CAST: Context-association architecture with simulated long-utterance training for mandarin speech recognition.
Yue MingBoyang LyuZerui LiPublished in: Speech Commun. (2023)
Keyphrases
- speech recognition
- wall street journal corpus
- isolated word
- automatic speech recognition
- hidden markov models
- speech processing
- speech recognizer
- pattern recognition
- speaker independent
- speech signal
- noisy environments
- acoustic models
- speech recognition technology
- speech understanding
- speech synthesis
- speech recognition systems
- discriminative training
- language model
- speaker identification
- keyword spotting
- speech recognizers
- cepstral coefficients
- speaker dependent
- speech recognition errors
- speech retrieval
- neural network