Related papers: Improving Reverberant Speech Separation with Multi…

We present an efficient and realistic geometric acoustic simulation approach for generating and augmenting training data in speech-related machine learning tasks. Our physically-based acoustic simulation method is capable of modeling…

Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an…

This paper proposes reverberation as supervision (RAS), a novel unsupervised loss function for single-channel reverberant speech separation. Prior methods for unsupervised separation required the synthesis of mixtures of mixtures or assumed…

We present a novel approach to improve the performance of learning-based speech dereverberation using accurate synthetic datasets. Our approach is designed to recover the reverb-free signal from a reverberant speech signal. We show that…

In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized for such situations. To address this issue, we propose a…

Sound propagation is the process by which sound energy travels through a medium, such as air, to the surrounding environment as sound waves. The room impulse response (RIR) describes this process and is influenced by the positions of the…

Modern neural-network-based speech processing systems are typically required to be robust against reverberation, and the training of such systems thus needs a large amount of reverberant data. During the training of the systems, on-the-fly…

Ensuring performance robustness for a variety of situations that can occur in real-world environments is one of the challenging tasks in sound event classification. One of the unpredictable and detrimental factors in performance, especially…

Achieving robust speech separation for overlapping speakers in various acoustic environments with noise and reverberation remains an open challenge. Although existing datasets are available to train separators for specific scenarios, they…

Background noise, interfering speech and room reverberation frequently distort target speech in real listening environments. In this study, we address joint speech separation and dereverberation, which aims to separate target speech from…

Room impulse response (RIR) generation remains a critical challenge for creating immersive virtual acoustic environments. Current methods suffer from two fundamental limitations: the scarcity of full-band RIR datasets and the inability of…

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…

State-of-the-art deep-learning-based voice activity detectors (VADs) are often trained with anechoic data. However, real acoustic environments are generally reverberant, which causes the performance to significantly deteriorate. To mitigate…

Room Impulse Responses (RIRs) enable realistic acoustic simulation, with applications ranging from multimedia production to speech data augmentation. However, acquiring high-quality real-world RIRs is labor-intensive, and data scarcity…

We propose RemixIT, a simple and novel self-supervised training method for speech enhancement. The proposed method is based on a continuously self-training scheme that overcomes limitations from previous studies including assumptions for…

Speech separation, the task of isolating multiple speech sources from a mixed audio signal, remains challenging in noisy environments. In this paper, we propose a generative correction method to enhance the output of a discriminative…

Recent audio-visual generative models have made substantial progress in generating images from audio. However, existing approaches focus on generating images from single-class audio and fail to generate images from mixed audio. To address…

Room impulse responses (RIRs) are fundamental to audio data augmentation, acoustic signal processing, and immersive audio rendering. While geometric simulators such as the image source method (ISM) can efficiently generate early…

Neural speech separation has made remarkable progress and its integration with automatic speech recognition (ASR) is an important direction towards realizing multi-speaker ASR. This work provides an insightful investigation of speech…

We present a Generative Adversarial Network (GAN) based room impulse response generator (IR-GAN) for generating realistic synthetic room impulse responses (RIRs). IR-GAN extracts acoustic parameters from captured real-world RIRs and uses…