Papers › ImportantAug: a data augmentation agent for speech

ImportantAug: a data augmentation agent for speech

14 Dec 2021ICASSP 2022 4arXiv:2112.07156archive 2025-07-28

Viet Anh Trinh, Hassan Salami Kavaki, Michael I Mandel

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 by a data augmentation agent that is trained to maximize the amount of noise it adds while minimizing its impact on recognition performance. The effectiveness of our method is illustrated on version two of the Google Speech Commands (GSC) dataset. On the standard GSC test set, it achieves a 23.3% relative error rate reduction compared to conventional noise augmentation which applies noise to speech without regard to where it might be most effective. It also provides a 25.4% error rate reduction compared to a baseline without data augmentation. Additionally, the proposed ImportantAug outperforms the conventional noise augmentation and the baseline on two test sets with additional noise added.

PaperPDFConference PDFCode

Code

tvanh512/importantAug officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationKeyword SpottingSpeech Recognition

Datasets

Introduced by this paper, per the archive.

Google Speech Commands - Musan

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keyword Spotting Google Speech Commands ImportantAug Google Speech Command-Musan 86.7 #35 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands ImportantAug Google Speech Commands V2 35 95 #35 of 42 Archive leaderboard report
Speech Recognition Google Speech Commands - Musan ImportantAug Error rate - SNR 0dB 13.3 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections