Guardado en:
Detalles Bibliográficos
Autores principales: Salhab, Mahmoud, Harmanani, Haidar
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2407.18571
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913450139058176
author Salhab, Mahmoud
Harmanani, Haidar
author_facet Salhab, Mahmoud
Harmanani, Haidar
contents Speech bandwidth expansion is crucial for expanding the frequency range of low-bandwidth speech signals, thereby improving audio quality, clarity and perceptibility in digital applications. Its applications span telephony, compression, text-to-speech synthesis, and speech recognition. This paper presents a novel approach using a high-fidelity generative adversarial network, unlike cascaded systems, our system is trained end-to-end on paired narrowband and wideband speech signals. Our method integrates various bandwidth upsampling ratios into a single unified model specifically designed for speech bandwidth expansion applications. Our approach exhibits robust performance across various bandwidth expansion factors, including those not encountered during training, demonstrating zero-shot capability. To the best of our knowledge, this is the first work to showcase this capability. The experimental results demonstrate that our method outperforms previous end-to-end approaches, as well as interpolation and traditional techniques, showcasing its effectiveness in practical speech enhancement applications.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18571
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networks
Salhab, Mahmoud
Harmanani, Haidar
Sound
Artificial Intelligence
Audio and Speech Processing
Speech bandwidth expansion is crucial for expanding the frequency range of low-bandwidth speech signals, thereby improving audio quality, clarity and perceptibility in digital applications. Its applications span telephony, compression, text-to-speech synthesis, and speech recognition. This paper presents a novel approach using a high-fidelity generative adversarial network, unlike cascaded systems, our system is trained end-to-end on paired narrowband and wideband speech signals. Our method integrates various bandwidth upsampling ratios into a single unified model specifically designed for speech bandwidth expansion applications. Our approach exhibits robust performance across various bandwidth expansion factors, including those not encountered during training, demonstrating zero-shot capability. To the best of our knowledge, this is the first work to showcase this capability. The experimental results demonstrate that our method outperforms previous end-to-end approaches, as well as interpolation and traditional techniques, showcasing its effectiveness in practical speech enhancement applications.
title Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networks
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2407.18571