Two-Stage Temporal Multimodal Learning for Speaker and Speech Recognition.
Qianli MaLifeng ShenRuishi SuJieyu ChenPublished in: ICONIP (2) (2017)
Keyphrases
- speech recognition
- automatic speech recognition
- speech processing
- speaker identification
- speaker recognition
- speaker dependent
- language model
- speech signal
- speech recognition technology
- speech synthesis
- speech recognizers
- speaker independent
- speech recognition systems
- speech recognizer
- noisy environments
- multi modal
- hidden markov models
- natural language processing
- feature selection
- speech recognition errors
- information retrieval
- neural network