Guardado en:
Detalles Bibliográficos
Autores principales: Jain, Arnav, Sanjotra, Jasmer Singh, Choudhary, Harshvardhan, Agrawal, Krish, Shah, Rupal, Jha, Rohan, Sajid, M., Hussain, Amir, Tanveer, M.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2409.02266
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916607496814592
author Jain, Arnav
Sanjotra, Jasmer Singh
Choudhary, Harshvardhan
Agrawal, Krish
Shah, Rupal
Jha, Rohan
Sajid, M.
Hussain, Amir
Tanveer, M.
author_facet Jain, Arnav
Sanjotra, Jasmer Singh
Choudhary, Harshvardhan
Agrawal, Krish
Shah, Rupal
Jha, Rohan
Sajid, M.
Hussain, Amir
Tanveer, M.
contents In this paper, we propose long short term memory speech enhancement network (LSTMSE-Net), an audio-visual speech enhancement (AVSE) method. This innovative method leverages the complementary nature of visual and audio information to boost the quality of speech signals. Visual features are extracted with VisualFeatNet (VFN), and audio features are processed through an encoder and decoder. The system scales and concatenates visual and audio features, then processes them through a separator network for optimized speech enhancement. The architecture highlights advancements in leveraging multi-modal data and interpolation techniques for robust AVSE challenge systems. The performance of LSTMSE-Net surpasses that of the baseline model from the COG-MHEAR AVSE Challenge 2024 by a margin of 0.06 in scale-invariant signal-to-distortion ratio (SISDR), $0.03$ in short-time objective intelligibility (STOI), and $1.32$ in perceptual evaluation of speech quality (PESQ). The source code of the proposed LSTMSE-Net is available at \url{https://github.com/mtanveer1/AVSEC-3-Challenge}.
format Preprint
id arxiv_https___arxiv_org_abs_2409_02266
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LSTMSE-Net: Long Short Term Speech Enhancement Network for Audio-visual Speech Enhancement
Jain, Arnav
Sanjotra, Jasmer Singh
Choudhary, Harshvardhan
Agrawal, Krish
Shah, Rupal
Jha, Rohan
Sajid, M.
Hussain, Amir
Tanveer, M.
Sound
Machine Learning
Multimedia
Audio and Speech Processing
In this paper, we propose long short term memory speech enhancement network (LSTMSE-Net), an audio-visual speech enhancement (AVSE) method. This innovative method leverages the complementary nature of visual and audio information to boost the quality of speech signals. Visual features are extracted with VisualFeatNet (VFN), and audio features are processed through an encoder and decoder. The system scales and concatenates visual and audio features, then processes them through a separator network for optimized speech enhancement. The architecture highlights advancements in leveraging multi-modal data and interpolation techniques for robust AVSE challenge systems. The performance of LSTMSE-Net surpasses that of the baseline model from the COG-MHEAR AVSE Challenge 2024 by a margin of 0.06 in scale-invariant signal-to-distortion ratio (SISDR), $0.03$ in short-time objective intelligibility (STOI), and $1.32$ in perceptual evaluation of speech quality (PESQ). The source code of the proposed LSTMSE-Net is available at \url{https://github.com/mtanveer1/AVSEC-3-Challenge}.
title LSTMSE-Net: Long Short Term Speech Enhancement Network for Audio-visual Speech Enhancement
topic Sound
Machine Learning
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2409.02266