SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Open accessThe DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Abstract
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5'00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“SpecAugment is a spectrum augmentation method, which is only suitable for the audio deepfake model based on front-end feature extraction, and it is not easy to operate on the audio waveform.”
From Voice Deepfake Detection Using the Self-Supervised Pre-Training Model HuBERT (2023) · cites this paper as [19]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In addition to balanced sampling, we also apply SpecAugment [23] and random time shift to alleviate the class-imbalance issue.”
From Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition (2022) · cites this paper as [23]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“Deep Learning has been applied successfully to Automatic Speech Recognition (ASR) [1], where the main focus of research has been designing better network architectures, for example, DNNs [2], CNNs [3], RNNs [4] and end-to-end models [5, 6, 7].”
Method“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Kaldi Speech Recognition Toolkit
Povey, D. (2024) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.57702/jb3fvbn9 · Cited by 4,609
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011 · cited 1×
“Deep Learning has been applied successfully to Automatic Speech Recognition (ASR) [1], where the main focus of research has been designing better network architectures, for example, DNNs [2], CNNs [3], RNNs [4] and end-to-end models [5, 6, 7].”
MethodImproved regularization of convolutional neural networks with cutout
DeVries, T., & Taylor, G. W. (2017) · arXiv · doi:10.48550/arxiv.1708.04552 · Cited by 2,776
AutoAugment: Learning Augmentation Strategies From Data
Cubuk, E. D., Zoph, B., Mané, D., Vasudevan, V., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00020 · Cited by 2,733
Self-citationTowards End-To-End Speech Recognition with Recurrent Neural Networks
Graves, A., & Jaitly, N. (2014) · Cited by 2,557
Listen, attend and spell: A neural network for large vocabulary conversational speech recognition
Chan, W., Jaitly, N., Le, Q., & Vinyals, O. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472621 · Cited by 2,226
Self-citationSWITCHBOARD: telephone speech corpus for research and development
Godfrey, J. J., Holliman, E. C., & McDaniel, J. (1992) · [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1992.225858 · Cited by 2,134 · cited 2×
“On Switchboard 300h (LDC97S62) [22], we obtain 7.2% WER on the Switchboard portion of the Hub5’00 (LDC2002S09, LDC2003T02) test set, and 14.6% on the Call-Home portion, without using an LM.”
BackgroundInfluential
Research works printed but not linked: 2
- [41][41] K. Vesely, A. Ghoshal, L. Burger, and D. Povey, 'Sequencediscriminative training of deep neural networks,' in INTERSPEECH , 2013. -
- [43][43] G. Zweig, C. Yu, J. Droppo, and A. Stolcke, 'Advances in AllNeural Speech Recognition,' in ICASSP , 2017. -
Cited by
Items 801–900 of 1,013
Leveraging Pre-trained BERT for Audio Captioning
Liu, X., Mei, X., Huang, Q., Sun, J., Zhao, J., Liu, H., Plumbley, M. D., Kılıç, V., & Wang, W. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909761 · Cited by 35
Rosero, K., Grijalva, F., & Masiero, B. S. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3284525 · Cited by 35
Heavily Augmented Sound Event Detection utilizing Weak PredictionsPreprint
Nam, H., Ko, B.-Y., Lee, G.-T., Kim, S.-H., Jung, W., Choi, S.-M., & Park, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03649 · Cited by 35
Liu, Z., Guo, Z., Ling, Z., & Li, Y. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9413566 · Cited by 34
Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap
Yang, G., Yu, F., Ma, Z., Du, Z., Gao, Z., Zhang, S. S., & Chen, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889894 · Cited by 34
