mlsanityData to 14 Oct 2026

Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges

arXiv 2507.18161 ↗First posted 24 Jul 2025eess.AS cs.CL cs.SDcited by 2

Not on the map. Why?

Abstract (arXiv)

The CHiME-7 and 8 distant speech recognition (DASR) challenges focus on multi-channel, generalizable, joint automatic speech recognition (ASR) and diarization of conversational speech. With participation from 9 teams submitting 32 diverse systems, these challenges have contributed to state-of-the-art research in the field. This paper outlines the challenges' design, evaluation metrics, datasets, and baseline systems while analyzing key trends from participant submissions. From this analysis it emerges that: 1) Most participants use end-to-end (e2e) ASR systems, whereas hybrid systems were prevalent in previous CHiME challenges. This transition is mainly due to the availability of robust large-scale pre-trained models, which lowers the data burden for e2e-ASR. 2) Despite recent advances in neural speech separation and enhancement (SSE), all teams still heavily rely on guided source separation, suggesting that current neural SSE techniques are still unable to reliably deal with complex scenarios and different recording setups. 3) All best systems employ diarization refinement via target-speaker diarization techniques. Accurate speaker counting in the first diarization pass is thus crucial to avoid compounding errors and CHiME-8 DASR participants especially focused on this part. 4) Downstream evaluation via meeting summarization can correlate weakly with transcription quality due to the remarkable effectiveness of large-language models in handling errors. On the NOTSOFAR-1 scenario, even systems with over 50% time-constrained minimum permutation WER can perform roughly on par with the most effective ones (around 11%). 5) Despite recent progress, accurately transcribing spontaneous speech in challenging acoustic environments remains difficult, even when using computationally intensive system ensembles.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 63 of its 109 references that are in the map. First posted on arXiv 24 Jul 2025.

Builds on

63 of 109 references.

References · 63

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  7. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  8. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  9. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
  10. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
  11. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  12. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 463
38 more
  1. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
  2. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 399
  3. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
  4. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 342
  5. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  6. 2024Rotary Position Embedding for Vision Transformercited by 236
  7. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 226
  8. 2022Generative Spoken Dialogue Language Modelingcited by 126
  9. 2018The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselinescited by 92
  10. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 91
  11. 2019End-to-End Neural Speaker Diarization with Permutation-Free Objectivescited by 88
  12. 2021End-to-end speaker segmentation for overlap-aware resegmentationcited by 80
  13. 2019End-to-End Neural Speaker Diarization with Self-attentioncited by 77
  14. 2020Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenariocited by 68
  15. 2021TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global contextcited by 62
  16. 2019SpecAugment on Large Scale Datasetscited by 60
  17. 2021AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenariocited by 60
  18. 2021SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Expertscited by 48
  19. 2021Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understandingcited by 42
  20. 2021Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversationscited by 42
  21. 2023Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Datacited by 42
  22. 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 40
  23. 2019The Second DIHARD Diarization Challenge: Dataset, task, and baselinescited by 39
  24. 2020Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengapcited by 36
  25. 2020Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysiscited by 35
  26. 2018Voices Obscured in Complex Environmental Settings (VOICES) corpuscited by 28
  27. 2023MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systemscited by 28
  28. 2019Advances in Online Audio-Visual Meeting Transcriptioncited by 23
  29. 2021Advances in integration of end-to-end neural and clustering-based diarization for real conversational speechcited by 23
  30. 2022Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimationcited by 23
  31. 2024Leveraging Self-Supervised Learning for Speaker Diarizationcited by 23
  32. 2021Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASRcited by 22
  33. 2024NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcriptioncited by 21
  34. 2024UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMscited by 21
  35. 2020WER we are and WER we think we arecited by 19
  36. 2020DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputscited by 19
  37. 2022Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognitioncited by 19
  38. 2022End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representationcited by 17

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metricscited by 0
  2. 2026YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speechcited by 0