English
Related papers

Related papers: Low-Complexity Audio Embedding Extractors

200 papers

Speaker embedding extractors significantly influence the performance of clustering-based speaker diarisation systems. Conventionally, only one embedding is extracted from each speech segment. However, because of the sliding window approach,…

Sound · Computer Science 2022-11-09 Hee-Soo Heo , Youngki Kwon , Bong-Jin Lee , You Jin Kim , Jee-weon Jung

The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale datasets are capable of capturing a diverse set of features, and…

Embeddings in machine learning are low-dimensional representations of complex input patterns, with the property that simple geometric operations like Euclidean distances and dot products can be used for classification and comparison tasks.…

Machine Learning · Statistics 2018-02-28 Niko Brummer , Anna Silnova , Lukas Burget , Themos Stafylakis

Unsupervised disentangled representation learning from the unlabelled audio data, and high fidelity audio generation have become two linchpins in the machine learning research fields. However, the representation learned from an unsupervised…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-20 Kazi Nazmul Haque , Rajib Rana , Björn W Schuller

Target sound extraction consists of extracting the sound of a target acoustic event (AE) class from a mixture of AE sounds. It can be realized using a neural network that extracts the target sound conditioned on a 1-hot vector that…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-15 Marc Delcroix , Jorge Bennasar Vázquez , Tsubasa Ochiai , Keisuke Kinoshita , Shoko Araki

Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-27 Saurabhchand Bhati , Samuel Thomas , Hilde Kuehne , Rogerio Feris , James Glass

We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of transferring those embeddings to other tasks within the speech…

Sound · Computer Science 2022-10-03 Heinrich Dinkel , Zhiyong Yan , Yongqing Wang , Junbo Zhang , Yujun Wang

Speaker embedding extractors (EEs), which map input audio to a speaker discriminant latent space, are of paramount importance in speaker diarisation. However, there are several challenges when adopting EEs for diarisation, from which we…

We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models,…

Sound · Computer Science 2025-06-13 Tobias Morocutti , Florian Schmid , Jonathan Greif , Francesco Foscarin , Gerhard Widmer

We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are…

Neural and Evolutionary Computing · Computer Science 2015-08-19 John R. Hershey , Zhuo Chen , Jonathan Le Roux , Shinji Watanabe

This study investigates the use of non-linear unsupervised dimensionality reduction techniques to compress a music dataset into a low-dimensional representation which can be used in turn for the synthesis of new sounds. We systematically…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-27 Fanny Roche , Thomas Hueber , Samuel Limier , Laurent Girin

The goal of text-queried target sound extraction (TSE) is to extract from a mixture a sound source specified with a natural-language caption. While it is preferable to have access to large-scale text-audio pairs to address a variety of text…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-23 Kohei Saijo , Janek Ebbers , François G. Germain , Sameer Khurana , Gordon Wichern , Jonathan Le Roux

This paper compares machine learning approaches with different input data formats for the classification of acoustic emission (AE) signals. AE signals are a promising monitoring technique in many structural health monitoring applications.…

Signal Processing · Electrical Eng. & Systems 2025-01-03 Uditha Muthumala , Yuxuan Zhang , Luciano Sebastian Martinez-Rau , Sebastian Bader

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically \textit{heterogeneous},…

In computational bioacoustics, deep learning models are composed of feature extractors and classifiers. The feature extractors generate vector representations of the input sound segments, called embeddings, which can be input to a…

Machine Learning · Computer Science 2025-04-10 Vincent S. Kather , Burooj Ghani , Dan Stowell

Most machine learning models for audio tasks are dealing with a handcrafted feature, the spectrogram. However, it is still unknown whether the spectrogram could be replaced with deep learning based features. In this paper, we answer this…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-20 Zhaoyang Bu , Hanhaodi Zhang , Xiaohu Zhu

Variational autoencoders (VAE) are a powerful and widely-used class of models to learn complex data distributions in an unsupervised fashion. One important limitation of VAEs is the prior assumption that latent sample representations are…

Machine Learning · Computer Science 2018-11-27 Francesco Paolo Casale , Adrian V Dalca , Luca Saglietti , Jennifer Listgarten , Nicolo Fusi

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-16 Xingwei Sun , Heinrich Dinkel , Yadong Niu , Linzhang Wang , Junbo Zhang , Jian Luan

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…

Sound · Computer Science 2020-10-28 Xavier Favory , Konstantinos Drossos , Tuomas Virtanen , Xavier Serra

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…

Computation and Language · Computer Science 2020-06-26 Yushi Hu , Shane Settle , Karen Livescu
‹ Prev 1 2 3 10 Next ›