Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition.
Shaoshi LingYuzong LiuJulian SalazarKatrin KirchhoffPublished in: CoRR (2019)
Keyphrases
- speech recognition
- semi supervised
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- hidden markov models
- speech recognizer
- automatic speech recognition
- speech processing
- language model
- semi supervised learning
- pattern recognition
- speech recognition technology
- noisy speech
- speech synthesis
- speech signal
- noisy environments
- speaker identification
- speech understanding
- speaker dependent
- labeled data
- keyword spotting
- pairwise
- speech retrieval
- acoustic features
- speaker diarization
- active learning
- computer vision
- speech enhancement
- mel frequency cepstral coefficients
- information retrieval
- speaker recognition
- speech recognition errors
- co training
- training data