Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis.
Wing-Zin LeungMattias CrossAnton RagniStefan GoetzePublished in: CoRR (2024)
Keyphrases
- speech synthesis
- speech recognition
- automatic speech recognition
- training data
- speech corpus
- conversational speech
- text to speech
- speech signal
- spontaneous speech
- spoken words
- vocal tract
- acoustic models
- hidden markov models
- word error rate
- noisy environments
- language model
- speech retrieval
- speech recognizer
- speech sounds
- pattern recognition
- word recognition
- broadcast news
- speaker identification
- information retrieval
- recognition errors
- acoustic features
- handwriting recognition
- text retrieval
- keywords
- spoken language