Effectiveness of text to speech pseudo labels for forced alignment and cross lingual pretrained models for low resource speech recognition.
Anirudh GuptaRishabh GaurAnkur DhuriyaHarveen Singh ChadhaNeeraj ChhimwalPriyanshi ShahVivek RaghavanPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speech synthesis
- text to speech
- cross lingual
- language model
- hidden markov models
- automatic speech recognition
- machine translation
- language modeling
- speech signal
- probabilistic model
- pattern recognition
- word alignment
- translation model
- speaker identification
- neural network
- noisy environments
- language independent
- cross language
- news articles