mlsanityData to 7 Oct 2026

The RoyalFlush System of Speech Recognition for M2MeT Challenge

arXiv 2202.01614 ↗First posted 3 Feb 2022cs.SD eess.AS stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper describes our RoyalFlush system for the track of multi-speaker automatic speech recognition (ASR) in the M2MeT challenge. We adopted the serialized output training (SOT) based multi-speakers ASR system with large-scale simulation data. Firstly, we investigated a set of front-end methods, including multi-channel weighted predicted error (WPE), beamforming, speech separation, speech enhancement and so on, to process training, validation and test sets. But we only selected WPE and beamforming as our frontend methods according to their experimental results. Secondly, we made great efforts in the data augmentation for multi-speaker ASR, mainly including adding noise and reverberation, overlapped speech simulation, multi-channel speech simulation, speed perturbation, front-end processing, and so on, which brought us a great performance improvement. Finally, in order to make full use of the performance complementary of different model architecture, we trained the standard conformer based joint CTC/Attention (Conformer) and U2++ ASR model with a bidirectional attention decoder, a modification of Conformer, to fuse their results. Comparing with the official baseline system, our system got a 12.22% absolute Character Error Rate (CER) reduction on the validation set and 12.11% on the test set.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 36 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

19 of 36 references.

References · 19

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  2. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  3. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  4. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
  5. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  6. 2020Serialized Output Training for End-to-End Overlapped Speech Recognitioncited by 87
  7. 2021M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challengecited by 67
  8. 2021AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenariocited by 58
  9. 2020Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakerscited by 41
  10. 2017Recognizing Multi-talker Speech with Permutation Invariant Trainingcited by 33
  11. 2021Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphonecited by 33
  12. 2021U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognitioncited by 28
7 more
  1. 2020Streaming Multi-speaker ASR with RNN-Tcited by 22
  2. 2019State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutionscited by 11
  3. 2021A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audiocited by 10
  4. 2021A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separationcited by 9
  5. 2021Data Augmentation Methods for End-to-end Speech Recognition on Distant-Talk Scenarioscited by 6
  6. 2021Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimationcited by 4
  7. 2020Context-aware RNNLM Rescoring for Conversational Speech Recognitioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 0; 2026: 1.

3 papers.

  1. 2022VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognitioncited by 7
  2. 2024Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTCcited by 4
  3. 2026SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrayscited by 0