End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training.
Heng-Jui ChangAlexander H. LiuHung-yi LeeLin-Shan LeePublished in: SLT (2021)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- wall street journal corpus
- speech recognition systems
- language model
- speech signal
- speech processing
- cepstral coefficients
- automatic speech recognition
- pattern recognition
- speech recognition technology
- speech recognizer
- congestion control
- speech recognizers
- speech synthesis
- noisy environments
- isolated word
- speaker identification
- probabilistic model
- speech retrieval
- maximum likelihood
- signal processing