Saved in:
Bibliographic Details
Main Authors: Rahimi, Akam, Afouras, Triantafyllos, Zisserman, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.01401
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912175550889984
author Rahimi, Akam
Afouras, Triantafyllos
Zisserman, Andrew
author_facet Rahimi, Akam
Afouras, Triantafyllos
Zisserman, Andrew
contents We present a transformer-based architecture for voice separation of a target speaker from multiple other speakers and ambient noise. We achieve this by using two separate neural networks: (A) An enrolment network designed to craft speaker-specific embeddings, exploiting various combinations of audio and visual modalities; and (B) A separation network that accepts both the noisy signal and enrolment vectors as inputs, outputting the clean signal of the target speaker. The novelties are: (i) the enrolment vector can be produced from: audio only, audio-visual data (using lip movements) or visual data alone (using lip movements from silent video); and (ii) the flexibility in conditioning the separation on multiple positive and negative enrolment vectors. We compare with previous methods and obtain superior performance.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01401
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VoiceVector: Multimodal Enrolment Vectors for Speaker Separation
Rahimi, Akam
Afouras, Triantafyllos
Zisserman, Andrew
Audio and Speech Processing
We present a transformer-based architecture for voice separation of a target speaker from multiple other speakers and ambient noise. We achieve this by using two separate neural networks: (A) An enrolment network designed to craft speaker-specific embeddings, exploiting various combinations of audio and visual modalities; and (B) A separation network that accepts both the noisy signal and enrolment vectors as inputs, outputting the clean signal of the target speaker. The novelties are: (i) the enrolment vector can be produced from: audio only, audio-visual data (using lip movements) or visual data alone (using lip movements from silent video); and (ii) the flexibility in conditioning the separation on multiple positive and negative enrolment vectors. We compare with previous methods and obtain superior performance.
title VoiceVector: Multimodal Enrolment Vectors for Speaker Separation
topic Audio and Speech Processing
url https://arxiv.org/abs/2501.01401