Papers › Learning Efficient Representations for Keyword Spotting with Triplet Loss

Learning Efficient Representations for Keyword Spotting with Triplet Loss

12 Jan 2021SPECOM 2021arXiv:2101.04792archive 2025-07-28

Roman Vygon, Nikolay Mikhaylovskiy

In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most no-tably, person reidentification. On the other hand, in the area of speech recognition the metric embeddings generated by the triplet loss are rarely used even for classification problems. We fill this gap showing that a combination of two representation learning techniques: a triplet loss-based embedding and a variant of kNN for classification instead of cross-entropy loss significantly (by 26% to 38%) improves the classification accuracy for convolutional networks on a LibriSpeech-derived LibriWords datasets. To do so, we propose a novel phonetic similarity based triplet mining approach. We also improve the current best published SOTA for Google Speech Commands dataset V1 10+2 -class classification by about 34%, achieving 98.55% accuracy, V2 10+2-class classification by about 20%, achieving 98.37% accuracy, and V2 35-class classification by over 50%, achieving 97.0% accuracy.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

roman-vygon/triplet_loss_kws officialmentioned in papermentioned on GitHubpytorch 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

ClassificationKeyword SpottingRepresentation LearningSpeech Recognitionspeech-recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keyword Spotting Google Speech Commands TripletLoss-res15 Google Speech Commands V1 12 98.56 #1 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands TripletLoss-res15 Google Speech Commands V2 12 98.37 #1 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands TripletLoss-res15 Google Speech Commands V2 35 97.0 #1 of 42 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