Related papers: Metric Analysis for Spatial Semantic Segmentation …

Label noise is a common issue in real-world datasets that inevitably impacts the generalization of models. This study focuses on robust classification tasks where the label noise is instance-dependent. Estimating the transition matrix…

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…

Recent neural network strategies for source separation attempt to model audio signals by processing their waveforms directly. Mean squared error (MSE) that measures the Euclidean distance between waveforms of denoised speech and the…

We introduce a new framework for analyzing classification datasets based on the ratios of reconstruction errors between autoencoders trained on individual classes. This analysis framework enables efficient characterization of datasets on…

End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision. This could result in recognition errors due to…

Target audio source separation with natural language queries presents a promising paradigm for extracting arbitrary audio events through arbitrary text descriptions. Existing methods mainly face two challenges, the difficulty in jointly…

We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream…

Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over…

We propose an efficient method to estimate source power spectral densities (PSDs) in a multi-source reverberant environment using a spherical microphone array. The proposed method utilizes the spatial correlation between the spherical…

Sound can convey significant information for spatial reasoning in our daily lives. To endow deep networks with such ability, we address the challenge of dense indoor prediction with sound in both 2D and 3D via cross-modal knowledge…

We investigate a speech enhancement method based on the binaural coherence-to-diffuse power ratio (CDR), which preserves auditory spatial cues for maskers and a broadside target. Conventional CDR estimators typically rely on a mathematical…

Despite impressive accuracy, deep neural networks are often miscalibrated and tend to overly confident predictions. Recent techniques like temperature scaling (TS) and label smoothing (LS) show effectiveness in obtaining a well-calibrated…

Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilizing large amounts of unlabeled data with limited labeled samples. Existing methods often suffer from coupling, where over-reliance on initial…

Speech separation has been studied widely for single-channel close-talk microphone recordings over the past few years; developed solutions are mostly in frequency-domain. Recently, a raw audio waveform separation network (TasNet) is…

This report presents our systems submitted to the audio-only and audio-visual tracks of the DCASE2025 Task 3 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. SELD is a complex task that combines…

Deep domain adaptation methods can reduce the distribution discrepancy by learning domain-invariant embedddings. However, these methods only focus on aligning the whole data distributions, without considering the class-level relations among…

Speaker Verification (SV) systems involve mainly two individual stages: feature extraction and classification. In this paper, we explore these two modules with the aim of improving the performance of a speaker verification system under…

Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end…

Recently, multi-channel speech enhancement has drawn much interest due to the use of spatial information to distinguish target speech from interfering signal. To make full use of spatial information and neural network based masking…

We present CS-SHRED, a novel deep learning architecture that integrates Compressed Sensing (CS) into a Shallow Recurrent Decoder (SHRED) to reconstruct spatiotemporal dynamics from incomplete, compressed, or corrupted data. Our approach…