VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition.
Naoyuki KandaJian WuXiaofei WangZhuo ChenJinyu LiTakuya YoshiokaPublished in: CoRR (2022)
Keyphrases
- speech recognition
- automatic speech recognition
- conversational speech
- hidden markov models
- multi modal
- language model
- speech recognizer
- pattern recognition
- speech processing
- speech recognition technology
- speech recognition systems
- speech signal
- spoken language
- speech synthesis
- noisy environments
- speech retrieval
- speech understanding
- speaker independent
- speech recognition errors
- speaker dependent
- neural network
- isolated word
- cepstral coefficients
- handwriting recognition
- natural language
- speaker identification
- non stationary
- signal processing