Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition.
Xuandi FuKanthashree Mysore SathyendraAnkur GandheJing LiuGrant P. StrimelRoss McGowanAthanasios MouchtarisPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- speech recognition systems
- speaker independent
- noisy environments
- speech recognizers
- hidden markov models
- language model
- speech recognizer
- automatic speech recognition
- speech signal
- acoustic models
- speech processing
- pattern recognition
- speech understanding
- speech synthesis
- noisy speech
- speech recognition technology
- contextual information
- semantic information
- keyword spotting
- speaker dependent
- neural network
- speech retrieval
- digital video library
- semantic analysis
- natural language
- probabilistic model
- speaker identification
- multi modal
- digit recognition
- vocal tract
- speaker recognition