Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary using limited training data.
Hsin-Min WangTai-Hsuan HoRung-Chiung YangJia-Lin ShenBo-Ren BaiJenn-Chau HongWei-Peng ChenTong-Lo YuLin-Shan LeePublished in: IEEE Trans. Speech Audio Process. (1997)
Keyphrases
- speech recognition
- training data
- speaker independent
- chinese language
- recognition engine
- broadcast news
- speech recognition systems
- hong kong
- speech recognizer
- language learning
- emotion recognition
- speaker identification
- hidden markov models
- automatic speech recognition
- speech corpus
- training set
- speech synthesis
- spoken term detection
- speech signal
- noisy environments
- spoken document retrieval
- prosodic features
- online environment
- language model
- information extraction
- text to speech
- chinese characters
- reinforcement learning
- image processing