mlsanityData to 7 Oct 2026

Continuous Speech Separation with Conformer

arXiv 2008.05773 ↗First posted 13 Aug 2020eess.AS cs.CLcited by 36

Not on the map. Why?

Abstract (arXiv)

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and conformer in lieu of recurrent neural networks in the separation system, as we believe capturing global information with the self-attention based method is crucial for the speech separation. Evaluating on the LibriCSS dataset, the conformer separation model achieves state of the art results, with a relative 23.5% word error rate (WER) reduction from bi-directional LSTM (BLSTM) in the utterance-wise evaluation and a 15.4% WER reduction in the continuous evaluation.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 14; 2023: 6; 2024: 2; 2025: 5; 2026: 1.

36 papers.

Sort:

By area:

  1. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  2. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 90
  3. 2023MM-VID: Advancing Video Understanding with GPT-4V(ision)cited by 82
  4. 2021PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitioncited by 50
  5. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 45
  6. 2022Streaming Multi-Talker ASR with Token-Level Serialized Output Trainingcited by 37
  7. 2022TranSpeech: Speech-to-Speech Translation With Bilateral Perturbationcited by 34
  8. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 22
  9. 2021Personalized Speech Enhancement: New Models and Comprehensive Evaluationcited by 18
  10. 2024NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcriptioncited by 18
  11. 2022Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddingscited by 14
  12. 2021A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audiocited by 10
24 more
  1. 2021VarArray: Array-Geometry-Agnostic Continuous Speech Separationcited by 10
  2. 2022Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Datacited by 9
  3. 2023HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methodscited by 8
  4. 2022A Conformer Based Acoustic Model for Robust Automatic Speech Recognitioncited by 6
  5. 2021Continuous Speech Separation with Ad Hoc Microphone Arrayscited by 5
  6. 2021MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separationcited by 5
  7. 2022Speech separation with large-scale self-supervised learningcited by 5
  8. 2023BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASRcited by 5
  9. 2022Exploring Self-Attention Mechanisms for Speech Separationcited by 4
  10. 2022Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separationcited by 4
  11. 2021BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancementcited by 3
  12. 2022Ultra Fast Speech Separation Model with Teacher Student Learningcited by 3
  13. 2023Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Fillingcited by 3
  14. 2023On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environmentscited by 3
  15. 2024AG-LSEC: Audio Grounded Lexical Speaker Error Correctioncited by 3
  16. 2022Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Expertscited by 2
  17. 2023Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learningcited by 2
  18. 2025SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Modelscited by 1
  19. 2025Error Analysis in a Modular Meeting Transcription Systemcited by 1
  20. 2022DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognitioncited by 0
  21. 2025Single-Channel Distance-Based Source Separation for Mobile GPU in Outdoor and Indoor Environmentscited by 0
  22. 2025Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarioscited by 0
  23. 2025CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-Car Speech Separation with Distributed Heterogeneous Arrayscited by 0
  24. 2026Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correctioncited by 0