Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training.
Gege QiYuefeng ChenXiaofeng MaoXiaojun JiaRanjie DuanRong ZhangHui XuePublished in: CoRR (2023)
Keyphrases
- automatic speech recognition
- speech recognition
- discriminative training
- noisy environments
- speech signal
- hidden markov models
- word error rate
- acoustic models
- spoken words
- recognition errors
- word recognition
- broadcast news
- acoustic features
- language model
- spontaneous speech
- conversational speech
- speech retrieval
- phoneme recognition
- information retrieval
- speaker adaptation
- speech corpus
- speech sounds
- data mining
- speech synthesis
- feature vectors