Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding.
Wei WangShuo RenYao QianShujie LiuYu ShiYanmin QianMichael ZengPublished in: ICASSP (2022)
Keyphrases
- end to end
- speech recognition
- isolated word
- speech synthesis
- speech recognizer
- speech signal
- automatic speech recognition
- speech processing
- hidden markov models
- spoken language
- speech recognition technology
- speaker identification
- speech recognition systems
- language model
- pattern recognition
- speaker independent
- text to speech
- speech recognizers
- speech recognition errors
- congestion control
- speaker recognition
- recognition engine
- noisy environments
- word error rate
- acoustic models
- natural language
- noisy speech
- multimedia
- image processing
- keyword spotting
- machine learning
- language processing