Speech Intelligibility Enhancement By Non-Parallel Speech Style Conversion Using CWT and iMetricGAN Based CycleGAN.
Jing XiaoJiaqi LiuDengshi LiLanxin ZhaoQianrui WangPublished in: MMM (1) (2022)
Keyphrases
- speech recognition
- speech signal
- speech synthesis
- audio visual
- automatic speech recognition
- hidden markov models
- recognition engine
- text to speech
- speaker identification
- shared memory
- speech processing
- dialogue system
- parallel processing
- image enhancement
- language model
- computer architecture
- endpoint detection
- speech recognizer
- text to speech synthesis
- automatic speech recognition systems
- spoken language
- linear prediction
- noisy environments
- data sets
- image processing
- information retrieval