Zero Shot Text to Speech Augmentation for Automatic Speech Recognition on Low-Resource Accented Speech Corpora.
Francesco NespoliDaniel BarredaPatrick A. NaylorPublished in: ACSSC (2023)
Keyphrases
- automatic speech recognition
- text to speech
- speech synthesis
- speech recognition
- speech corpus
- speech signal
- prosodic features
- spontaneous speech
- word error rate
- broadcast news
- hidden markov models
- conversational speech
- text to speech synthesis
- noisy environments
- vocal tract
- english text
- spoken words
- acoustic features
- speech recognizer
- speech retrieval
- pattern recognition
- language model
- natural language processing
- word recognition
- word processing
- recognition errors
- speech sounds
- speech recognizers
- writing skills
- visual features
- speech segments
- phoneme recognition
- non stationary