Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition.
Guodong MaPengfei HuJian KangShen HuangHao HuangPublished in: Interspeech (2021)
Keyphrases
- speech recognition
- acoustic models
- noisy environments
- speech recognizer
- hidden markov models
- wall street journal corpus
- speaker independent
- automatic speech recognition
- speech synthesis
- speech understanding
- language model
- isolated word
- speech signal
- speech processing
- speech recognition systems
- speaker identification
- pattern recognition
- speech recognition technology
- discriminative training
- broadcast news
- speaker dependent
- image processing
- information retrieval
- signal processing
- training set
- cepstral coefficients
- speech retrieval
- computer vision