Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914693279383552 |
|---|---|
| author | Diaz-Guerra, David Politis, Archontis Miguel, Antonio Beltran, Jose R. Virtanen, Tuomas |
| author_facet | Diaz-Guerra, David Politis, Archontis Miguel, Antonio Beltran, Jose R. Virtanen, Tuomas |
| contents | Many multi-source localization and tracking models based on neural networks use one or several recurrent layers at their final stages to track the movement of the sources. Conventional recurrent neural networks (RNNs), such as the long short-term memories (LSTMs) or the gated recurrent units (GRUs), take a vector as their input and use another vector to store their state. However, this approach results in the information from all the sources being contained in a single ordered vector, which is not optimal for permutation-invariant problems such as multi-source tracking. In this paper, we present a new recurrent architecture that uses unordered sets to represent both its input and its state and that is invariant to the permutations of the input set and equivariant to the permutations of the state set. Hence, the information of every sound source is represented in an individual embedding and the new estimates are assigned to the tracked trajectories regardless of their order. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_08510 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications Diaz-Guerra, David Politis, Archontis Miguel, Antonio Beltran, Jose R. Virtanen, Tuomas Audio and Speech Processing Machine Learning Sound Signal Processing Many multi-source localization and tracking models based on neural networks use one or several recurrent layers at their final stages to track the movement of the sources. Conventional recurrent neural networks (RNNs), such as the long short-term memories (LSTMs) or the gated recurrent units (GRUs), take a vector as their input and use another vector to store their state. However, this approach results in the information from all the sources being contained in a single ordered vector, which is not optimal for permutation-invariant problems such as multi-source tracking. In this paper, we present a new recurrent architecture that uses unordered sets to represent both its input and its state and that is invariant to the permutations of the input set and equivariant to the permutations of the state set. Hence, the information of every sound source is represented in an individual embedding and the new estimates are assigned to the tracked trajectories regardless of their order. |
| title | Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications |
| topic | Audio and Speech Processing Machine Learning Sound Signal Processing |
| url | https://arxiv.org/abs/2306.08510 |