English
Related papers

Related papers: Loud-loss: A Perceptually Motivated Loss Function …

200 papers

Acoustic word embeddings (AWEs) are discriminative representations of speech segments, and learned embedding space reflects the phonetic similarity between words. With multi-view learning, where text labels are considered as supplementary…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-28 Myunghun Jung , Hoirin Kim

Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function. In this paper, we argue that the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-23 Wen Qian , Xue Yang , Silong Peng , Yue Guo , Junchi Yan

The S{\o}rensen--Dice Coefficient has recently seen rising popularity as a loss function (also known as Dice loss) due to its robustness in tasks where the number of negative samples significantly exceeds that of positive samples, such as…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-05 Karn N. Watcharasupat , Thi Ngoc Tho Nguyen , Ngoc Khanh Nguyen , Zhen Jian Lee , Douglas L. Jones , Woon Seng Gan

We derive the mapping between two of the most pervasive utility functions, the mean square error ($MSE$) and the concordance correlation coefficient (CCC, $\rho_c$). Despite its drawbacks, $MSE$ is one of the most popular performance…

Machine Learning · Computer Science 2020-07-03 Vedhas Pandit , Björn Schuller

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-10 Philippe Gonzalez , Zheng-Hua Tan , Jan Østergaard , Jesper Jensen , Tommy Sonne Alstrøm , Tobias May

Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i.e., denoising score matching loss. In this paper, we show that restoring data…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Jooyoung Choi , Jungbeom Lee , Chaehun Shin , Sungwon Kim , Hyunwoo Kim , Sungroh Yoon

In this paper, the coherence between speech and noise signals is used to obtain a Speech Enhancement (SE) gain function, in combination with a Super Gaussian Joint Maximum a Posteriori (SGJMAP) single microphone SE gain function. The…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-28 Nikhil Shankar , Gautam S Bhat , Chandan K A Reddy , Issa Panahi

Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-20 Sefik Emre Eskimez , Takuya Yoshioka , Huaming Wang , Xiaofei Wang , Zhuo Chen , Xuedong Huang

In neural networks, the loss function represents the core of the learning process that leads the optimizer to an approximation of the optimal convergence error. Convolutional neural networks (CNN) use the loss function as a supervisory…

Computer Vision and Pattern Recognition · Computer Science 2020-09-30 Riccardo La Grassa , Ignazio Gallo , Nicola Landro

Noise robustness is a key aspect of successful speech applications. Speech enhancement (SE) has been investigated to improve automatic speech recognition accuracy; however, its effectiveness for keyword spotting (KWS) is still…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-23 Avamarie Brueggeman , Takuya Higuchi , Masood Delfarah , Stephen Shum , Vineet Garg

Although supervised learning based on a deep neural network has recently achieved substantial improvement on speech enhancement, the existing schemes have either of two critical issues: spectrum or metric mismatches. The spectrum mismatch…

Sound · Computer Science 2020-05-12 Jaeyoung Kim , Mostafa El-Khamy , Jungwon Lee

In real-world scenarios, speech signals are inevitably corrupted by various types of interference, making speech enhancement (SE) a critical task for robust speech processing. However, most existing SE methods only handle a limited range of…

Sound · Computer Science 2025-12-12 Fei Liu , Yang Ai , Ye-Xin Lu , Rui-Chen Zheng , Hui-Peng Du , Zhen-Hua Ling

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

Sound · Computer Science 2018-05-03 Han Zhao , Shuayb Zarar , Ivan Tashev , Chin-Hui Lee

To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity. We propose such a loss function based on Watson's perceptual model, which computes a…

Machine Learning · Computer Science 2021-01-07 Steffen Czolbe , Oswin Krause , Ingemar Cox , Christian Igel

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-28 Ziqian Wang , Zikai Liu , Xinfa Zhu , Yike Zhu , Mingshuai Liu , Jun Chen , Longshuai Xiao , Chao Weng , Lei Xie

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-12 Muhammad Shakeel , Yui Sudo , Yifan Peng , Shinji Watanabe

We propose the Signal Dice Similarity Coefficient (SDSC), a structure-aware metric function for time series self-supervised representation learning. Most Self-Supervised Learning (SSL) methods for signals commonly adopt distance-based…

Machine Learning · Computer Science 2026-01-30 Jeyoung Lee , Hochul Kang

Speech emotion recognition (SER) plays a critical role in building emotion-aware speech systems, but its performance degrades significantly under noisy conditions. Although speech enhancement (SE) can improve robustness, it often introduces…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-29 Jing-Tong Tzeng , Carlos Busso , Chi-Chun Lee

The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception…

Sound · Computer Science 2021-06-07 Szu-Wei Fu , Cheng Yu , Tsun-An Hsieh , Peter Plantinga , Mirco Ravanelli , Xugang Lu , Yu Tsao

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