mlsanityData to 7 Oct 2026

USTC-NELSLIP System Description for DIHARD-III Challenge

arXiv 2103.10661 ↗First posted 19 Mar 2021cs.SD cs.LG eess.AScited by 7

Not on the map. Why?

Abstract (arXiv)

This system description describes our submission system to the Third DIHARD Speech Diarization Challenge. Besides the traditional clustering based system, the innovation of our system lies in the combination of various front-end techniques to solve the diarization problem, including speech separation and target-speaker based voice activity detection (TS-VAD), combined with iterative data purification. We also adopted audio domain classification to design domain-dependent processing. Finally, we performed post processing to do system fusion and selection. Our best system achieved DERs of 11.30% in track 1 and 16.78% in track 2 on evaluation set, respectively.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 14 of its 21 references that are in the map. First posted on arXiv 19 Mar 2021.

Builds on

14 of 21 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  3. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  4. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
  5. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  6. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  7. 2020CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordingscited by 129
  8. 2020Spot the conversation: speaker diarisation in the wildcited by 75
  9. 2020Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenariocited by 67
  10. 2020Asteroid: the PyTorch-based audio source separation toolkit for researcherscited by 45
  11. 2020The Third DIHARD Diarization Challengecited by 44
  12. 2015THCHS-30 : A Free Chinese Speech Corpuscited by 43
2 more
  1. 2020DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputscited by 18
  2. 2020BUT System for the Second DIHARD Speech Diarization Challengecited by 11

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 0; 2024: 1; 2025: 2.

7 papers.

  1. 2021Three-class Overlapped Speech Detection using a Convolutional Recurrent Neural Networkcited by 8
  2. 2022Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarizationcited by 7
  3. 2021Multi-scale speaker embedding-based graph attention networks for speaker diarisationcited by 6
  4. 2022High-resolution embedding extractor for speaker diarisationcited by 1
  5. 2024From Modular to End-to-End Speaker Diarizationcited by 0
  6. 2025Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challengecited by 0
  7. 2025Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithmcited by 0