English
Related papers

Related papers: Performance Based Cost Functions for End-to-End Sp…

200 papers

Recently, deep neural network (DNN) has made a breakthrough in monaural source enhancement. Through a training step by using a large amount of data, DNN estimates a mapping between mixed signals and clean signals. At this time, we use an…

Sound · Computer Science 2018-06-18 Hiroaki Nakajima , Yu Takahashi , Kazunobu Kondo , Yuji Hisaminato

A promising approach for multi-microphone speech separation involves two deep neural networks (DNN), where the predicted target speech from the first DNN is used to compute signal statistics for time-invariant minimum variance…

Sound · Computer Science 2021-10-04 Zhong-Qiu Wang , Gordon Wichern , Jonathan Le Roux

Deep neural network (DNN) based end-to-end optimization in the complex time-frequency (T-F) domain or time domain has shown considerable potential in monaural speech separation. Many recent studies optimize loss functions defined solely in…

Sound · Computer Science 2022-01-05 Zhong-Qiu Wang , Gordon Wichern , Jonathan Le Roux

In this article, a study of the mean-square error (MSE) performance of linear echo-state neural networks is performed, both for training and testing tasks. Considering the realistic setting of noise present at the network nodes, we derive…

Machine Learning · Computer Science 2016-03-28 Romain Couillet , Gilles Wainrib , Harry Sevi , Hafiz Tiomoko Ali

Blind speech separation (BSS) aims to recover multiple speech sources from multi-channel, multi-speaker mixtures under unknown array geometry and room impulse responses. In unsupervised setup where clean target speech is not available for…

Sound · Computer Science 2025-10-13 Shulin He , Zhong-Qiu Wang

We derive a simple general parametric representation of the rate-distortion function of a memoryless source, where both the rate and the distortion are given by integrals whose integrands include the minimum mean square error (MMSE) of the…

Information Theory · Computer Science 2010-04-30 Neri Merhav

Source separation is a crucial pre-processing step for various speech processing tasks, such as automatic speech recognition (ASR). Traditionally, the evaluation metrics for speech separation rely on the matched reference audios and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-28 Ari Frummer , Helin Wang , Tianyu Cao , Adi Arbel , Yuval Sieradzki , Oren Gal , Jesús Villalba , Thomas Thebaud , Najim Dehak

In this work we explore possibilities for coding and decoding tailor-made for mean squared error evaluation of error in contexts such as image transmission. To do so, we introduce a loss function that expresses the overall performance of a…

Information Theory · Computer Science 2014-11-06 Marcelo Firer , Luciano Panek , Jerry Anderson Pinheiro

Utilizing a human-perception-related objective function to train a speech enhancement model has become a popular topic recently. The main reason is that the conventional mean squared error (MSE) loss cannot represent auditory perception…

Sound · Computer Science 2020-02-19 Szu-Wei Fu , Chien-Feng Liao , Yu Tsao

In recent years, speaker verification has primarily performed using deep neural networks that are trained to output embeddings from input features such as spectrograms or Mel-filterbank energies. Studies that design various loss functions,…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-18 Hee-Soo Heo , Jee-weon Jung , IL-Ho Yang , Sung-Hyun Yoon , Hye-jin Shim , Ha-Jin Yu

We consider the problem of signal estimation (denoising) from a statistical-mechanical perspective, in continuation to a recent work on the analysis of mean-square error (MSE) estimation using a direct relationship between optimum…

Information Theory · Computer Science 2013-06-04 Wasim Huleihel , Neri Merhav

Consider the minimum mean-square error (MMSE) of estimating an arbitrary random variable from its observation contaminated by Gaussian noise. The MMSE can be regarded as a function of the signal-to-noise ratio (SNR) as well as a functional…

Information Theory · Computer Science 2010-04-21 Dongning Guo , Yihong Wu , Shlomo Shamai , Sergio Verdu

In speech enhancement and source separation, signal-to-noise ratio is a ubiquitous objective measure of denoising/separation quality. A decade ago, the BSS_eval toolkit was developed to give researchers worldwide a way to evaluate the…

Sound · Computer Science 2018-11-07 Jonathan Le Roux , Scott Wisdom , Hakan Erdogan , John R. Hershey

This paper proposes a new paradigm for handling far-field multi-speaker data in an end-to-end neural network manner, called directional automatic speech recognition (D-ASR), which explicitly models source speaker locations. In D-ASR, the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-03 Aswin Shanmugam Subramanian , Chao Weng , Shinji Watanabe , Meng Yu , Yong Xu , Shi-Xiong Zhang , Dong Yu

In the field of audio generation, signal-to-noise ratio (SNR) has long served as an objective metric for evaluating audio quality. Nevertheless, recent studies have shown that SNR and its variants are not always highly correlated with human…

Sound · Computer Science 2026-01-21 Lingling Dai , Andong Li , Cheng Chi , Yifan Liang , Xiaodong Li , Chengshi Zheng

Separating vocal elements from musical tracks is a longstanding challenge in audio signal processing. This study tackles the distinct separation of vocal components from musical spectrograms. We employ the Short Time Fourier Transform…

Sound · Computer Science 2024-05-31 Adam Sorrenti

Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-23 Minhua Wu , Kenichi Kumatani , Shiva Sundaram , Nikko Strom , Bjorn Hoffmeister

An entropy-regularized mean square error (MSE-X) cost function is proposed for nonlinear equalization of short-reach optical channels. For a coherent optical transmission experiment, MSE-X achieves the same bit error rate as the standard…

Information Theory · Computer Science 2022-06-03 Francesca Diedolo , Georg Böcherer , Maximilian Schädler , Stefano Calabró

Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions. However, severe performance degradation is still observed in the…

Sound separation (SS) and target sound extraction (TSE) are fundamental techniques for addressing complex acoustic scenarios. While existing SS methods struggle with determining the unknown number of sound sources, TSE approaches require…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-25 Hongyu Wang , Chenda Li , Xin Zhou , Shuai Wang , Yanmin Qian