Transducers with Pronunciation-Aware Embeddings for Automatic Speech Recognition.
Hainan XuZhehuai ChenFei JiaBoris GinsburgPublished in: ICASSP (2024)
Keyphrases
- automatic speech recognition
- speech recognition
- spontaneous speech
- hidden markov models
- word error rate
- speech signal
- broadcast news
- conversational speech
- vector space
- speech retrieval
- discriminative training
- acoustic models
- word recognition
- recognition errors
- spoken words
- acoustic features
- noisy environments
- speech recognizer
- speech sounds
- machine learning
- speech synthesis
- image patches
- speech corpus
- information retrieval systems