mlsanityData to 14 Oct 2026

Towards noise robust trigger-word detection with contrastive learning pre-task for fast on-boarding of new trigger-words

arXiv 2111.03971 ↗First posted 6 Nov 2021cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. But supporting a particular word as a trigger-word involves huge amount of data collection, augmentation and labelling for that word. This makes supporting new trigger-words a tedious and time consuming process. To combat this, we explore the use of contrastive learning as a pre-training task that helps the detection model to generalize to different words and noise conditions. We explore supervised contrastive techniques and also propose a novel self-supervised training technique using chunked words from long sentence audios. We show that both supervised and the new self-supervised contrastive pre-training techniques have comparable results to a traditional classification pre-training on new trigger words with less data availability.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 25 references that are in the map. First posted on arXiv 6 Nov 2021.

Builds on

17 of 25 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2020Supervised Contrastive Learningcited by 2,829
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  5. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  6. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  7. 2017Transfer learning for music classification and regression taskscited by 37
  8. 2018Mining on Manifolds: Metric Learning without Labelscited by 36
  9. 2020Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learningcited by 33
  10. 2020CLAR: Contrastive Learning of Auditory Representationscited by 31
  11. 2018Attention-based End-to-End Models for Small-Footprint Keyword Spottingcited by 18
  12. 2020Towards Data-efficient Modeling for Wake Word Spottingcited by 13
5 more
  1. 2021Wake Word Detection with Streaming Transformerscited by 10
  2. 2021Teaching keyword spotters to spot new keywords with limited examplescited by 9
  3. 2018Efficient keyword spotting using time delay neural networkscited by 5
  4. 2020Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancementcited by 4
  5. 2021SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classificationcited by 4

Built on by

Not cited yet.