mlsanityData to 7 Oct 2026

Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss

arXiv 2102.07061 ↗First posted 14 Feb 2021cs.CL cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

This paper proposes a neural network architecture for tackling the query-by-example user-defined keyword spotting task. A multi-head attention module is added on top of a multi-layered GRU for effective feature extraction, and a normalized multi-head attention module is proposed for feature aggregation. We also adopt the softtriple loss - a combination of triplet loss and softmax loss - and showcase its effectiveness. We demonstrate the performance of our model on internal datasets with different languages and the public Hey-Snips dataset. We compare the performance of our model to a baseline system and conduct an ablation study to show the benefit of each component in our architecture. The proposed work shows solid performance while preserving simplicity.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 14 Feb 2021.

Builds on

11 of 20 references.

References · 11

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  3. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  4. 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
  5. 2016Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approachescited by 25
  6. 2018Efficient keyword spotting using dilated convolutions and gatingcited by 21
  7. 2017End-to-End ASR-free Keyword Search from Speechcited by 19
  8. 2017Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Modelscited by 19
  9. 2017Attention-Based Models for Text-Dependent Speaker Verificationcited by 17
  10. 2018DONUT: CTC-based Query-by-Example Keyword Spottingcited by 15
  11. 2017Query-by-example Spoken Term Detection using Attention-based Multi-hop Networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 5; 2024: 6; 2025: 3; 2026: 3.

25 papers.

Sort:

  1. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  2. 2021Few-Shot Keyword Spotting in Any Languagecited by 27
  3. 2022Learning Audio-Text Agreement for Open-vocabulary Keyword Spottingcited by 20
  4. 2023Matching Latent Encoding for Audio-Text based Keyword Spottingcited by 15
  5. 2023Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systemscited by 9
  6. 2023Open-vocabulary Keyword-spotting with Adaptive Instance Normalizationcited by 8
  7. 2022Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spottingcited by 7
  8. 2022Personalized Keyword Spotting through Multi-task Learningcited by 7
  9. 2022On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spottingcited by 4
  10. 2022QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixercited by 4
  11. 2024MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spottingcited by 4
  12. 2024Relational Proxy Loss for Audio-Text based Keyword Spottingcited by 3
13 more
  1. 2024Text-Aware Adapter for Few-Shot Keyword Spottingcited by 2
  2. 2022Improving Voice Trigger Detection with Metric Learningcited by 1
  3. 2024End-to-End User-Defined Keyword Spotting using Shifted Delta Coefficientscited by 1
  4. 2025Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spottingcited by 1
  5. 2023Continuously Reliable Detection of New-Normal Misinformation: Semantic Masking and Contrastive Smoothing in High-Density Latent Regionscited by 0
  6. 2023Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Datacited by 0
  7. 2024Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learningcited by 0
  8. 2024SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spottingcited by 0
  9. 2025Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detectioncited by 0
  10. 2025Keyword Spotting with Hyper-Matched Filters for Small Footprint Devicescited by 0
  11. 2026MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spottingcited by 0
  12. 2026PCOV-KWS: Multi-task Learning for Personalized Customizable Open Vocabulary Keyword Spottingcited by 0
  13. 2026ProKWS: Personalized Keyword Spotting via Collaborative Learning of Phonemes and Prosodycited by 0