Search Results for author: Ahmed Mustafa

Found 12 papers, 5 papers with code

Efficient Evaluation of Quantization-Effects in Neural Codecs

no code implementations7 Feb 2025 Wolfgang Mack, Ahmed Mustafa, Rafał Łaganowski, Samer Hijazy

Neural codecs, comprising an encoder, quantizer, and decoder, enable signal transmission at exceptionally low bitrates.

Decoder Quantization

Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion

no code implementations28 Aug 2024 Muhammad Tahir Rafique, Ahmed Mustafa, Hasan Sajid

The growing demand for road use in urban areas has led to significant traffic congestion, posing challenges that are costly to mitigate through infrastructure expansion alone.

reinforcement-learning Reinforcement Learning (RL) +1

A Permuted Autoregressive Approach to Word-Level Recognition for Urdu Digital Text

no code implementations27 Aug 2024 Ahmed Mustafa, Muhammad Tahir Rafique, Muhammad Ijlal Baig, Hasan Sajid, Muhammad Jawad Khan, Karam Dad Kallu

This research paper introduces a novel word-level Optical Character Recognition (OCR) model specifically designed for digital Urdu text, leveraging transformer-based architectures and attention mechanisms to address the distinct challenges of Urdu script recognition, including its diverse text styles, fonts, and variations.

Data Augmentation Optical Character Recognition +1

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

1 code implementation13 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.

DRED: Deep REDundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder

no code implementations8 Dec 2022 Jean-Marc Valin, Jan Büthe, Ahmed Mustafa, Michael Klingbeil

Despite recent advancements in packet loss concealment (PLC) using deep learning techniques, packet loss remains a significant challenge in real-time speech communication.

Packet Loss Concealment

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

no code implementations8 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.

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

1 code implementation11 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).

Packet Loss Concealment Speech Synthesis

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

no code implementations9 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.

Speech Synthesis

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

2 code implementations3 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.

Spectral Reconstruction Text to Speech +1

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

no code implementations1 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.