Picture for Ahmed Mustafa

Ahmed Mustafa

Very Low Complexity Speech Synthesis Using Framewise Autoregressive GAN (FARGAN) with Pitch Prediction

Add code
May 31, 2024
Viaarxiv icon

NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping

Add code
Sep 25, 2023
Figure 1 for NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping
Figure 2 for NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping
Figure 3 for NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping
Figure 4 for NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping
Viaarxiv icon

LACE: A light-weight, causal model for enhancing coded speech through adaptive convolutions

Add code
Jul 13, 2023
Figure 1 for LACE: A light-weight, causal model for enhancing coded speech through adaptive convolutions
Figure 2 for LACE: A light-weight, causal model for enhancing coded speech through adaptive convolutions
Figure 3 for LACE: A light-weight, causal model for enhancing coded speech through adaptive convolutions
Figure 4 for LACE: A light-weight, causal model for enhancing coded speech through adaptive convolutions
Viaarxiv icon

Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity

Add code
Dec 08, 2022
Figure 1 for Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
Figure 2 for Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
Figure 3 for Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
Viaarxiv icon

Low-Bitrate Redundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder

Add code
Dec 08, 2022
Figure 1 for Low-Bitrate Redundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder
Figure 2 for Low-Bitrate Redundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder
Figure 3 for Low-Bitrate Redundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder
Viaarxiv icon

Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model

Add code
May 11, 2022
Figure 1 for Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
Figure 2 for Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
Figure 3 for Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
Figure 4 for Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
Viaarxiv icon

A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate

Add code
Aug 09, 2021
Figure 1 for A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate
Figure 2 for A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate
Figure 3 for A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate
Figure 4 for A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate
Viaarxiv icon

StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization

Add code
Nov 03, 2020
Figure 1 for StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization
Figure 2 for StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization
Figure 3 for StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization
Figure 4 for StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization
Viaarxiv icon

Analysis by Adversarial Synthesis -- A Novel Approach for Speech Vocoding

Add code
Jul 01, 2019
Figure 1 for Analysis by Adversarial Synthesis -- A Novel Approach for Speech Vocoding
Figure 2 for Analysis by Adversarial Synthesis -- A Novel Approach for Speech Vocoding
Figure 3 for Analysis by Adversarial Synthesis -- A Novel Approach for Speech Vocoding
Figure 4 for Analysis by Adversarial Synthesis -- A Novel Approach for Speech Vocoding
Viaarxiv icon