HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement
By Pavel Andreev, Aibek Alanov, Oleg Ivanov, Dmitry P. Vetrov. 2022
24 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Speech & Audio, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yossi Adi
- Gabriel Synnaeve
- Jade Copet
- Alexandre D'efossez
- Wei-Ning Hsu
- Ronan Collobert
- Emmanuel Dupoux
- Abdel-rahman Mohamed
In Computer Vision and Pattern Recognition
- Yossi Adi
- Gabriel Synnaeve
- Alexandre D'efossez
- Jade Copet
- Luc Van Gool
- Xiaogang Wang
- Dacheng Tao
- Jiashi Feng
In Speech & Audio
- Yossi Adi
- Gabriel Synnaeve
- Jade Copet
- Alexandre D'efossez
- Wei-Ning Hsu
- Jinyu Li
- Ronan Collobert
- Bowen Shi
In Signal Processing
- Yossi Adi
- Gabriel Synnaeve
- Jade Copet
- Alexandre D'efossez
- Wei-Ning Hsu
- Jinyu Li
- Ronan Collobert
- Bowen Shi
Citations in the corpus
- High Fidelity Neural Audio Compression (2022, methodology): “The Multi-Scale Discriminator (MSD) model proposed by Kumar et al. (2019) and adopted in (Kong et al., 2020; Andreev et al., 2022; Zeghidour et al., 2021), operates on the raw waveform at different resolutions.”
- HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis (2022, unknown): “, 2022b) in the decoder and simplifying the discriminator to facilitate more rapid training (Andreev et al., 2022), and replace the decoder with an diffusion-based neural vocoder (Koizumi et al.”