Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
SpecAugment
Description:
SpecAugment is a data augmentation method for speech processing that masks portions of audio spectrograms during model training.
Primary topic:
Speech Recognition and Synthesis (53%)
Related topics:
Speech Recognition and Synthesis (53%),
Music and Audio Processing (21%),
Emotion and Mood Recognition (7%)
OpenAlex ID:
keywords/specaugment
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
2019
·
Daniel S. Park
, William Chan
, et al.
·
Interspeech (USB)
·
4,984
PDF
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
2020
·
Zhang, Yu
, Qin, James
, et al.
·
arXiv (Cornell University)
·
378
PDF
Improved Noisy Student Training for Automatic Speech Recognition
2020
·
Daniel S. Park
, Yu Zhang
, et al.
·
Interspeech (USB)
·
317
PDF
A Comparison of Transformer and LSTM Encoder Decoder Models for ASR
2019
·
Albert Zeyer
, Parnia Bahar
, et al.
·
IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)
·
290
Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation
2021
·
Feng Liu
, Tongsheng Shen
, et al.
·
Applied Acoustics
·
219
Specaugment on Large Scale Datasets
2020
·
Daniel S. Park
, Yu Zhang
, et al.
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
182
PDF
A Comparison on Data Augmentation Methods Based on Deep Learning for Audio Classification
2020
·
Shengyun Wei
, Shun Zou
, et al.
·
Journal of Physics Conference Series
·
176
PDF
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems
2020
·
Nick Rossenbach
, Albert Zeyer
, et al.
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
123
PDF
MixSpeech: Data Augmentation for Low-Resource Automatic Speech Recognition
2021
·
Linghui Meng
, Jin Xu
, et al.
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
113
PDF
Attention-based hybrid CNN-LSTM and spectral data augmentation for COVID-19 diagnosis from cough sound
2022
·
Skander Hamdi
, Mourad Oussalah
, et al.
·
Journal of Intelligent Information Systems
·
77
PDF
End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020
2020
·
Marco Gaido
, Mattia A. Di Gangi
, et al.
·
International Conference on Spoken Language Translation (IWSLT)
·
76
PDF
Training Keyword Spotting Models on Non-IID Data with Federated Learning
2020
·
Andrew Hard
, Kurt Partridge
, et al.
·
Interspeech (USB)
·
75
PDF
On Using SpecAugment for End-to-End Speech Translation
2019
·
Bahar, Parnia
, Zeyer, Albert
, et al.
·
RWTH Publications (RWTH Aachen)
·
71
PDF
Time–Frequency Domain Deep Convolutional Neural Network for Li-Ion Battery SoC Estimation
2023
·
Ki-Hyeon Kim
, Koog-Hwan Oh
, et al.
·
IEEE Transactions on Power Electronics
·
65
SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification
2021
·
Helin Wang
, Yuexian Zou
, et al.
·
Interspeech (USB)
·
63
PDF
ASV-SUBTOOLS: Open Source Toolkit for Automatic Speaker Verification
2021
·
Fuchuan Tong
, Miao Zhao
, et al.
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
60
Semantic Mask for Transformer Based End-to-End Speech Recognition
2020
·
Chengyi Wang
, Yu Wu
, et al.
·
Interspeech (USB)
·
58
PDF
A comparison of data augmentation methods in voice pathology detection
2023
·
Farhad Javanmardi
, Sudarsana Reddy Kadiri
, et al.
·
Computer Speech & Language
·
57
PDF
The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment
2020
·
Wei Zhou
, Wilfried Michel
, et al.
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
57
PDF
Transfer learning and SpecAugment applied to SSVEP based BCI classification
2021
·
Pedro R.A.S. Bassi
, Willian Rampazzo
, et al.
·
Biomedical Signal Processing and Control
·
54
PDF
Speaker Augmentation for Low Resource Speech Recognition
2020
·
Chenpeng Du
, Kai Yu
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
50
Investigation of Specaugment for Deep Speaker Embedding Learning
2020
·
Shuai Wang
, Johan Rohdin
, et al.
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
48
Speech Emotion Recognition Based on Parallel CNN-Attention Networks with Multi-Fold Data Augmentation
2022
·
John Lorenzo Bautista
, Yun Kyung Lee
, et al.
·
Electronics
·
47
PDF
Data Augmentation for end-to-end Code-Switching Speech Recognition
2021
·
Chenpeng Du
, Hao Li
, et al.
·
IEEE Spoken Language Technology Workshop (SLT)
·
43
PDF
RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
2024
·
June-Woo Kim
, Miika Toikkanen
, et al.
·
Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
·
38
PDF
Show more works
View as search
Works count:
265
Citation count:
8,942
Year
Topic
Type