Related papers: Remastering Divide and Remaster: A Cinematic Audio…

Source separation is a fundamental task in speech, music, and audio processing, and it also provides cleaner and larger data for training generative models. However, improving separation performance in practice often depends on increasingly…

Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely…

It becomes urgent to design effective anti-spoofing algorithms for vulnerable automatic speaker verification systems due to the advancement of high-quality playback devices. Current studies mainly treat anti-spoofing as a binary…

Code-switching, the alternation between two or more languages within communication, poses great challenges for Automatic Speech Recognition (ASR) systems. Existing models and datasets are limited in their ability to effectively handle these…

Separation of multiple singing voices into each voice is a rarely studied area in music source separation research. The absence of a benchmark dataset has hindered its progress. In this paper, we present an evaluation dataset and provide…

Open-vocabulary 3D scene understanding is crucial for applications requiring natural language-driven spatial interpretation, such as robotics and augmented reality. While 3D Gaussian Splatting (3DGS) offers a powerful representation for…

In this paper, we present a novel multi-channel speech extraction system to simultaneously extract multiple clean individual sources from a mixture in noisy and reverberant environments. The proposed method is built on an improved…

Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in…

We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation using image diffusion, its core idea of distilling a…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

We introduce a new dataset of conversational speech representing English from India, Nigeria, and the United States. The Multi-Dialect Dataset of Dialogues (MD3) strikes a new balance between open-ended conversational speech and…

Identification and extraction of singing voice from within musical mixtures is a key challenge in source separation and machine audition. Recently, deep neural networks (DNN) have been used to estimate 'ideal' binary masks for carefully…

Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short…

We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models relying on language backbones have achieved remarkable…

This report describes our submissions to Task2 and Task3 of the DCASE 2016 challenge. The systems aim at dealing with the detection of overlapping audio events in continuous streams, where the detectors are based on random decision forests.…

Modern smart glasses leverage advanced audio sensing and machine learning technologies to offer real-time transcribing and captioning services, considerably enriching human experiences in daily communications. However, such systems…

Music source separation demixes a piece of music into its individual sound sources (vocals, percussion, melodic instruments, etc.), a task with no simple mathematical solution. It requires deep learning methods involving training on large…

We present a prompt-engineering-based text-augmentation approach applied to a language-queried audio source separation (LASS) task. To enhance the performance of LASS, the proposed approach utilizes large language models (LLMs) to generate…

Emulating the human ability to solve the cocktail party problem, i.e., focus on a source of interest in a complex acoustic scene, is a long standing goal of audio source separation research. Much of this research investigates separating…

Code-switching (CS) is the alternating use of two or more languages within a conversation or utterance, often influenced by social context and speaker identity. This linguistic phenomenon poses challenges for Automatic Speech Recognition…