Hu, J., Cao, Y. P., Wu, M., Kang, F., Yang, F., Wang, W., Plumbley, M. D., & Yang, J. J. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3587446 · Cited by 34
Busbridge, D., Ramapuram, J., Ablin, P., Likhomanenko, T., Dhekane, E. G., Cuadros, X. S., & Webb, R. (2023) · neural information processing systems · doi:10.52202/075280-3197 · Cited by 34
Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition
Zhang, S., Gao, Z., Luo, H., Lei, M., Gao, J., Yan, Z., & Xie, L. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1972 · Cited by 34
Punjabi, S., Arsikere, H., Raeesy, Z., Chandak, C., Bhave, N., Bansal, A., Müller, M., Murillo, S., Rastrow, A., Stolcke, A., et al. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413734 · Cited by 34
Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer
Kim, S., Shangguan, Y., Mahadeokar, J., Bruguier, A., Fuegen, C., Seltzer, M. L., & Le, D. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414784 · Cited by 34
Jeong, Y., Kim, J., Kim, D., Kim, J., & Lee, K. (2021) · Applied Sciences · doi:10.3390/app11104544 · Cited by 34
Code-switched automatic speech recognition in five South African languages
Biswas, A., Yılmaz, E., van der Westhuizen, E., de Wet, F., & Niesler, T. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2021.101262 · Cited by 34
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
Higuchi, Y., Karube, K., Ogawa, T., & Kobayashi, T. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746580 · Cited by 34
Zhang, W., Shi, J. Y., Li, C., Watanabe, S., & Qian, Y. (2021) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa52581.2021.9632720 · Cited by 34
Data Augmentation for Dementia Detection in Spoken Language.
Woszczyk, D. C., Hedlikova, A., Akman, A., Demetriou, S., & Schuller, B. W. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10210 · Cited by 34
Adaptive multilingual speech recognition with pretrained models
Pham, N.-Q., Waibel, A. H., & Niehues, J. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-872 · Cited by 34
Business Data Analyst, M. A., Mamun, A., & Nijhum, A. M. (2023) · American Journal of Scholarly Research and Innovation · doi:10.63125/rpjwke42 · Cited by 34
Adversarial Regularization for Attention Based End-to-End Robust Speech Recognition
Sun, S., Guo, P., Xie, L., & Hwang, M.-Y. (2019) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2019.2933146 · Cited by 34
Bimodal Speech Emotion Recognition Using Pre-Trained Language ModelsPreprint
Heußer, V., Freymuth, N., Constantin, S., & Waibel, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02610 · Cited by 34
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech TranslationPreprint
Le, H., Pino, J., Wang, C., Gu, J., Schwab, D., & Besacier, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.00747 · Cited by 34
RegMix: Data Mixing Augmentation for RegressionPreprint
Hwang, S.-H., & Whang, S. E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03374 · Cited by 34
Zorro: the masked multimodal transformerPreprint
Recasens, A., Lin, J., Carreira, J., Jaegle, D., Wang, L., Alayrac, J.-B., Luc, P., Miech, A., Smaira, L., Hemsley, R., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.09595 · Cited by 34
Beat this! Accurate beat tracking without DBN postprocessingPreprint
Foscarin, F., Schlüter, J., & Widmer, G. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.21658 · Cited by 34
Voice Deepfake Detection Using the Self-Supervised Pre-Training Model HuBERT
Li, L., Lu, T., Ma, X., Yuan, M., & Wan, D. (2023) · Applied Sciences · doi:10.3390/app13148488 · Cited by 33
BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs
Jeon, Y., Park, B., Kwon, S. J., Kim, B., Yun, J., & Lee, D. (2020) · arXiv · doi:10.48550/arxiv.2005.09904 · Cited by 33
Speech Robust Bench: A Robustness Benchmark For Speech Recognition
Shah, M. A., Noguero, D. S., Heikkilä, M., Raj, B., & Kourtellis, N. (2024) · Helda - University of Helsinki Institutional Repository · doi:10.48550/arxiv.2403.07937 · Cited by 33
