pMCT: Patched Multi-Condition Training for Robust Speech Recognition.
Pablo Peso ParadaAgnieszka DobrowolskaKarthikeyan SaravananMete OzayPublished in: CoRR (2022)
Keyphrases
- speech recognition
- noisy environments
- wall street journal corpus
- hidden markov models
- language model
- speech recognizer
- acoustic models
- speech processing
- speech synthesis
- isolated word
- speech signal
- automatic speech recognition
- speech understanding
- speech recognition technology
- speaker identification
- pattern recognition
- keyword spotting
- training set
- speaker recognition
- machine learning
- speaker dependent
- speech recognition systems
- speaker independent
- speech retrieval