A Reference-Less Quality Metric for Automatic Speech Recognition Via Contrastive-Learning of A Multi-Language Model with Self-Supervision.
Kamer Ali YukselThiago Castro FerreiraAhmet GunduzMohamed Al-BadrashinyGolara JavadiPublished in: ICASSP Workshops (2023)
Keyphrases
- language model
- speech recognition
- automatic speech recognition
- word error rate
- language modeling
- probabilistic model
- n gram
- information retrieval
- hidden markov models
- wavelet transform
- mixture model
- document retrieval
- quality metrics
- pattern recognition
- query expansion
- information extraction
- low level
- retrieval model
- speech signal
- machine learning