Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching.
Tolúlopé ÒgúnrèmíChristopher D. ManningDan JurafskyPublished in: CoRR (2023)
Keyphrases
- speech recognition
- speech signal
- speech synthesis
- automatic speech recognition
- hidden markov models
- speech recognition technology
- speech processing
- speech recognizer
- speaker identification
- pattern recognition
- multi lingual
- language independent
- speech recognition systems
- language model
- noisy environments
- language identification
- cross lingual
- word error rate
- keyword spotting
- speaker independent
- cepstral coefficients
- speech recognition errors
- speech recognizers
- neural network
- isolated word
- speech retrieval
- noisy speech
- speech enhancement
- speaker diarization
- signal processing
- image processing