Avoid Overthinking in Self-Supervised Models for Speech Recognition.
Dan BerrebbiBrian YanShinji WatanabePublished in: ICASSP (2023)
Keyphrases
- speech recognition
- speech processing
- hidden markov models
- language model
- acoustic models
- speech understanding
- speech synthesis
- automatic speech recognition
- pattern recognition
- model selection
- noisy environments
- speaker identification
- speech signal
- signal processing
- autoregressive
- probabilistic model
- speaker independent