Categorical Unsupervised Variational Acoustic Clustering

2025-04-10 · Luan Vinícius Fiorio, Ivana Nikoloska, Ronald M. Aarts

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.

📄 PDF Abstract BibTeX arXiv:2504.07652

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Unsupervised Variational Acoustic Clustering

2025-03-24 · Luan Vinícius Fiorio, Bruno Defraene, Johan David, Frans Widdershoven 외

We propose an unsupervised variational acoustic clustering model for clustering audio data in the time-frequency domain. The model leverages variational inference, extended to an autoencoder framework, with a Gaussian mi…

Clustering Variational Inference

InfoCatVAE: Representation Learning with Categorical Variational Autoencoders

2018-06-20 · Edouard Pineau, Marc Lelarge

This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning. InfoCatVAE uses multimodal distributions for the prior and the inference networ…

Clustering Representation Learning

Multi-Facet Clustering Variational Autoencoders

2021-06-09 · NeurIPS 2021 12 · Fabian Falck, Haoting Zhang, Matthew Willetts, George Nicholson 외

Work in deep clustering focuses on finding a single partition of data. However, high-dimensional data, such as images, typically feature multiple interesting characteristics one could cluster over. For example, images of…

Clustering Deep Clustering

Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks

2019-04-16 · Ryan Eloff, André Nortje, Benjamin van Niekerk, Avashna Govender 외

For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could…

Acoustic Unit Discovery Decoder Speech Synthesis

Unsupervised Clustered Federated Learning in Complex Multi-source Acoustic Environments

2021-06-07 · Alexandru Nelus, Rene Glitza, Rainer Martin

In this paper we introduce a realistic and challenging, multi-source and multi-room acoustic environment and an improved algorithm for the estimation of source-dominated microphone clusters in acoustic sensor networks. O…

Clustering Federated Learning