English
Related papers

Related papers: MixCycle: Unsupervised Speech Separation via Cycli…

200 papers

Permutation-invariant training (PIT) is a dominant approach for addressing the permutation ambiguity problem in talker-independent speaker separation. Leveraging spatial information afforded by microphone arrays, we propose a new training…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-11 Hassan Taherian , Ke Tan , DeLiang Wang

In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target.…

Machine Learning · Computer Science 2024-02-26 Maurice Kraus , Felix Divo , David Steinmann , Devendra Singh Dhami , Kristian Kersting

This paper presents a joint source separation algorithm that simultaneously reduces acoustic echo, reverberation and interfering sources. Target speeches are separated from the mixture by maximizing independence with respect to the other…

Sound · Computer Science 2021-04-12 Yueyue Na , Ziteng Wang , Zhang Liu , Biao Tian , Qiang Fu

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Computer Vision and Pattern Recognition · Computer Science 2022-02-18 Zhiqiang Shen , Zechun Liu , Zhuang Liu , Marios Savvides , Trevor Darrell , Eric Xing

In this paper, we study whether music source separation can be used as a pre-training strategy for music representation learning, targeted at music classification tasks. To this end, we first pre-train U-Net networks under various music…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-24 Christos Garoufis , Athanasia Zlatintsi , Petros Maragos

Consider a time series of measurements of the state of an evolving system, x(t), where x has two or more components. This paper shows how to perform nonlinear blind source separation; i.e., how to determine if these signals are equal to…

Methodology · Statistics 2017-03-07 David N. Levin

We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…

Sound · Computer Science 2022-07-18 Zhongweiyang Xu , Romit Roy Choudhury

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Hila Chefer , Patrick Esser , Dominik Lorenz , Dustin Podell , Vikash Raja , Vinh Tong , Antonio Torralba , Robin Rombach

The separation of single-channel underwater acoustic signals is a challenging problem with practical significance. Few existing studies focus on the source separation problem with unknown numbers of signals, and how to evaluate the…

Sound · Computer Science 2024-05-29 Qinggang Sun , Kejun Wang

Speech separation has been well developed, with the very successful permutation invariant training (PIT) approach, although the frequent label assignment switching happening during PIT training remains to be a problem when better…

Sound · Computer Science 2021-08-24 Sung-Feng Huang , Shun-Po Chuang , Da-Rong Liu , Yi-Chen Chen , Gene-Ping Yang , Hung-yi Lee

Binaural speech separation in real-world scenarios often involves moving speakers. Most current speech separation methods use utterance-level permutation invariant training (u-PIT) for training. In inference time, however, the order of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-15 Cong Han , Nima Mesgarani

We propose a training scheme to train neural network-based source separation algorithms from scratch when parallel clean data is unavailable. In particular, we demonstrate that an unsupervised spatial clustering algorithm is sufficient to…

Machine Learning · Computer Science 2019-04-03 Lukas Drude , Daniel Hasenklever , Reinhold Haeb-Umbach

Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between interferent sources. Current state-of-the-art solutions can separate well the different…

Signal Processing · Electrical Eng. & Systems 2021-02-09 Nicolas Furnon , Romain Serizel , Irina Illina , Slim Essid

Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present…

While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge. To solve this problem, we present…

Computation and Language · Computer Science 2021-10-22 Ting Jiang , Shaohan Huang , Zihan Zhang , Deqing Wang , Fuzhen Zhuang , Furu Wei , Haizhen Huang , Liangjie Zhang , Qi Zhang

Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-24 Dongwei Jiang , Wubo Li , Ruixiong Zhang , Miao Cao , Ne Luo , Yang Han , Wei Zou , Xiangang Li

Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its…

Sound · Computer Science 2023-11-23 Marco Pasini , Stefan Lattner , George Fazekas

Speech separation has been studied in time domain because of lower latency and higher performance compared to time-frequency domain. The masking-based method has been mostly used in time domain, and the other common method (mapping-based)…

Sound · Computer Science 2022-03-22 Chenyang Gao , Yue Gu , Ivan Marsic

We consider the problem of separating a particular sound source from a single-channel mixture, based on only a short sample of the target source. Using SoundFilter, a wave-to-wave neural network architecture, we can train a model without…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-05 Beat Gfeller , Dominik Roblek , Marco Tagliasacchi

Self-supervised learning leverages unlabeled data effectively, improving label efficiency and generalization to domains without labeled data. While recent work has studied generalization to more acoustic/linguistic domains, languages, and…

Computation and Language · Computer Science 2023-03-21 Maryam Fazel-Zarandi , Wei-Ning Hsu
‹ Prev 1 4 5 6 7 8 10 Next ›