Deep Speaker Embedding for Speaker-Targeted Automatic Speech Recognition.
Guan-Lin ChaoJohn Paul ShenIan R. LanePublished in: NLPIR (2019)
Keyphrases
- automatic speech recognition
- speech recognition
- hidden markov models
- word error rate
- speech signal
- broadcast news
- word recognition
- noisy environments
- spoken words
- speech retrieval
- acoustic features
- recognition errors
- conversational speech
- spontaneous speech
- computer vision
- vector space
- speaker adaptation
- speech corpus
- speech sounds
- pattern recognition
- multiscale
- bayesian networks