# Pseudo Labels-based Neural Speech Enhancement for the AVSR Task in the MISP-Meeting Challenge

arXiv: https://arxiv.org/abs/2505.24446 · HTML: https://mlsanity.com/paper/2505.24446/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 23 of 23)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge](https://mlsanity.com/paper/2110.07393/) (2021)
- [AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario](https://mlsanity.com/paper/2104.03603/) (2021)
- [Glancing Transformer for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2008.07905/) (2020)
- [CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition](https://mlsanity.com/paper/1905.11235/) (2019)
- [The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios](https://mlsanity.com/paper/2306.13734/) (2023)
- [NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription](https://mlsanity.com/paper/2401.08887/) (2024)
- [SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation](https://mlsanity.com/paper/2307.16516/) (2023)
- [GPU-accelerated Guided Source Separation for Meeting Transcription](https://mlsanity.com/paper/2212.05271/) (2022)
- [A Simultaneous Denoising and Dereverberation Framework with Target Decoupling](https://mlsanity.com/paper/2106.12743/) (2021)
- [The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization](https://mlsanity.com/paper/2407.16447/) (2024)
- [Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation](https://mlsanity.com/paper/2108.07376/) (2021)
- [The Multimodal Information based Speech Processing (MISP) 2022 Challenge: Audio-Visual Diarization and Recognition](https://mlsanity.com/paper/2303.06326/) (2023)
- [The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement](https://mlsanity.com/paper/2307.03533/) (2023)
- [UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures](https://mlsanity.com/paper/2305.20054/) (2023)
- [The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction](https://mlsanity.com/paper/2309.08348/) (2023)
- [Mixture to Mixture: Leveraging Close-talk Mixtures as Weak-supervision for Speech Separation](https://mlsanity.com/paper/2402.09313/) (2024)

## Built on by (most cited first, 1 of 1)

- [Cross-Talk Speech Reduction, by Separation, for Separation](https://mlsanity.com/paper/2605.19695/) (2026)

## Abstract (arXiv)

This paper presents our system for the MISP-Meeting Challenge Track 2. The primary difficulty lies in the dataset, which contains strong background noise, reverberation, overlapping speech, and diverse meeting topics. To address these issues, we (a) designed G-SpatialNet, a speech enhancement (SE) model to improve Guided Source Separation (GSS) signals; (b) proposed TLS, a framework comprising time alignment, level alignment, and signal-to-noise ratio filtering, to generate signal-level pseudo labels for real-recorded far-field audio data, thereby facilitating SE models' training; and (c) explored fine-tuning strategies, data augmentation, and multimodal information to enhance the performance of pre-trained Automatic Speech Recognition (ASR) models in meeting scenarios. Finally, our system achieved character error rates (CERs) of 5.44% and 9.52% on the Dev and Eval sets, respectively, with relative improvements of 64.8% and 52.6% over the baseline, securing second place.