Deep Contextualized Acoustic Representations for Semi-Supervised Speech Recognition.
Shaoshi LingYuzong LiuJulian SalazarKatrin KirchhoffPublished in: ICASSP (2020)
Keyphrases
- speech recognition
- semi supervised
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- hidden markov models
- speech signal
- speech recognizer
- language model
- automatic speech recognition
- semi supervised learning
- speech synthesis
- noisy speech
- speaker identification
- labeled data
- speech processing
- pattern recognition
- noisy environments
- acoustic features
- speech recognition technology
- speaker dependent
- co training
- speech understanding
- active learning
- keyword spotting
- isolated word
- speaker recognition
- unsupervised learning
- speech retrieval
- pairwise