Channel adaptation

MaRDI QIDQ4942729zbMATH OpenFDO

Authors Keith M. Ponting

Publication date 5 June 2000

zbMATH Keywords

automatic speech recognitionchannel adaptationmismatch problem

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Natural language processing (68T50) Channel models (including quantum) in information and communication theory (94A40)

Recommendations

• HMM adaptation for applications in telecommunication
• Speaker compensation in automatic speech recognition
• Robust speech recognition based on adaptive classification and decision strategies
• Acoustic features and a distance measure that reduce the impact of training–test mismatch in ASR
• Variance compensation for recognition of reverberant speech with dereverberation preprocessing

Cited in

(12)

• Feature-dependent compensation of coders in speech recognition
• Robust adaptation to non-native accents in automatic speech recognition.
• Lamarckian vs Darwinian evolution for the adaptation to acoustical environment change
• Speaker compensation in automatic speech recognition
• Uncertainty decoding and conditional Bayesian estimation
• Variance compensation for recognition of reverberant speech with dereverberation preprocessing
• Adaptive channels and human decisionmaking
• Hidden Markov model and neural network hybrid
• Acoustic features and a distance measure that reduce the impact of training–test mismatch in ASR
• Compensation of channel and noise distortions combining normalization and speech enhancement techniques
• Transformation-based Bayesian prediction for adaptation of HMMs
• On the efficiency of classical RASTA filtering for continuous speech recognition: Keeping the balance between acoustic pre-processing and acoustic modelling

This page was built for publication: Channel adaptation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4942729)