相关论文: Unsupervised Sound Separation Using Mixture Invari…

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only on separating sources belonging to a restricted domain of…

We introduce UNMIXX, a novel framework for multiple singing voices separation (MSVS). While related to speech separation, MSVS faces unique challenges: data scarcity and the highly correlated nature of singing voices mixture. To address…

Source separation is the process of isolating individual sounds in an auditory mixture of multiple sounds [1], and has a variety of applications ranging from speech enhancement and lyric transcription [2] to digital audio production for…

Recent research has shown remarkable performance in leveraging multiple extraneous conditional and non-mutually exclusive semantic concepts for sound source separation, allowing the flexibility to extract a given target source based on…

Audio separation in real-world scenarios, where mixtures contain a variable number of sources, presents significant challenges due to limitations of existing models, such as over-separation, under-separation, and dependence on predefined…

RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by remixing the outputs of the teacher model. The student model…

We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are…

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…

Recent work achieved remarkable results in training neural machine translation (NMT) systems in a fully unsupervised way, with new and dedicated architectures that rely on monolingual corpora only. In this work, we propose to define…

Source separation is the task to separate an audio recording into individual sound sources. Source separation is fundamental for computational auditory scene analysis. Previous work on source separation has focused on separating particular…

The end-to-end speech synthesis model can directly take an utterance as reference audio, and generate speech from the text with prosody and speaker characteristics similar to the reference audio. However, an appropriate acoustic embedding…

Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and…

In the recent years, singing voice separation systems showed increased performance due to the use of supervised training. The design of training datasets is known as a crucial factor in the performance of such systems. We investigate on how…

Self-supervised audio-visual source separation leverages natural correlations between audio and vision modalities to separate mixed audio signals. In this work, we first systematically analyse the performance of existing multimodal fusion…

Self-supervised learning has been used to leverage unlabelled data, improving accuracy and generalisation of speech systems through the training of representation models. While many recent works have sought to produce effective…

While significant advances have been made with respect to the separation of overlapping speech signals, studies have been largely constrained to mixtures of clean, near anechoic speech, not representative of many real-world scenarios.…

To date, the bulk of research on single-channel speech separation has been conducted using clean, near-field, read speech, which is not representative of many modern applications. In this work, we develop a procedure for constructing…

Existing methods utilizing spatial information for sound source separation require prior knowledge of the direction of arrival (DOA) of the source or utilize estimated but imprecise localization results, which impairs the separation…

We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood criterion derived from a spatial mixture model of the…