Intermediate Fine-Tuning Using Imperfect Synthetic Speech for Improving Electrolaryngeal Speech Recognition.
Lester Phillip VioletaDing MaWen-Chin HuangTomoki TodaPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- fine tuning
- speech synthesis
- speech signal
- automatic speech recognition
- speech recognizer
- hidden markov models
- pattern recognition
- language model
- speech processing
- speech recognition systems
- fine tuned
- noisy environments
- speaker identification
- recognition engine
- handwriting recognition
- speech recognition technology
- word error rate
- speaker independent
- speech recognition errors
- isolated word
- speaker dependent
- computer vision
- noisy speech
- keyword spotting
- acoustic models
- cepstral coefficients
- speech recognizers
- voice activity detection