Generative De-Quantization for Neural Speech Codec Via Latent Diffusion.
Haici YangInseon JangMinje KimPublished in: ICASSP (2024)
Keyphrases
- network architecture
- speech recognition
- speech signal
- neural network
- anisotropic diffusion
- latent variables
- generative model
- audio visual
- speech synthesis
- diffusion process
- bitstream
- broadcast news
- video codec
- associative memory
- text to speech
- video coding
- automatic speech recognition
- diffusion model
- spoken language
- generative process
- tensor field
- distributed video coding
- information diffusion
- dialogue system
- edge detection
- denoising
- social networks