Reconstructing Speech From CNN Embeddings.
Luca ComanducciPaolo BestaginiMarco TagliasacchiAugusto SartiStefano TubaroPublished in: IEEE Signal Process. Lett. (2021)
Keyphrases
- speech recognition
- cellular neural networks
- speech signal
- low dimensional
- automatic speech recognition
- vector space
- audio visual
- dimensionality reduction
- speech synthesis
- speaker recognition
- dialogue system
- spoken language
- speaker identification
- text to speech
- english text
- speech processing
- recognition engine
- convolutional neural network
- endpoint detection
- euclidean space
- noisy environments
- fixed point
- broadcast news
- distance measure
- multimodal interfaces
- genetic algorithm