Investigation into Phone-Based Subword Units for Multilingual End-to-End Speech Recognition.
Saierdaer YusuyinHao HuangJunhua LiuCong LiuPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- end to end
- acoustic models
- speech recognizer
- automatic speech recognition
- language model
- hidden markov models
- speech processing
- speech synthesis
- congestion control
- speech signal
- pattern recognition
- digital libraries
- speaker identification
- cross language
- language independent
- cross lingual
- noisy environments
- broadcast news
- n gram
- speech recognition technology
- speech recognition systems
- natural language processing
- speaker independent
- neural network
- isolated word
- speech retrieval
- information retrieval
- machine learning
- real world