Leveraging Language ID to Calculate Intermediate CTC Loss for Enhanced Code-Switching Speech Recognition.
Tzu-Ting YangHsin-Wei WangBerlin ChenPublished in: CoRR (2023)
Keyphrases
- speech recognition
- isolated word
- hidden markov models
- speech synthesis
- speech signal
- speech understanding
- speech recognizer
- pattern recognition
- automatic speech recognition
- speech processing
- speech recognition systems
- speech recognition technology
- keyword spotting
- speech recognition errors
- language learning
- noisy environments
- speaker identification
- natural language
- language model
- speech retrieval
- speech recognizers
- training set
- speaker independent
- cepstral coefficients
- feature selection