Categorical Unsupervised Variational Acoustic Clustering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914267501953024 |
|---|---|
| author | Fiorio, Luan Vinícius Nikoloska, Ivana Aarts, Ronald M. |
| author_facet | Fiorio, Luan Vinícius Nikoloska, Ivana Aarts, Ronald M. |
| contents | We propose a categorical approach for unsupervised variational acoustic clustering of audio data in the time-frequency domain. The consideration of a categorical distribution enforces sharper clustering even when data points strongly overlap in time and frequency, which is the case for most datasets of urban acoustic scenes. To this end, we use a Gumbel-Softmax distribution as a soft approximation to the categorical distribution, allowing for training via backpropagation. In this settings, the softmax temperature serves as the main mechanism to tune clustering performance. The results show that the proposed model can obtain impressive clustering performance for all considered datasets, even when data points strongly overlap in time and frequency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07652 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Categorical Unsupervised Variational Acoustic Clustering Fiorio, Luan Vinícius Nikoloska, Ivana Aarts, Ronald M. Audio and Speech Processing We propose a categorical approach for unsupervised variational acoustic clustering of audio data in the time-frequency domain. The consideration of a categorical distribution enforces sharper clustering even when data points strongly overlap in time and frequency, which is the case for most datasets of urban acoustic scenes. To this end, we use a Gumbel-Softmax distribution as a soft approximation to the categorical distribution, allowing for training via backpropagation. In this settings, the softmax temperature serves as the main mechanism to tune clustering performance. The results show that the proposed model can obtain impressive clustering performance for all considered datasets, even when data points strongly overlap in time and frequency. |
| title | Categorical Unsupervised Variational Acoustic Clustering |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2504.07652 |