mlsanityData to 19 Oct 2026

BUT CHiME-7 system description

arXiv 2310.11921 ↗First posted 18 Oct 2023cs.SD eess.AScited by 3

On the map: Speech and audio language models → Speaker recognition and diarization

Abstract (arXiv)

This paper describes the joint effort of Brno University of Technology (BUT), AGH University of Krakow and University of Buenos Aires on the development of Automatic Speech Recognition systems for the CHiME-7 Challenge. We train and evaluate various end-to-end models with several toolkits. We heavily relied on Guided Source Separation (GSS) to convert multi-channel audio to single channel. The ASR is leveraging speech representations from models pre-trained by self-supervised learning, and we do a fusion of several ASR systems. In addition, we modified external data from the LibriSpeech corpus to become a close domain and added it to the training. Our efforts were focused on the far-field acoustic robustness sub-track of Task 1 - Distant Automatic Speech Recognition (DASR), our systems use oracle segmentation.

Key facts. Cited by 3 papers in the map (data through 19 Oct 2026). Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models. Builds on 16 of its 34 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

16 of 34 references.

References · 16

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 4,385
  2. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,420
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 2,293
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 2,135
  5. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 2,060
  6. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 754
  7. 2019WHAM!: Extending Speech Separation to Noisy Environmentscited by 246
  8. 2022TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separationcited by 76
  9. 2022Pruned RNN-T for fast, memory-efficient ASR trainingcited by 61
  10. 2018Building and Evaluation of a Real Room Impulse Response Datasetcited by 55
  11. 2019DiPCo -- Dinner Party Corpuscited by 42
  12. 2022GPU-accelerated Guided Source Separation for Meeting Transcriptioncited by 33
4 more
  1. 2021DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extractioncited by 12
  2. 2021Leveraging Low-Distortion Target Estimates for Improved Speech Enhancementcited by 10
  3. 2023Multi-Channel Target Speaker Extraction with Refinement: The WavLab Submission to the Second Clarity Enhancement Challengecited by 9
  4. 2023Hystoc: Obtaining word confidences for fusion of end-to-end ASR systemscited by 1

Built on by

Cited by year (2026 to 19 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarizationcited by 27
  2. 2025MOVER: Combining Multiple Meeting Recognition Systemscited by 2
  3. 2026Cross-Talk Speech Reduction, by Separation, for Separationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios
  2. 2025Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges
  3. 2023The CHiME-7 Challenge: System Description and Performance of NeMo Team's DASR System
  4. 2024NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge
  5. 2024The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
  6. 2023The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
  7. 2023Automatic channel selection and spatial feature integration for multi-channel speech recognition across various array topologies
  8. 2025Automatic Speech Recognition in the Modern Era: Architectures, Training, and Evaluation