相关论文: Smule Renaissance Small: Efficient General-Purpose…

Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature fusion approach has been proposed to effectively capture speaker…

Event cameras sense intensity changes and have many advantages over conventional cameras. To take advantage of event cameras, some methods have been proposed to reconstruct intensity images from event streams. However, the outputs are still…

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With RS, achieving high accuracy at small radii requires a small noise variance, while achieving high…

Recent advancements in automatic speech recognition (ASR) have achieved notable progress, whereas robustness in noisy environments remains challenging. While speech enhancement (SE) front-ends are widely used to mitigate noise as a…

The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real…

Weakly-Supervised Semantic Segmentation (WSSS) segments objects without a heavy burden of dense annotation. While as a price, generated pseudo-masks exist obvious noisy pixels, which result in sub-optimal segmentation models trained over…

Although state-of-the-art Speech Foundational Models can produce high-quality text pseudo-labels, applying Semi-Supervised Learning (SSL) for in-the-wild real-world data remains challenging due to its richer and more complex acoustics…

Robust sound source localization for environments with noise and reverberation are increasingly exploiting deep neural networks fed with various acoustic features. Yet, state-of-the-art research mainly focuses on optimizing algorithmic…

The performance of most emotion recognition systems degrades in real-life situations ('in the wild' scenarios) where the audio is contaminated by reverberation. Our study explores new methods to alleviate the performance degradation of SER…

Recently, diffusion models (DMs) have been increasingly used in audio processing tasks, including speech super-resolution (SR), which aims to restore high-frequency content given low-resolution speech utterances. This is commonly achieved…

Automatic Speech Recognition (ASR) models demonstrate outstanding performance on high-resource languages but face significant challenges when applied to low-resource languages due to limited training data and insufficient cross-lingual…

It is estimated that around 70 million people worldwide are affected by a speech disorder called stuttering. With recent advances in Automatic Speech Recognition (ASR), voice assistants are increasingly useful in our everyday lives. Many…

Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions. However, severe performance degradation is still observed in the…

Background noise and room reverberation are regarded as two major factors to degrade the subjective speech quality. In this paper, we propose an integrated framework to address simultaneous denoising and dereverberation under complicated…

We study device-addressed speech detection under pre-ASR edge deployment constraints, where systems must decide whether to forward audio before transcription under strict latency and compute limits. We show that, in multi-speaker…

In this paper, we present an efficient neural network for end-to-end general purpose audio source separation. Specifically, the backbone structure of this convolutional network is the SUccessive DOwnsampling and Resampling of…

Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-based tasks. To mitigate this problem, we propose a powerful…

Phase selection design for reconfigurable intelligent surfaces (RISs) is a significant research challenge, as a closed-form optimal solution for a multi-user (MU) system is believed to be intractable. While existing methods achieve strong…

Referring expression segmentation (RES), a task that involves localizing specific instance-level objects based on free-form linguistic descriptions, has emerged as a crucial frontier in human-AI interaction. It demands an intricate…