An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging Encoder Disentanglement.
Tzu-Ting YangHsin-Wei WangYi-Cheng WangChi-Han LinBerlin ChenPublished in: ICASSP (2024)
Keyphrases
- speech recognition
- speech synthesis
- language model
- hidden markov models
- speech processing
- automatic speech recognition
- pattern recognition
- speech signal
- speech recognizer
- speech understanding
- speech recognition technology
- mixture model
- audio visual speech recognition
- noisy environments
- speech recognizers
- keyword spotting
- speaker dependent
- speaker diarization
- isolated word
- speech recognition systems
- motion estimation
- gaussian distribution
- visual features