Phonetic state tied-mixture tone modeling for large vocabulary continuous Mandarin speech recognition.
Tai-Hsuan HoChin-Jung LiuHerman SunMing-Yi TsaiLin-Shan LeePublished in: EUROSPEECH (1999)
Keyphrases
- speech recognition
- speaker independent
- hidden markov models
- speech recognizer
- language model
- pattern recognition
- speech signal
- speaker identification
- speech recognition systems
- noisy environments
- speech synthesis
- automatic speech recognition
- speech understanding
- speech processing
- speech recognition technology
- keyword spotting
- mixture model
- speech retrieval
- isolated word
- speaker recognition
- test collection
- expectation maximization