Language and Speaker-Independent Feature Transformation for End-to-End Multilingual Speech Recognition.
Tomoaki HayakawaChee Siang LeowAkio KobayashiTakehito UtsuroHiromitsu NishizakiPublished in: Interspeech (2021)
Keyphrases
- end to end
- speech recognition
- speaker independent
- speaker identification
- speaker dependent
- noisy environments
- speech signal
- speech recognizer
- hidden markov models
- language model
- gaussian mixture model
- automatic speech recognition
- natural language
- speech recognition systems
- speaker adaptation
- pattern recognition
- acoustic models
- feature extraction
- cross lingual
- multimedia