic Speech Recognition and Tracking of Prewritten ScriptUS 9,953,646 · 2018 SYSTEMS AND METHODS FOR EVALUATING DIFFICULTY OF SPOKEN TEXTUS 9,449,522 · 2016

Related research

CompNet: Complementary network for single-channel speech enhancementSemantic Scholar Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech GenerationOpenAlex Distant, Multichannel Speech Recognition Using Microphone Array Coding and Cloud-Based Beamforming with a Self-Attention Channel CombinatorSemantic Scholar Microphone Array Coding Preserving Spatial Information for Cloud-based Multichannel Speech RecognitionSemantic Scholar Improving Channel Decorrelation for Multi-Channel Target Speech ExtractionarXiv

Full text

Google Patents