Lightweight domain adaptation: A filtering pipeline to improve accuracy of an Automatic Speech Recognition (ASR) engine.
Jordan HosierYu ZhouNikhita SharmaVijay K. GurbaniPublished in: ACAI (2021)
Keyphrases
- automatic speech recognition
- lightweight
- domain adaptation
- speech recognition
- speech recognizers
- speech signal
- word error rate
- hidden markov models
- conversational speech
- speech retrieval
- broadcast news
- spoken words
- spontaneous speech
- multiple sources
- cross domain
- speech corpus
- transfer learning
- labeled data
- co training
- noisy environments
- unlabeled data
- semi supervised learning
- wireless sensor networks
- training data
- computer vision