no code implementations • 25 Sep 2023 • Jan Büthe, Ahmed Mustafa, Jean-Marc Valin, Karim Helwani, Michael M. Goodwin
Speech codec enhancement methods are designed to remove distortions added by speech codecs.
no code implementations • 13 Jul 2023 • Jan Büthe, Jean-Marc Valin, Ahmed Mustafa
Classical speech coding uses low-complexity postfilters with zero lookahead to enhance the quality of coded speech, but their effectiveness is limited by their simplicity.
no code implementations • 8 Dec 2022 • Ahmed Mustafa, Jean-Marc Valin, Jan Büthe, Paris Smaragdis, Mike Goodwin
GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models.
no code implementations • 8 Dec 2022 • Jean-Marc Valin, Jan Büthe, Ahmed Mustafa
Robustness to packet loss is one of the main ongoing challenges in real-time speech communication.
1 code implementation • 11 May 2022 • Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery, Timothy B. Terriberry, Michael Klingbeil, Paris Smaragdis, Arvindh Krishnaswamy
As deep speech enhancement algorithms have recently demonstrated capabilities greatly surpassing their traditional counterparts for suppressing noise, reverberation and echo, attention is turning to the problem of packet loss concealment (PLC).
no code implementations • 9 Aug 2021 • Ahmed Mustafa, Jan Büthe, Srikanth Korse, Kishan Gupta, Guillaume Fuchs, Nicola Pia
Recently, GAN vocoders have seen rapid progress in speech synthesis, starting to outperform autoregressive models in perceptual quality with much higher generation speed.
2 code implementations • 3 Nov 2020 • Ahmed Mustafa, Nicola Pia, Guillaume Fuchs
In recent years, neural vocoders have surpassed classical speech generation approaches in naturalness and perceptual quality of the synthesized speech.
no code implementations • 1 Jul 2019 • Ahmed Mustafa, Arijit Biswas, Christian Bergler, Julia Schottenhamml, Andreas Maier
Recently, autoregressive deep generative models such as WaveNet and SampleRNN have been used as speech vocoders to scale up the perceptual quality of the reconstructed signals without increasing the coding rate.