Learn and Don't Forget: Adding a New Language to ASR Foundation Models
Qian, M., Tang, S., Ma, R., Knill, K., & Gales, M. (2024) · Interspeech (USB) · doi:10.21437/interspeech.2024-1045 · Cited by 34
Yu, S., Yu, J., Chen, L., Zhu, B., Liang, X., Xie, Y., & Sun, Q. (2025) · Electronics · doi:10.3390/electronics14142794 · Cited by 33
Ling, S., Salazar, J., Liu, Y., & Kirchhoff, K. (2020) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2020-2 · Cited by 33
AutoKWS: Keyword Spotting with Differentiable Architecture Search
Zhang, B., Li, W., Li, Q., Zhuang, W., Chu, X., & Wang, Y. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414848 · Cited by 33
Schreyer, M., Sattarov, T., & Borth, D. (2021) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3490354.3494373 · Cited by 33
Conformer-Based Self-Supervised Learning For Non-Speech Audio Tasks
Srivastava, S., Wang, Y., Tjandra, A., Kumar, A., Liu, C., Singh, K., & Saraf, Y. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746490 · Cited by 33
Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization
Yamashita, N., Horiguchi, S., & Homma, T. (2022) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2022-19 · Cited by 33
LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Tian, J., Yu, J., Zhang, C., Zou, Y., & Yu, D. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-923 · Cited by 33
Yao, D., Chi, W., & Khishe, M. (2022) · Applied Acoustics · doi:10.1016/j.apacoust.2022.109003 · Cited by 33
Can a robot laugh with you?: Shared laughter generation for empathetic spoken dialogue
Inoue, K., Lala, D., & Kawahara, T. (2022) · Frontiers in Robotics and AI · doi:10.3389/frobt.2022.933261 · Cited by 33
Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis
Chen, H., Du, J., Dai, Y., Lee, C., Siniscalchi, S. M., Watanabe, S., Scharenborg, O., Chen, J., Yin, B., & Pan, J. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10483 · Cited by 33
ECAPA-TDNN Based Depression Detection from Clinical Speech
Wang, D., Ding, Y., Zhao, Q., Yang, P., Tan, S., & Li, Y. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10051 · Cited by 33
I Spy You: Eavesdropping Continuous Speech on Smartphones via Motion Sensors
Zhang, S., Liu, Y., & Gowda, M. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3569486 · Cited by 33
Peng, Y., Arora, S., Higuchi, Y., Ueda, Y., Kumar, S., Ganesan, K., Dalmia, S., Chang, X., & Watanabe, S. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10022399 · Cited by 33
Ferreira, A. I. S., da Silva, N. F. F., Mesquita, F. N., Rosa, T. C., Monzón, V. H., & Neto, J. N. M. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1081050 · Cited by 33
Efficient Domain Adaptation for Speech Foundation Models
Li, B., Hwang, D., Huo, Z., Bai, J., Prakash, G., Sainath, T. N., Sim, K. C., Zhang, Y., Han, W., Strohman, T., et al. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096330 · Cited by 33
Self-citationData augmentation for speech separation
Alex, A., Wang, L., Gastaldo, P., & Cavallaro, A. (2023) · Speech Communication · doi:10.1016/j.specom.2023.05.009 · Cited by 33
Higuchi, Y., Yan, B., Arora, S., Ogawa, T., Kobayashi, T., & Watanabe, S. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.402 · Cited by 33
Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks
Tang, Y., Sun, A., Inaguma, H., Chen, X., Dong, N., Ma, X., Tomasello, P., & Pino, J. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.695 · Cited by 33
Waveform-Domain Speech Enhancement Using Spectrogram Encoding for Robust Speech Recognition
Shi, H., Mimura, M., & Kawahara, T. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3407511 · Cited by 33
M&M Mix: A Multimodal Multiview Transformer EnsemblePreprint
Xiong, X., Arnab, A., Nagrani, A., & Schmid, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.09852 · Cited by 33
Exploring Train and Test-Time Augmentations for Audio-Language LearningPreprint
