Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognition.
Hainan XuZhehuai ChenFei JiaBoris GinsburgPublished in: CoRR (2024)
Keyphrases
- automatic speech recognition
- speech recognition
- spontaneous speech
- speech signal
- hidden markov models
- word error rate
- noisy environments
- speech retrieval
- vector space
- broadcast news
- acoustic models
- conversational speech
- recognition errors
- word recognition
- spoken words
- speech corpus
- speaker identification
- language model
- speaker independent
- speech recognizer
- speech synthesis
- speaker adaptation
- bayesian networks