Dynamic Language Group-Based MoE: Enhancing Efficiency and Flexibility for Code-Switching Speech Recognition.
Hukai HuangShenghui LuYahui ShanHe QuWenhao GuanQingyang HongLin LiPublished in: CoRR (2024)
Keyphrases
- speech recognition
- isolated word
- hidden markov models
- language model
- speech synthesis
- speech processing
- speech recognizer
- speech signal
- speech recognition technology
- automatic speech recognition
- pattern recognition
- noisy environments
- speech understanding
- natural language
- speaker identification
- text to speech
- signal processing
- speech recognition systems
- speaker independent
- cepstral coefficients
- speech recognition errors
- speaker recognition
- language processing
- language learning
- machine learning