English
Related papers

Related papers: The Effect of Training Dataset Size on Discriminat…

200 papers

Large-scale pretraining datasets drive the success of large language models (LLMs). However, these web-scale corpora inevitably contain large amounts of noisy data due to unregulated web content or randomness inherent in data. Although LLM…

Machine Learning · Computer Science 2026-02-03 Qizhen Zhang , Ankush Garg , Jakob Foerster , Niladri Chatterji , Kshitiz Malik , Mike Lewis

In this paper, we address the generalization of deep neural network (DNN) based speech enhancement to unseen noise conditions for the case that training data is limited in size and diversity. To gain more insights, we analyze the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-18 Robert Rehr , Timo Gerkmann

In this paper, we present a causal speech signal improvement system that is designed to handle different types of distortions. The method is based on a generative diffusion model which has been shown to work well in scenarios with missing…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-16 Julius Richter , Simon Welker , Jean-Marie Lemercier , Bunlong Lay , Tal Peer , Timo Gerkmann

Diffusion models have emerged as the de facto choice for generating high-quality visual signals across various domains. However, training a single model to predict noise across various levels poses significant challenges, necessitating…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Tiankai Hang , Shuyang Gu , Xin Geng , Baining Guo

Diffusion models are becoming increasingly popular in synthetic data generation and image editing applications. However, these models can amplify existing biases and propagate them to downstream applications. Therefore, it is crucial to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Malsha V. Perera , Vishal M. Patel

Speech enhancement significantly improves the clarity and intelligibility of speech in noisy environments, improving communication and listening experiences. In this paper, we introduce a novel pretraining feature-guided diffusion model…

Sound · Computer Science 2024-06-13 Yiyuan Yang , Niki Trigoni , Andrew Markham

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…

Sound · Computer Science 2019-06-07 Laure Prétet , Romain Hennequin , Jimena Royo-Letelier , Andrea Vaglio

This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model…

Machine Learning · Computer Science 2019-04-03 Stefano Imoscopi , Volodya Grancharov , Sigurdur Sverrisson , Erlendur Karlsson , Harald Pobloth

Recently, deep neural network (DNN)-based speech enhancement (SE) systems have been used with great success. During training, such systems require clean speech data - ideally, in large quantity with a variety of acoustic conditions, many…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-27 Koichi Saito , Stefan Uhlich , Giorgio Fabbro , Yuki Mitsufuji

Dysarthric speech poses significant challenges for automatic speech recognition (ASR) systems due to its high variability and reduced intelligibility. In this work we explore the use of diffusion models for dysarthric speech enhancement,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-26 Dimme de Groot , Tanvina Patel , Devendra Kayande , Odette Scharenborg , Zhengjun Yue

Diffusion-based speech enhancement (SE) models need to incorporate correct prior knowledge as reliable conditions to generate accurate predictions. However, providing reliable conditions using noisy features is challenging. One solution is…

Sound · Computer Science 2025-10-08 Hao Shi , Xugang Lu , Kazuki Shimada , Tatsuya Kawahara

The ability to train generative models that produce realistic, safe and useful tabular data is essential for data privacy, imputation, oversampling, explainability or simulation. However, generating tabular data is not straightforward due…

Machine Learning · Computer Science 2025-09-18 G. Charbel N. Kindji , Lina Maria Rojas-Barahona , Elisa Fromont , Tanguy Urvoy

Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strategies to address this problem, there are few studies that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Emeson Santana , Gustavo Carneiro , Filipe R. Cordeiro

Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representative ones. Although the introduction of generative models has…

Machine Learning · Computer Science 2025-05-27 Mingzhuo Li , Guang Li , Jiafeng Mao , Takahiro Ogawa , Miki Haseyama

Diffusion-based generative models have recently gained attention in speech enhancement (SE), providing an alternative to conventional supervised methods. These models transform clean speech training samples into Gaussian noise centered at…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Jean-Eudes Ayilo , Mostafa Sadeghi , Romain Serizel

This study investigates the impact of integrating a dataset of disordered speech recordings ($\sim$1,000 hours) into the fine-tuning of a near state-of-the-art ASR baseline system. Contrary to what one might expect, despite the data being…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-22 Jimmy Tobin , Katrin Tomanek , Subhashini Venugopalan

Creating synthetic voices with found data is challenging, as real-world recordings often contain various types of audio degradation. One way to address this problem is to pre-enhance the speech with an enhancement model and then use the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-03 Yusheng Tian , Wei Liu , Tan Lee

In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ…

Machine Learning · Computer Science 2018-12-18 Sam McCandlish , Jared Kaplan , Dario Amodei , OpenAI Dota Team

Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this…

Computation and Language · Computer Science 2022-03-21 Houman Mehrafarin , Sara Rajaee , Mohammad Taher Pilehvar

The paper introduces Diff-Filter, a multichannel speech enhancement approach based on the diffusion probabilistic model, for improving speaker verification performance under noisy and reverberant conditions. It also presents a new two-step…

Sound · Computer Science 2023-07-06 Sandipana Dowerah , Ajinkya Kulkarni , Romain Serizel , Denis Jouvet