Kim, E., Kim, J.-H., Oh, Y., Kim, K., Park, M., Sim, J., Lee, J., & Lee, K. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.17143 · Cited by 33
Puvvada, K. C., Koluguri, N. R., Dhawan, K., Balam, J., & Ginsburg, B. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446998 · Cited by 32
Yusuyin, S., Ma, T., Huang, H., Zhao, W., & Ou, Z. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3550683 · Cited by 32
ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition
Pan, J. S., Shapiro, J., Wohlwend, J., Han, K. J., Lei, T., & Ma, T. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2947 · Cited by 32
Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition
Baskar, M. K., Burget, L., Watanabe, S., Astudillo, R. F., & Černocký, J. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413375 · Cited by 32
Voicemoji: Emoji Entry Using Voice for Visually Impaired People
Zhang, M. R., Wang, R., Xu, X., Li, Q., Sharif, A., & Wobbrock, J. O. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445338 · Cited by 32
Masumura, R., Makishima, N., Ihori, M., Takashima, A., Tanaka, T., & Orihashi, S. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414928 · Cited by 32
Shah, M. A., Szurley, J., Mueller, M., Mouchtaris, A., & Droppo, J. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1188 · Cited by 32
Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition
Moritz, N., Hori, T., & Roux, J. L. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1693 · Cited by 32
A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English
Mussakhojayeva, S., Khassanov, Y., & Varol, H. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87802-3_41 · Cited by 32
Data Augmentation for ASR Using TTS Via a Discrete Representation
Ueno, S., Mimura, M., Sakai, S., & Kawahara, T. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688218 · Cited by 32
Unsupervised Cross-Corpus Speech Emotion Recognition Using a Multi-Source Cycle-GAN
Su, B.-H., & Lee, C.-C. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3146325 · Cited by 32
Ilias, L., & Askounis, D. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110834 · Cited by 32
Mixture-of-Expert Conformer for Streaming Multilingual ASR
Hu, K., Li, B., Sainath, T. N., Zhang, Y., & Beaufays, F. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-480 · Cited by 32
Self-citationNeural Architecture Search for LF-MMI Trained Time Delay Neural Networks
Hu, S., Xie, X., Cui, M., Deng, J., Liu, S., Yu, J., Geng, M., Liu, X., & Meng, H. M. L. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3153253 · Cited by 32
SapAugment: Learning A Sample Adaptive Policy for Data Augmentation
Hu, T.-Y., Shrivastava, A., Chang, J.-H. R., Koppula, H. S., Braun, S., Hwang, K., Kalinli, O., & Tuzel, O. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413928 · Cited by 32
Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition
Li, L., Kang, Y., Shi, Y., Kürzinger, L., Watzel, T., & Rigoll, G. (2021) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-021-00215-6 · Cited by 32
Improving Semi-Supervised Learning for Audio Classification with FixMatch
Grollmisch, S., & Cano, E. (2021) · Electronics · doi:10.3390/electronics10151807 · Cited by 32
Sch-net: a deep learning architecture for automatic detection of schizophrenia
Fu, J., Yang, S., He, F., He, L., Li, Y., Zhang, J., & Xiong, X. (2021) · BioMedical Engineering OnLine · doi:10.1186/s12938-021-00915-2 · Cited by 31
“To improve the invariance properties to geometric perturbations and noise, data augmentation methods are utilized, including random crop, random rotation, random rescaling, random Gaussian noise, masking blocks of frequency channels [42], and masking blocks of time steps [42].”
MethodAudioProtoPNet: An interpretable deep learning model for bird sound classification
Heinrich, R., Rauch, L., Sick, B., & Scholz, C. (2024) · arXiv · doi:10.48550/arxiv.2404.10420 · Cited by 31
“We also applied time and frequency masking [54] as spectrogram augmentation 4 .”
