Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.01518 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909447550402560 |
|---|---|
| author | Rahimi, Akam Afouras, Triantafyllos Zisserman, Andrew |
| author_facet | Rahimi, Akam Afouras, Triantafyllos Zisserman, Andrew |
| contents | The goal of this paper is speech separation and enhancement in multi-speaker and noisy environments using a combination of different modalities. Previous works have shown good performance when conditioning on temporal or static visual evidence such as synchronised lip movements or face identity. In this paper, we present a unified framework for multi-modal speech separation and enhancement based on synchronous or asynchronous cues. To that end we make the following contributions: (i) we design a modern Transformer-based architecture tailored to fuse different modalities to solve the speech separation task in the raw waveform domain; (ii) we propose conditioning on the textual content of a sentence alone or in combination with visual information; (iii) we demonstrate the robustness of our model to audio-visual synchronisation offsets; and, (iv) we obtain state-of-the-art performance on the well-established benchmark datasets LRS2 and LRS3. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01518 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reading to Listen at the Cocktail Party: Multi-Modal Speech Separation Rahimi, Akam Afouras, Triantafyllos Zisserman, Andrew Audio and Speech Processing Sound Signal Processing The goal of this paper is speech separation and enhancement in multi-speaker and noisy environments using a combination of different modalities. Previous works have shown good performance when conditioning on temporal or static visual evidence such as synchronised lip movements or face identity. In this paper, we present a unified framework for multi-modal speech separation and enhancement based on synchronous or asynchronous cues. To that end we make the following contributions: (i) we design a modern Transformer-based architecture tailored to fuse different modalities to solve the speech separation task in the raw waveform domain; (ii) we propose conditioning on the textual content of a sentence alone or in combination with visual information; (iii) we demonstrate the robustness of our model to audio-visual synchronisation offsets; and, (iv) we obtain state-of-the-art performance on the well-established benchmark datasets LRS2 and LRS3. |
| title | Reading to Listen at the Cocktail Party: Multi-Modal Speech Separation |
| topic | Audio and Speech Processing Sound Signal Processing |
| url | https://arxiv.org/abs/2501.01518 |