Open-vocabulary keyword spotting in any language through multilingual contrastive speech-phoneme pretraining.
Jian ZhuFarhan SamirChangbing YangJahurul IslamPublished in: CoRR (2023)
Keyphrases
- keyword spotting
- speech recognition
- speech synthesis
- speech processing
- hidden markov models
- automatic speech recognition
- speech signal
- language model
- pattern recognition
- language resources
- speaker dependent
- handwriting recognition
- digital libraries
- speaker identification
- english text
- text to speech
- natural language
- vocal tract
- noisy environments
- printed documents
- machine translation
- natural language processing
- vowel phonemes
- cross language
- metadata
- signal processing
- language independent
- audio visual