Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition.
Murali Karthick BaskarLukás BurgetShinji WatanabeRamón Fernandez AstudilloJan Honza CernockýPublished in: ICASSP (2021)
Keyphrases
- speech recognition
- automatic speech recognition
- speech synthesis
- speech signal
- hidden markov models
- speech processing
- noisy environments
- text to speech
- speech understanding
- speech recognizer
- language model
- pattern recognition
- speech recognition technology
- word error rate
- speech recognizers
- speech recognition systems
- speaker identification
- keyword spotting
- broadcast news
- handwriting recognition
- speaker independent
- speaker diarization
- cepstral coefficients
- speaker adaptation
- speech retrieval
- machine learning