EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition.
Murali Karthick BaskarLukás BurgetShinji WatanabeRamón Fernandez AstudilloJan Honza CernockýPublished in: CoRR (2021)
Keyphrases
- speech recognition
- automatic speech recognition
- speech synthesis
- hidden markov models
- text to speech
- speech recognizer
- speech processing
- speech signal
- language model
- noisy environments
- pattern recognition
- speech retrieval
- word error rate
- speech understanding
- speaker identification
- handwriting recognition
- speech recognition systems
- speech recognition technology
- speech recognizers
- information retrieval
- broadcast news
- discriminative training
- semantic analysis
- signal processing
- keyword spotting
- cepstral coefficients
- isolated word