# GPU-accelerated Guided Source Separation for Meeting Transcription

arXiv: https://arxiv.org/abs/2212.05271 · HTML: https://mlsanity.com/paper/2212.05271/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2022.

## Built on by (most cited first, 10 of 10)

- [Powerset multi-class cross entropy loss for neural speaker diarization](https://mlsanity.com/paper/2310.13025/) (2023)
- [The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios](https://mlsanity.com/paper/2306.13734/) (2023)
- [A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2403.04245/) (2024)
- [Neural Blind Source Separation and Diarization for Distant Speech Recognition](https://mlsanity.com/paper/2406.08396/) (2024)
- [The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition](https://mlsanity.com/paper/2505.13971/) (2025)
- [Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges](https://mlsanity.com/paper/2507.18161/) (2025)
- [End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization](https://mlsanity.com/paper/2401.12850/) (2024)
- [ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings](https://mlsanity.com/paper/2406.03251/) (2024)
- [The NUS-HLT System for ICASSP2024 ICMC-ASR Grand Challenge](https://mlsanity.com/paper/2312.16002/) (2023)
- [SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays](https://mlsanity.com/paper/2601.18037/) (2026)

## Abstract (arXiv)

Guided source separation (GSS) is a type of target-speaker extraction method that relies on pre-computed speaker activities and blind source separation to perform front-end enhancement of overlapped speech signals. It was first proposed during the CHiME-5 challenge and provided significant improvements over the delay-and-sum beamforming baseline. Despite its strengths, however, the method has seen limited adoption for meeting transcription benchmarks primarily due to its high computation time. In this paper, we describe our improved implementation of GSS that leverages the power of modern GPU-based pipelines, including batched processing of frequencies and segments, to provide 300x speed-up over CPU-based inference. The improved inference time allows us to perform detailed ablation studies over several parameters of the GSS algorithm -- such as context duration, number of channels, and noise class, to name a few. We provide end-to-end reproducible pipelines for speaker-attributed transcription of popular meeting benchmarks: LibriCSS, AMI, and AliMeeting. Our code and recipes are publicly available: https://github.com/desh2608/gss.