Cross-Domain Contrastive Learning-Based Few-Shot Underwater Acoustic Target Recognition
Cui, X., He, Z., Xue, Y., Tang, K., Zhu, P., & Han, J. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12020264 · Cited by 31
PromptASR for Contextualized ASR with Controllable Style
Yang, X., Kang, W., Yao, Z., Yang, Y., Guo, L., Kuang, F., Lin, L., & Povey, D. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448264 · Cited by 31
Deep semi-supervised regression via pseudo-label filtering and calibration
Jo, Y., Kahng, H., & Kim, S. B. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111670 · Cited by 31
Enhancing heart disease prediction with reinforcement learning and data augmentation
Gayathri, R., Sangeetha, S. K. B., Mathivanan, S. K., Rajadurai, H., B, B. A. M. M., Mallik, S., & Qin, H. H. (2024) · Systems and Soft Computing · doi:10.1016/j.sasc.2024.200129 · Cited by 31
Khanom, F., Biswas, S. K., Uddin, M. S., & Mostafiz, R. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10152-2 · Cited by 31
M2D-CLAP: Exploring General-Purpose Audio-Language Representations Beyond CLAP
Niizumi, D., Takeuchi, D., Yasuda, M., Nguyen, B. T., Ohishi, Y., & Harada, N. (2025) · IEEE Access · doi:10.1109/access.2025.3611348 · Cited by 31
SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation
McCarthy, A. D., Puzon, L., & Pino, J. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053406 · Cited by 31
An, K., Xiang, H., & Ou, Z. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2732 · Cited by 31
The STC System for the CHiME 2018 Challenge
Medennikov, I., Sorokin, I., Romanenko, A., Popov, D., Khokhlov, Y., Prisyach, T., Malkovskiy, N., Bataev, V., Astapov, S., Korenevsky, M. L., et al. (2018) · International Workshop on Speech Processing in Everyday Environments (CHiME) · doi:10.21437/chime.2018-1 · Cited by 31
A convolutional neural network for estimating synaptic connectivity from spike trains
Endo, D., Kobayashi, R., Bartolo, R., Averbeck, B. B., Sugase-Miyamoto, Y., Hayashi, K., Kawano, K., Richmond, B. J., & Shinomoto, S. (2021) · Scientific Reports · doi:10.1038/s41598-021-91244-w · Cited by 31
Chuang, S.-P., Chuang, Y.-S., Chang, C.-C., & Lee, H.-Y. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.92 · Cited by 31
Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition
Gong, X., Lu, Y., Zhou, Z., & Qian, Y. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1075 · Cited by 31
Overlapped Speech Detection and speaker counting using distant microphone arrays
Cornell, S., Omologo, M., Squartini, S., & Vincent, E. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2021.101306 · Cited by 31
Cascade or Direct Speech Translation? A Case Study
Etchegoyhen, T., Arzelus, H., Gete, H., Álvarez, A., Torre, I. G., Martín-Doñas, J. M., González-Docasal, A., & Fernandez, E. B. (2022) · Applied Sciences · doi:10.3390/app12031097 · Cited by 31
Multi-Turn RNN-T for Streaming Recognition of Multi-Party Speech
Sklyar, I., Piunova, A., Zheng, X., & Liu, Y. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746074 · Cited by 31
A ResNet attention model for classifying mosquitoes from wing-beating sounds
Wei, X., Hossain, M. Z., & Ahmed, K. A. (2022) · Scientific Reports · doi:10.1038/s41598-022-14372-x · Cited by 31
An Ensemble of Deep Learning Frameworks for Predicting Respiratory Anomalies
Pham, L. D., Ngo, D. T., Tran, K., Hoang, T., Schindler, A., & McLoughlin, I. V. (2022) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc48229.2022.9871440 · Cited by 31
Tjandra, A., Singhal, N., Zhang, D., Kalinli, O., Mohamed, A., Le, D., & Seltzer, M. L. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094667 · Cited by 31
Boosting Cross-Domain Speech Recognition With Self-Supervision
Zhu, H., Cheng, G., Wang, J., Hou, W., Zhang, P., & Yan, Y. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3301230 · Cited by 31
