Synthesizing Dysarthric Speech Using Multi-Speaker Tts For Dysarthric Speech Recognition.
Mohammad SoleymanpourMichael T. JohnsonRahim SoleymanpourJeffrey BerryPublished in: ICASSP (2022)
Keyphrases
- speech recognition
- speech synthesis
- prosodic features
- automatic speech recognition
- speech signal
- text to speech
- hidden markov models
- speech recognizer
- speaker identification
- language model
- speaker dependent
- speech recognition systems
- speech processing
- speaker independent
- vocal tract
- pattern recognition
- speech recognition technology
- speaker diarization
- speaker recognition
- word error rate
- speech recognizers
- speaker adaptation
- keyword spotting
- acoustic models
- isolated word
- noisy environments
- speech retrieval
- noisy speech
- recognition engine
- handwriting recognition
- hybrid method
- non stationary
- probabilistic model
- computer vision
- machine learning