Improving the response timing estimation for spoken dialogue systems by reducing the effect of speech recognition delay.
Jin SakumaShinya FujieHuaibo ZhaoTetsunori KobayashiPublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- spoken dialogue systems
- hidden markov models
- language model
- dialogue system
- speech processing
- human machine interaction
- pattern recognition
- automatic speech recognition
- speech synthesis
- speech recognition technology
- multi domain
- noisy environments
- speaker identification
- computer vision
- speech signal
- speech recognizers
- speech recognizer
- context aware
- information retrieval
- neural network
- speech recognition systems
- isolated word
- speaker adaptation
- artificial intelligence
- data mining