A cascaded diarization-then-recognition system that combines DiariZen-Large-s80 (WavLM-Large) segmentation, CAM++ embedding-based two-speaker clustering, and a LoRA-adapted omniASR LLM 7B v2 recognizer, with no oracle segmentation or speaker labels at test time is described.
Abstract
We describe our submission to Task 1 of the 2nd MLCSLM Challenge: a cascaded diarization-then-recognition system that combines DiariZen-Large-s80 (WavLM-Large) segmentation, CAM++ embedding-based two-speaker clustering, and a LoRA-adapted omniASR LLM 7B v2 recognizer, with no oracle segmentation or speaker labels at test time. On the official Development set (150 conversations, 21 language/accent categories) the system attains a macro tcpMER of 29.27%, versus 79.15% for the official baseline; on the Evaluation set it scores 50.23%. We also analyze two engineering choices that substantially affect tcpMER. First, embedding-based speaker clustering outperforms an end-to-end-style alternative that assigns speakers from ASRturn markers alone. Second, overlap-aware segmentation, although intended to raise diarization recall, increases tcpMER because overlapped speech is transcribed twice.
This paper presents the tttAI system submitted to the TSA-ASR task of the SmartGlasses Challenge 2026, evaluated on both two- person dialogues and multi-party meetings, and proposes a cascaded architecture consisting of speaker diarization, overlap detection, target-speaker extraction, post-processing, and automatic sp...
Xuanji He, Gaoyang Dong, Xiaoxiao Li et al.· 0 citations
Traditional speaker-attributed ASR systems treated ASR and speaker diarization as two separate tasks. Recently, end-to-end models such as VibeVoice-ASR have unified the two tasks within a single model. However, existing unified models still mainly support offline recognition, making it difficult to meet the low-latency...
Yu-Jie Tu, Zhiliang Peng, Jianwei Yu et al.· 0 citations
In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility r...
Chuan-Meng Bian, Da-Ren Chen, Pei-Xin Chen et al.· 2 citations
This paper details the Eloquence team's approach to Task 2 of the 2nd MLC-SLM challenge at Interspeech 2026, which involves multilingual Multiple-Choice Question Answering (MCQA) across 21 languages. Three approaches are explored. First, we fine-tune Voxtral-Mini-3B via LoRA with cross-lingual data augmentation, ASR tr...
Jordi Luque, Lorenzo Concina, M. Matassoni et al.· 1 citation
Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embedd...
Yi-Ru Zhang, Hang Su, Li-Chun Fan et al.· 1 citation
This paper describes the system for Task~2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which adapt Qwen3-Omni-30B-A3B-Instruct with a segment-evidence-aware data and post-training pipeline and obtains 90.92% accuracy on the final official evaluation set.
H. Le, L. Nguyen, Minh Tri Dao· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
