English
Related papers

Related papers: SpecAugment on Large Scale Datasets

200 papers

Data augmentation is an essential technique in natural language processing (NLP) for enriching training datasets by generating diverse samples. This process is crucial for improving the robustness and generalization capabilities of NLP…

Computation and Language · Computer Science 2025-10-16 Zaitian Wang , Jinghan Zhang , Xinhao Zhang , Kunpeng Liu , Pengfei Wang , Yuanchun Zhou

Adapting pre-trained text Large Language Models (LLMs) into Speech Language Models (Speech LMs) via continual pretraining on speech data is promising, but often degrades the original text capabilities. We propose Multimodal Depth Upscaling,…

Computation and Language · Computer Science 2026-04-02 Kazuki Yano , Jun Suzuki , Shinji Watanabe

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-31 Gil Keren , Jing Han , Björn Schuller

We propose an on-the-fly data augmentation method for automatic speech recognition (ASR) that uses alignment information to generate effective training samples. Our method, called Aligned Data Augmentation (ADA) for ASR, replaces…

Computation and Language · Computer Science 2023-06-13 Tsz Kin Lam , Mayumi Ohta , Shigehiko Schamoni , Stefan Riezler

We examine the effect of data augmentation for training of language models for speech recognition. We compare augmentation based on global error statistics with one based on per-word unigram statistics of ASR errors and observe that it is…

Computation and Language · Computer Science 2020-11-13 Karel Beneš , Lukáš Burget

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Is pushing numbers on a single benchmark valuable in automatic speech recognition? Research results in acoustic modeling are typically evaluated based on performance on a single dataset. While the research community has coalesced around…

In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The idea here is to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Steffen Illium , Robert Müller , Andreas Sedlmeier , Claudia Linnhoff-Popien

Large Language Models (LLMs) have been applied in the speech domain, often incurring a performance drop due to misaligned between speech and language representations. To bridge this gap, we propose a joint speech and language model (SLM)…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-14 Mingqiu Wang , Izhak Shafran , Hagen Soltau , Wei Han , Yuan Cao , Dian Yu , Laurent El Shafey

Data augmentation is a technique to generate new training data based on existing data. We evaluate the simple and cost-effective method of concatenating the original data examples to build new training instances. Continued training with…

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

Self-supervised learning models have revolutionized the field of speech processing. However, the process of fine-tuning these models on downstream tasks requires substantial computational resources, particularly when dealing with multiple…

Computation and Language · Computer Science 2024-06-24 Varsha Suresh , Salah Aït-Mokhtar , Caroline Brun , Ioan Calapodescu

Recently, phase processing is attracting increasinginterest in speech enhancement community. Some researchersintegrate phase estimations module into speech enhancementmodels by using complex-valued short-time Fourier transform(STFT)…

Sound · Computer Science 2019-01-03 Xingjian Du , Mengyao Zhu , Xuan Shi , Xinpeng Zhang , Wen Zhang , Jingdong Chen

The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…

Sound · Computer Science 2022-07-25 Tianqu Kang , Anh-Dung Dinh , Binghong Wang , Tianyuan Du , Yijia Chen , Kevin Chau

Fake speech detection systems have become a necessity to combat against speech deepfakes. Current systems exhibit poor generalizability on out-of-domain speech samples due to lack to diverse training data. In this paper, we attempt to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-27 Rishith Sadashiv T N , Abhishek Bedge , Saisha Suresh Bore , Jagabandhu Mishra , Mrinmoy Bhattacharjee , S R Mahadeva Prasanna

Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…

Sound · Computer Science 2022-04-29 Dan Oneata , Horia Cucu

Speech-to-text (S2T) generation systems frequently face challenges in low-resource scenarios, primarily due to the lack of extensive labeled datasets. One emerging solution is constructing virtual training samples by interpolating inputs…

Computation and Language · Computer Science 2024-06-25 Chen Xu , Jie Wang , Xiaoqian Liu , Qianqian Dong , Chunliang Zhang , Tong Xiao , Jingbo Zhu , Dapeng Man , Wu Yang

Data augmentation is commonly used for generating additional data from the available training data to achieve a robust estimation of the parameters of complex models like the one for speaker verification (SV), especially for under-resourced…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-29 Achintya Kumar Sarkar , Himangshu Sarma , Priyanka Dwivedi , Zheng-Hua Tan

This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic…

Sound · Computer Science 2020-01-14 Jing-Xuan Zhang , Zhen-Hua Ling , Yuan Jiang , Li-Juan Liu , Chen Liang , Li-Rong Dai

We introduce ImportantAug, a technique to augment training data for speech classification and recognition models by adding noise to unimportant regions of the speech and not to important regions. Importance is predicted for each utterance…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-22 Viet Anh Trinh , Hassan Salami Kavaki , Michael I Mandel

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…

Computation and Language · Computer Science 2018-11-05 Jason Li , Ravi Gadde , Boris Ginsburg , Vitaly Lavrukhin