mlsanityData to 14 Oct 2026

Auto-KWS 2021 Challenge: Task, Datasets, and Baselines

arXiv 2104.00513 ↗First posted 31 Mar 2021cs.SD cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Auto-KWS 2021 challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to a customized keyword spotting task. Compared with other keyword spotting tasks, Auto-KWS challenge has the following three characteristics: 1) The challenge focuses on the problem of customized keyword spotting, where the target device can only be awakened by an enrolled speaker with his specified keyword. The speaker can use any language and accent to define his keyword. 2) All dataset of the challenge is recorded in realistic environment. It is to simulate different user scenarios. 3) Auto-KWS is a "code competition", where participants need to submit AutoML solutions, then the platform automatically runs the enrollment and prediction steps with the submitted code.This challenge aims at promoting the development of a more personalized and flexible keyword spotting system. Two baseline systems are provided to all participants as references.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 31 Mar 2021.

Builds on

21 of 33 references.

References · 21

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  4. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 340
  5. 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 198
  6. 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 186
  7. 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 110
  8. 2019Learning Problem-agnostic Speech Representations from Multiple Self-supervised Taskscited by 87
  9. 2020DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantizationcited by 77
  10. 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
  11. 2018Automated Machine Learning: From Principles to Practicescited by 62
  12. 2016Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencodercited by 34
9 more
  1. 2018Attention-based End-to-End Models for Small-Footprint Keyword Spottingcited by 18
  2. 2020Few-Shot Keyword Spotting With Prototypical Networkscited by 18
  3. 2017Attention-Based Models for Text-Dependent Speaker Verificationcited by 17
  4. 2018Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Searchcited by 7
  5. 2020Wake Word Detection with Alignment-Free Lattice-Free MMIcited by 6
  6. 2021The 2020 Personalized Voice Trigger Challenge: Open Database, Evaluation Metrics and the Baseline Systemscited by 4
  7. 2020AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classificationcited by 2
  8. 2021The NPU System for the 2020 Personalized Voice Trigger Challengecited by 2
  9. 2020IEEE SLT 2021 Alpha-mini Speech Challenge: Open Datasets, Tracks, Rules and Baselinescited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 1.

2 papers.

  1. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  2. 2024MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spottingcited by 4