Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge

• URL: http://arxiv.org/abs/2608.14150v1
• Date: Fri, 14 Aug 2026 10:00:42 GMT
• Title: Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge
• Abstract summary: The second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge evaluates two tasks over complete, unsegmented multilingual conversations.<n>Neither task provides oracle utterance boundaries or speaker labels at evaluation, and Task 2 provides no question-answer training set.<n>We fine-tune VibeVoice-ASR-7B with random leading-silence cropping, consistent timestamp correction, and distribution-matched augmentation.
• Score: 28.363948904202932
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge evaluates two tasks over complete, unsegmented multilingual conversations: speaker diarization and recognition (Task 1) and conversational speech understanding (Task 2). Neither task provides oracle utterance boundaries or speaker labels at evaluation, and Task 2 provides no question-answer training set. For Task 1, we fine-tune VibeVoice-ASR-7B with random leading-silence cropping, consistent timestamp correction, and an exponential moving average (EMA) training strategy. For Task 2, we construct synthetic question-answer pairs through multimodal candidate generation, silent-audio filtering, and distribution-matched augmentation, and fine-tune Qwen3-Omni-30B-A3B-Instruct for tagged direct answering. On the Task 1 evaluation set, cropping reduces tcpMER from 18.30% to 17.27%, and EMA further reduces it to 16.73%. On the Task 2 evaluation set, jointly applying distribution-matched augmentation and tagged direct answering raises accuracy from 83.0% to 86.0%.

Related papers

• The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge [7.980139831363608]
  We fine-tune Voxtral-Mini-3B via LoRA with cross-lingual data augmentation, ASR transcript augmentation and timestamp-aware audio cropping.<n>Second, we apply multimodal in-context learning to the frozen Voxtral-24B model to correct a strong label bias, reaching 0.81.<n>Third, a training-free retrieval system based on a three-layer voice-anchored memory combining acoustic identity, semantic content, and a knowledge graph achieves 0.68.
  arXiv  Detail & Related papers  (2026-09-10T15:41:11Z)
• SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ [0.0]
  This paper describes our system for Task2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge.<n>A language model converts timestamped ASR into coherent event spans, which are expanded by a boundary margin and cropped from the original recording.<n>A text-only probe partitions the data into weak, text-answerable items used for supervised fine-tuning and strong, audio-dependent items used for reinforcement learning.
  arXiv  Detail & Related papers  (2026-09-10T10:38:19Z)
• Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech [14.048968602801606]
  This paper describes our self-designed hallucination system for Task 1 of the MLC-SLM 2026 Challenge for multilingual two-speaker conversational speech.<n>The system combines a modular speaker diarization front end with a challenge-adapted Qwen3-ASR-1.7B recognizer.
  arXiv  Detail & Related papers  (2026-07-09T08:07:34Z)
• VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing [45.15289852736435]
  VoiceAssistant-Eval comprises 10,497 curated examples spanning 13 task categories.<n>To demonstrate its utility, we evaluate 21 open-source models and GPT-4o-Audio.<n>Results reveal three key findings: proprietary models do not universally outperform open-source models.
  arXiv  Detail & Related papers  (2025-09-26T17:59:59Z)
• Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges [63.741916531380696]
  The CHiME-7 and 8 distant speech recognition (DASR) challenges focus on multi-channel, generalizable, joint automatic speech recognition (ASR) and diarization of conversational speech.<n>This paper outlines the challenges' design, evaluation metrics, datasets, and baseline systems while analyzing key trends from participant submissions.
  arXiv  Detail & Related papers  (2025-07-24T07:56:24Z)
• Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice [52.747242157396315]
  Simultaneous Interpretation (SI) represents one of the most daunting frontiers in the translation industry.<n>We introduce Seed-LiveInterpret 2.0, an end-to-end SI model that delivers high-fidelity, ultra-low-latency speech-to-speech generation with voice cloning capabilities.
  arXiv  Detail & Related papers  (2025-07-23T14:07:41Z)
• Audio Large Language Models Can Be Descriptive Speech Quality Evaluators [46.765203628127345]
  We introduce the first natural language-based speech evaluation corpus, generated from authentic human ratings.<n>This corpus offers detailed analysis across multiple dimensions and identifies causes of quality degradation.<n>We propose an alignment approach with LLM distillation (ALLD) to guide the audio LLM in extracting relevant information from raw speech.
  arXiv  Detail & Related papers  (2025-01-27T22:47:51Z)
• Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System [73.34663391495616]
  We propose a pioneering approach to tackle joint multi-talker and target-talker speech recognition tasks. Specifically, we freeze Whisper and plug a Sidecar separator into its encoder to separate mixed embedding for multiple talkers. We deliver acceptable zero-shot performance on multi-talker ASR on AishellMix Mandarin dataset.
  arXiv  Detail & Related papers  (2024-07-13T09:28:24Z)
• Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE [203.65227947509933]
  This report describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmark, containing eight difficult language understanding tasks.
  arXiv  Detail & Related papers  (2022-12-04T15:36:18Z)
• Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition [55.25565305101314]
  Articulatory features are invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition systems. This paper presents a cross-domain and cross-lingual A2A inversion approach that utilizes the parallel audio and ultrasound tongue imaging (UTI) data of the 24-hour TaL corpus in A2A model pre-training. Experiments conducted on three tasks suggested incorporating the generated articulatory features consistently outperformed the baseline TDNN and Conformer ASR systems.
  arXiv  Detail & Related papers  (2022-06-15T07:20:28Z)
• MAESTRO: Matched Speech Text Representations through Modality Matching [35.566604806335626]
  Maestro is a self-supervised training method to unify representations learnt from speech and text modalities. We establish a new state-of-the-art (SOTA) on VoxPopuli multilingual ASR with a 11% relative reduction in Word Error Rate (WER) We establish a new state-of-the-art (SOTA) on CoVoST 2 with an improvement of 2.8 BLEU averaged over 21 languages.
  arXiv  Detail & Related papers  (2022-04-07T12:48:16Z)
• A Simple Language Model for Task-Oriented Dialogue [61.84084939472287]
  SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2.
  arXiv  Detail & Related papers  (2020-05-02T11:09:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.