English
Related papers

Related papers: SpecAugment on Large Scale Datasets

200 papers

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

Sound · Computer Science 2026-05-01 Alexandre R. Ferreira , Cláudio E. C. Campelo

We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition. We push the limits of non-autoregressive state-of-the-art results for multiple datasets: LibriSpeech, Fisher+Switchboard and…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-14 Edwin G. Ng , Chung-Cheng Chiu , Yu Zhang , William Chan

The task of making speaker verification systems robust to adverse scenarios remain a challenging and an active area of research. We developed an unsupervised feature enhancement approach in log-filter bank domain with the end goal of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-18 Phani Sankar Nidadavolu , Saurabh Kataria , Jesús Villalba , Paola García-Perera , Najim Dehak

The performance of deep neural network-based speech enhancement systems typically increases with the training dataset size. However, studies that investigated the effect of training dataset size on speech enhancement performance did not…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Philippe Gonzalez , Zheng-Hua Tan , Jan Østergaard , Jesper Jensen , Tommy Sonne Alstrøm , Tobias May

Deep learning-based speech enhancement (SE) models have achieved impressive performance in the past decade. Numerous advanced architectures have been designed to deliver state-of-the-art performance; however, their scalability potential…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Wangyou Zhang , Kohei Saijo , Jee-weon Jung , Chenda Li , Shinji Watanabe , Yanmin Qian

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-28 Arun Narayanan , Rohit Prabhavalkar , Chung-Cheng Chiu , David Rybach , Tara N. Sainath , Trevor Strohman

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-02 Asad Ullah , Alessandro Ragano , Andrew Hines

Automatic speech recognition (ASR) should serve every speaker, not only the majority ``standard'' speakers of a language. In order to build inclusive ASR, mitigating the bias against speaker groups who speak in a ``non-standard'' or…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-27 Yuanyuan Zhang , Aaricia Herygers , Tanvina Patel , Zhengjun Yue , Odette Scharenborg

Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While…

Computation and Language · Computer Science 2019-10-01 Tong Niu , Mohit Bansal

There is a surge in interest in self-supervised learning approaches for end-to-end speech encoding in recent years as they have achieved great success. Especially, WavLM showed state-of-the-art performance on various speech processing…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-21 Hyungchan Song , Sanyuan Chen , Zhuo Chen , Yu Wu , Takuya Yoshioka , Min Tang , Jong Won Shin , Shujie Liu

Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…

Sound · Computer Science 2022-01-20 Mengzhe Geng , Xurong Xie , Shansong Liu , Jianwei Yu , Shoukang Hu , Xunying Liu , Helen Meng

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set…

Machine Learning · Statistics 2017-02-21 Terrance DeVries , Graham W. Taylor

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time…

Sound · Computer Science 2023-05-24 Eungbeom Kim , Jinhee Kim , Yoori Oh , Kyungsu Kim , Minju Park , Jaeheon Sim , Jinwoo Lee , Kyogu Lee

We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model. Key to our approach are a strong baseline acoustic and…

Computation and Language · Computer Science 2020-05-08 Jacob Kahn , Ann Lee , Awni Hannun

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-24 Zhepei Wang , Ritwik Giri , Devansh Shah , Jean-Marc Valin , Michael M. Goodwin , Paris Smaragdis

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…

Computation and Language · Computer Science 2018-06-14 Hao Tang , Wei-Ning Hsu , Francois Grondin , James Glass

End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or…

Computation and Language · Computer Science 2023-06-12 Tsz Kin Lam , Shigehiko Schamoni , Stefan Riezler

We study transfer learning in convolutional network architectures applied to the task of recognizing audio, such as environmental sound events and speech commands. Our key finding is that not only is it possible to transfer representations…

Sound · Computer Science 2017-10-24 Brian McMahan , Delip Rao

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Sound · Computer Science 2025-11-14 Inbal Rimon , Oren Gal , Haim Permuter

OpenAI's Whisper Automated Speech Recognition model excels in generalizing across diverse datasets and domains. However, this broad adaptability can lead to diminished performance in tasks requiring recognition of specific vocabularies.…

Artificial Intelligence · Computer Science 2025-08-12 Vishakha Lall , Yisi Liu