Saved in:
Bibliographic Details
Main Authors: Elyaderani, Mahsa Kadkhodaei, Shirani, Shahram
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.01321
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911900627894272
author Elyaderani, Mahsa Kadkhodaei
Shirani, Shahram
author_facet Elyaderani, Mahsa Kadkhodaei
Shirani, Shahram
contents Speech in-painting is the task of regenerating missing audio contents using reliable context information. Despite various recent studies in multi-modal perception of audio in-painting, there is still a need for an effective infusion of visual and auditory information in speech in-painting. In this paper, we introduce a novel sequence-to-sequence model that leverages the visual information to in-paint audio signals via an encoder-decoder architecture. The encoder plays the role of a lip-reader for facial recordings and the decoder takes both encoder outputs as well as the distorted audio spectrograms to restore the original speech. Our model outperforms an audio-only speech in-painting model and has comparable results with a recent multi-modal speech in-painter in terms of speech quality and intelligibility metrics for distortions of 300 ms to 1500 ms duration, which proves the effectiveness of the introduced multi-modality in speech in-painting.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01321
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sequence-to-Sequence Multi-Modal Speech In-Painting
Elyaderani, Mahsa Kadkhodaei
Shirani, Shahram
Sound
Artificial Intelligence
Machine Learning
Multimedia
Audio and Speech Processing
Speech in-painting is the task of regenerating missing audio contents using reliable context information. Despite various recent studies in multi-modal perception of audio in-painting, there is still a need for an effective infusion of visual and auditory information in speech in-painting. In this paper, we introduce a novel sequence-to-sequence model that leverages the visual information to in-paint audio signals via an encoder-decoder architecture. The encoder plays the role of a lip-reader for facial recordings and the decoder takes both encoder outputs as well as the distorted audio spectrograms to restore the original speech. Our model outperforms an audio-only speech in-painting model and has comparable results with a recent multi-modal speech in-painter in terms of speech quality and intelligibility metrics for distortions of 300 ms to 1500 ms duration, which proves the effectiveness of the introduced multi-modality in speech in-painting.
title Sequence-to-Sequence Multi-Modal Speech In-Painting
topic Sound
Artificial Intelligence
Machine Learning
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2406.01321