4-Bit Quantization of LSTM-Based Speech Recognition Models.
Andrea FasoliChia-Yu ChenMauricio J. SerranoXiao SunNaigang WangSwagath VenkataramaniGeorge SaonXiaodong CuiBrian KingsburyWei ZhangZoltán TüskeKailash GopalakrishnanPublished in: Interspeech (2021)
Keyphrases
- speech recognition
- acoustic models
- language model
- hidden markov models
- speech signal
- speech understanding
- automatic speech recognition
- speech synthesis
- speech processing
- speech recognition systems
- speaker identification
- pattern recognition
- speaker dependent
- speech recognizer
- noisy environments
- probabilistic model
- speaker recognition
- broadcast news
- image compression
- speaker independent
- machine learning
- speech retrieval