Improving CTC-Based Speech Recognition Via Knowledge Transferring from Pre-Trained Language Models.
Keqi DengSongjun CaoYike ZhangLong MaGaofeng ChengJi XuPengyuan ZhangPublished in: ICASSP (2022)
Keyphrases
- speech recognition
- language model
- language modeling
- pre trained
- automatic speech recognition
- probabilistic model
- document retrieval
- query expansion
- pattern recognition
- retrieval model
- hidden markov models
- speech signal
- n gram
- information retrieval
- handwriting recognition
- query terms
- mixture model
- speech recognition systems
- machine learning
- prior knowledge
- test collection
- generative model
- training data
- multimedia
- computer vision
- relevance model
- data mining
- neural network