Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge

arXiv cs.CL Papers

Summary

The paper presents a cascaded framework for speaker-attributed multilingual ASR, achieving second place in the MLC-SLM 2026 Challenge with a tcpMER of 15.41%.

arXiv:2609.20833v1 Announce Type: new Abstract: This paper presents the Transsion Speech Team submission to Task 1 of the MLC-SLM 2026 Challenge, which focuses on speaker-attributed transcription for multilingual conversational speech. We propose a cascaded framework consisting of three components: a speaker diarization module, a long-form multilingual ASR module, and a speaker-transcription fusion module. The diarization module is built upon DiariZen and produces speaker-homogeneous segments through local speaker activity estimation and global speaker clustering. The ASR module is based on Qwen3-Omni and generates multilingual transcriptions, while an external CTC-based alignment model provides precise word- and character-level timestamps. Finally, the fusion module combines diarization outputs with timestamped transcriptions to generate speaker-attributed STM outputs. Experimental results on the official evaluation set demonstrate the effectiveness of the proposed framework. The submitted system achieves a tcpMER of 15.41% and ranks second among all participating teams.
Original Article
View Cached Full Text

Cached at: 09/21/26, 08:58 AM

# Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge
Source: [https://arxiv.org/abs/2609.20833](https://arxiv.org/abs/2609.20833)
[View PDF](https://arxiv.org/pdf/2609.20833)

> Abstract:This paper presents the Transsion Speech Team submission to Task 1 of the MLC\-SLM 2026 Challenge, which focuses on speaker\-attributed transcription for multilingual conversational speech\. We propose a cascaded framework consisting of three components: a speaker diarization module, a long\-form multilingual ASR module, and a speaker\-transcription fusion module\. The diarization module is built upon DiariZen and produces speaker\-homogeneous segments through local speaker activity estimation and global speaker clustering\. The ASR module is based on Qwen3\-Omni and generates multilingual transcriptions, while an external CTC\-based alignment model provides precise word\- and character\-level timestamps\. Finally, the fusion module combines diarization outputs with timestamped transcriptions to generate speaker\-attributed STM outputs\. Experimental results on the official evaluation set demonstrate the effectiveness of the proposed framework\. The submitted system achieves a tcpMER of 15\.41% and ranks second among all participating teams\.

## Submission history

From: Xiaoxiao Li \[[view email](https://arxiv.org/show-email/0272dffc/2609.20833)\] **\[v1\]**Fri, 24 Jul 2026 09:42:54 UTC \(1,072 KB\)

Similar Articles

@YichiZ03: https://x.com/YichiZ03/status/2078588932191895976

X AI KOLs Timeline

MOSS-TD, a speaker-aware ASR system, is optimized within the SGLang-Omni serving stack, enabling 38-minute multi-speaker audio to be transcribed in about 49 seconds on a single H100, with concurrent processing of 16 meetings.

Streaming Speech-to-Text Translation with a SpeechLLM

arXiv cs.CL

Presents a SpeechLLM architecture for streaming speech-to-text translation that adaptively decides when to output tokens based on audio, achieving 1-2 second latency with quality close to non-streaming baselines.