Speech Audio Super-Resolution for Speech Recognition.
Xinyu LiVenkata ChebiyyamKatrin KirchhoffPublished in: INTERSPEECH (2019)
Keyphrases
- super resolution
- speech recognition
- speaker identification
- speech processing
- speech recognition technology
- low resolution
- automatic speech recognition
- speech signal
- high resolution
- speech recognizer
- broadcast news
- language model
- speech synthesis
- hidden markov models
- cepstral coefficients
- high quality
- image restoration
- pattern recognition
- speaker recognition
- voice activity detection
- speech recognition systems
- motion estimation
- acoustic features
- multimedia
- speaker independent
- noisy environments
- speaker dependent
- audio visual speech recognition
- visual information
- speech recognition errors
- audio visual
- speech recognizers
- mel frequency cepstral coefficients
- motion blur
- isolated word
- multi frame
- signal processing
- text to speech
- speaker adaptation
- music information retrieval
- speaker diarization
- multi stream
- audio features