Improving RNN Transducer Acoustic Models for English Conversational Speech Recognition.
Xiaodong CuiGeorge SaonBrian KingsburyPublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- acoustic models
- speech recognition technology
- broadcast news
- speech recognizer
- spoken language
- automatic speech recognition
- hidden markov models
- speaker independent
- language model
- natural language
- conversational speech
- pattern recognition
- speaker identification
- noisy environments
- speech signal
- multi modal
- speech recognition systems
- discriminative training
- machine translation
- dialogue system
- cross lingual
- information retrieval