Analyzing analytical methods: The case of phonology in neural models of spoken language
Chrupała, G., Higy, B., & Alishahi, A. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.381 · Cited by 31
Few-shot bioacoustic event detection: A new task at the DCASE 2021 challenge
Morfi, V., Nolasco, I., Lostanlen, V., Singh, S., Strandburg‐Peshkin, A., Gill, L. F., Pamuła, H., Benvent, D., & Stowell, D. (2021) · Research portal (Tilburg University) · doi:10.26116/ab2h-gm83 · Cited by 31
Mel-spectrogram augmentation for sequence to sequence voice conversionPreprint
Hwang, Y., Cho, H. M., Yang, H., Won, D.-O., Oh, I., & Lee, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01401 · Cited by 31
Exploiting Spectral Augmentation for Code-Switched Spoken Language IdentificationPreprint
Rangan, P., Teki, S., & Misra, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.07130 · Cited by 31
Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech TranslationPreprint
Gaido, M., Negri, M., Cettolo, M., & Turchi, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.11710 · Cited by 31
Shimada, K., Takahashi, N., Koyama, Y., Takahashi, S., Tsunoo, E., Takahashi, M., & Mitsufuji, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10806 · Cited by 31
Plüss, M., Neukom, L., Scheller, C., & Vogel, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.02810 · Cited by 31
Data Augmentation for ElectrocardiogramsPreprint
Raghu, A., Shanmugam, D., Pomerantsev, E. V., Guttag, J. V., & Stultz, C. M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.04360 · Cited by 31
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text SystemsPreprint
Park, T., Medennikov, I., Dhawan, K., Wang, W., Huang, H., Koluguri, N. R., Puvvada, K. C., Balam, J., & Ginsburg, B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.06656 · Cited by 31
Wang, X., Delgado, H., Tak, H., Jung, J.-W., Shim, H.-J., Todisco, M., Kukanov, I., Liu, X., Sahidullah, M., Kinnunen, T., et al. (2026) · Computer Speech & Language · doi:10.1016/j.csl.2025.101825 · Cited by 30
“As illustrated in Figure 3 and described in § 2.7, CM systems can be used on their own as solutions to Challenge Track 1.”
InfluentialSelf-citationAutomatic Speech Recognition Tuned for Child Speech in the Classroom
Southwell, R. V., Ward, W., Trinh, V. A., Clevenger, C., Clevenger, C., Watts, E., Reitman, J. G., D’Mello, S. K., & Whitehill, J. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447428 · Cited by 30
UAPT: an underwater acoustic target recognition method based on pre-trained Transformer
Tang, J., Ma, E., Qu, Y., Gao, W., Zhang, Y., & Gan, L. (2025) · Multimedia Systems · doi:10.1007/s00530-024-01614-3 · Cited by 30
Self-citationA comprehensive survey on Arabic text augmentation: approaches, challenges, and applications
ElSabagh, A. A., Azab, S. S., & Hefny, H. A. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11020-z · Cited by 30
A Review on Sound Source Localization in Robotics: Focusing on Deep Learning Methods
Jalayer, R., Jalayer, M., & Baniasadi, A. (2025) · Applied Sciences · doi:10.3390/app15179354 · Cited by 30
Metadata
- Authors
- Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V.
- Affiliations
- Google (United States) (US)
- Venue
- Interspeech 2019
- Publisher
- ISCA
- Published
- 2019-09-15
- Pages
- 2613-2617
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2936774411
- Cited by
- 3,558
- References
- 51
- Citations by year
- 2026: 239 · 2025: 415 · 2024: 450 · 2023: 649 · 2022: 603 · 2021: 738 · 2020: 391 · 2019: 69
- FWCI
- 172.29
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Keywords
- SpecAugment, data augmentation, speech recognition, frequency masking, feature warping, end-to-end speech recognition, LibriSpeech, switchboards, CALLHOME, word error rate
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.