Related papers: AmbiDrop: Array-Agnostic Speech Enhancement Using …

Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of…

In many applications of multi-microphone multi-device processing, the synchronization among different input channels can be affected by the lack of a common clock and isolated drops of samples. In this work, we address the issue of sample…

Spherical microphone arrays are convenient tools for capturing the spatial characteristics of a sound field. However, achieving superior spatial resolution requires arrays with numerous capsules, consequently leading to expensive devices.…

Automatic speech emotion recognition provides computers with critical context to enable user understanding. While methods trained and tested within the same dataset have been shown successful, they often fail when applied to unseen…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Many recent works on deep speaker embeddings train their feature extraction networks on large classification tasks, distinguishing between all speakers in a training set. Empirically, this has been shown to produce speaker-discriminative…

Neural networks (NNs) have been widely applied in speech processing tasks, and, in particular, those employing microphone arrays. Nevertheless, most existing NN architectures can only deal with fixed and position-specific microphone arrays.…

Humans can robustly recognize and localize objects by using visual and/or auditory cues. While machines are able to do the same with visual data already, less work has been done with sounds. This work develops an approach for scene…

This paper proposes an adaptive margin contrastive learning method for 3D semantic segmentation on point clouds. Most existing methods use equally penalized objectives, which ignore the per-point ambiguities and less discriminated features…

Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states.…

Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable enhancement…

Acoustic Scene Classification (ASC) faces challenges in generalizing across recording devices, particularly when labeled data is limited. The DCASE 2024 Challenge Task 1 highlights this issue by requiring models to learn from small labeled…

The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising critical security concerns. Existing methods for detecting…

Automated respiratory sound classification faces practical challenges from background noise and insufficient denoising in existing systems. We propose Adaptive Differential Denoising network, that integrates noise suppression and…

Monaural Speech enhancement on drones is challenging because the ego-noise from the rotating motors and propellers leads to extremely low signal-to-noise ratios at onboard microphones. Although recent masking-based deep neural network…

We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific…

Transformer-based architectures achieve state-of-the-art performance across a wide range of tasks in natural language processing, computer vision, and speech processing. However, their immense capacity often leads to overfitting, especially…

Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by…

Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM) approach that…

The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious information such as…