Mixup Augmentation for Generalizable Speech Separation.
Ashish AlexLin WangPaolo GastaldoAndrea CavallaroPublished in: MMSP (2021)
Keyphrases
- speech recognition
- speech synthesis
- endpoint detection
- automatic speech recognition
- recognition engine
- speech signal
- speech processing
- dialogue system
- speaker recognition
- hearing impaired
- databases
- text to speech synthesis
- audio stream
- speech corpus
- spontaneous speech
- spoken language
- noisy environments
- multi modal
- social networks
- neural network