# Look, Listen and Learn - A Multimodal LSTM for Speaker Identification

arXiv: https://arxiv.org/abs/1602.04364 · HTML: https://mlsanity.com/paper/1602.04364/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2016.

## Built on by (most cited first, 4 of 4)

- [WASD: A Wilder Active Speaker Detection Dataset](https://mlsanity.com/paper/2303.05321/) (2023)
- [Audio-video fusion strategies for active speaker detection in meetings](https://mlsanity.com/paper/2206.10411/) (2022)
- [Multimodal Query-guided Object Localization](https://mlsanity.com/paper/2212.00749/) (2022)
- [Early Classifying Multimodal Sequences](https://mlsanity.com/paper/2305.01151/) (2023)

## Abstract (arXiv)

Speaker identification refers to the task of localizing the face of a person who has the same identity as the ongoing voice in a video. This task not only requires collective perception over both visual and auditory signals, the robustness to handle severe quality degradations and unconstrained content variations are also indispensable. In this paper, we describe a novel multimodal Long Short-Term Memory (LSTM) architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input. The key idea is to extend the conventional LSTM by not only sharing weights across time steps, but also sharing weights across modalities. We show that modeling the temporal dependency across face and voice can significantly improve the robustness to content quality degradations and variations. We also found that our multimodal LSTM is robustness to distractors, namely the non-speaking identities. We applied our multimodal LSTM to The Big Bang Theory dataset and showed that our system outperforms the state-of-the-art systems in speaker identification with lower false alarm rate and higher recognition accuracy.