English
Related papers

Related papers: Bitwise Source Separation on Hashed Spectra: An Ef…

200 papers

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-28 Jinwei Dong , Xinsheng Wang , Qirong Mao

We propose a batchwise monotone algorithm for dictionary learning. Unlike the state-of-the-art dictionary learning algorithms which impose sparsity constraints on a sample-by-sample basis, we instead treat the samples as a batch, and impose…

Machine Learning · Computer Science 2015-02-03 Huan Wang , John Wright , Daniel Spielman

We propose a novel joint decoding technique for distributed source-channel (DSC) coded systems for transmission of correlated binary Markov sources over additive white Gaussian noise (AWGN) channels. In the proposed scheme, relatively…

Information Theory · Computer Science 2013-08-02 Reza Asvadi , Tad Matsumoto , Markku Juntti

Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-08 Pyry Pyykkönen , Styliannos I. Mimilakis , Konstantinos Drossos , Tuomas Virtanen

Extractive Text Summarization is the process of selecting the most representative parts of a larger text without losing any key information. Recent attempts at extractive text summarization in Bengali, either relied on statistical…

Computation and Language · Computer Science 2024-11-28 Fahim Morshed , Md. Abdur Rahman , Sumon Ahmed

Discrete diffusion language models have shown strong potential for text generation, yet standard supervised fine-tuning (SFT) misaligns with their semi-autoregressive inference: training randomly masks tokens across the entire response,…

Computation and Language · Computer Science 2025-10-24 Bowen Sun , Yujun Cai , Ming-Hsuan Yang , Yiwei Wang

We present a novel blind source separation (BSS) method, called information geometric blind source separation (IGBSS). Our formulation is based on the log-linear model equipped with a hierarchically structured sample space, which has…

Machine Learning · Statistics 2021-06-14 Simon Luo , Lamiae Azizi , Mahito Sugiyama

Time-domain training criteria have proven to be very effective for the separation of single-channel non-reverberant speech mixtures. Likewise, mask-based beamforming has shown impressive performance in multi-channel reverberant speech…

Recently, Constant Separating Vector (CSV) mixing model has been proposed for the Blind Source Extraction (BSE) of moving sources. In this paper, we experimentally verify the applicability of CSV in the blind extraction of a moving speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-08 Jakub Janský , Zbyněk Koldovský , Jiří Málek , Tomáš Kounovský , Jaroslav Čmejla

In this work, a new indexing technique of data streams called BSTree is proposed. This technique uses the method of data discretization, SAX [4], to reduce online the dimensionality of data streams. It draws on Btree to build the index and…

Databases · Computer Science 2014-06-24 Abdelwaheb Ferchichi , Mohamed Salah Gouider

The mismatch between the numerical and actual nonlinear models is a challenge to nonlinear acoustic echo cancellation (NAEC) when the nonlinear adaptive filter is utilized. To alleviate this problem, we combine a basis-generic expansion of…

Signal Processing · Electrical Eng. & Systems 2021-04-07 Guoliang Cheng , Lele Liao , Hongsheng Chen , Jing Lu

We propose a new method to enforce priors on the solution of the nonnegative matrix factorization (NMF). The proposed algorithm can be used for denoising or single-channel source separation (SCSS) applications. The NMF solution is guided to…

Machine Learning · Computer Science 2013-03-01 Emad M. Grais , Hakan Erdogan

We propose theoretical and empirical improvements for two-stage hashing methods. We first provide a theoretical analysis on the quality of the binary codes and show that, under mild assumptions, a residual learning scheme can construct…

Machine Learning · Computer Science 2018-08-07 Fatih Cakir , Kun He , Stan Sclaroff

We establish that it is possible to extract accurate blockwise and bitwise soft output from Guessing Codeword Decoding with minimal additional computational complexity by considering it as a variant of Guessing Random Additive Noise…

Information Theory · Computer Science 2025-12-18 Ken R. Duffy , Peihong Yuan , Joseph Griffin , Muriel Medard

Unsupervised hashing is important for indexing huge image or video collections without having expensive annotations available. Hashing aims to learn short binary codes for compact storage and efficient semantic retrieval. We propose an…

Computer Vision and Pattern Recognition · Computer Science 2020-12-24 Yunqiang Li , Jan van Gemert

Blind source separation (BSS) is a key technique in array processing and data analysis, aiming to recover unknown sources from observed mixtures without knowledge of the mixing matrix. Classical independent component analysis (ICA) methods…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Zhongxuan Li

Recently Lin et al. proposed a method of using the underdetermined BSS (blind source separation) problem to realize image and speech encryption. In this paper, we give a cryptanalysis of this BSS-based encryption and point out that it is…

Cryptography and Security · Computer Science 2010-06-23 Shujun Li , Chengqing Li , Kwok-Tung Lo , Guanrong Chen

Speckle noise is a fundamental challenge in coherent imaging systems, significantly degrading image quality. Over the past decades, numerous despeckling algorithms have been developed for applications such as Synthetic Aperture Radar (SAR)…

Information Theory · Computer Science 2025-01-31 Ali Zafari , Shirin Jalali

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…

Neural and Evolutionary Computing · Computer Science 2015-08-19 John R. Hershey , Zhuo Chen , Jonathan Le Roux , Shinji Watanabe

We consider the problem of joint source and channel coding of structured data such as natural language over a noisy channel. The typical approach to this problem in both theory and practice involves performing source coding to first…

Information Theory · Computer Science 2018-02-21 Nariman Farsad , Milind Rao , Andrea Goldsmith
‹ Prev 1 8 9 10 Next ›