Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition.
Yukiya HonoKoh MitsudaTianyu ZhaoKentaro MitsuiToshiaki WakatsukiKei SawadaPublished in: ACL (Findings) (2024)
Keyphrases
- speech recognition
- end to end
- language model
- pre trained
- speech signal
- speech synthesis
- language modeling
- automatic speech recognition
- document retrieval
- training data
- n gram
- probabilistic model
- speech recognizer
- test collection
- speech recognition systems
- word error rate
- query expansion
- speaker identification
- information retrieval
- noisy environments
- speech recognition technology
- retrieval model
- isolated word
- training examples
- speaker dependent
- handwriting recognition
- mixture model
- hidden markov models
- speaker independent
- pattern recognition
- non stationary