FedNST: Federated Noisy Student Training for Automatic Speech Recognition.
Haaris MehmoodAgnieszka DobrowolskaKarthikeyan SaravananMete OzayPublished in: INTERSPEECH (2022)
Keyphrases
- automatic speech recognition
- noisy environments
- speech recognition
- discriminative training
- speech signal
- hidden markov models
- broadcast news
- word error rate
- learning environment
- speech retrieval
- speech corpus
- learning styles
- acoustic models
- recognition errors
- spontaneous speech
- spoken words
- conversational speech
- multimedia
- acoustic features
- word recognition
- speech synthesis
- training process
- noise reduction
- error rate
- information retrieval systems
- digital libraries