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