mlsanityData to 19 Oct 2026

Frontend-Assisted Large Audio-Language Models for SLT2026 SmartGlasses Challenge

arXiv 2610.13282 ↗First posted 9 Oct 2026eess.AS cs.SDcited by 0

On the map: Speech and audio language models → Audio language models and spoken dialogue also fits: Speaker recognition and diarization

Abstract (arXiv)

This paper describes our systems for the Track 1 time-stamped speaker-attributed ASR task of the SmartGlasses Challenge. To handle overlapping speech, background noise and far-field conditions in two-person conversations, we employ SoulX-Transcriber, a multimodal large language model that takes full-length audio as input and generates structured transcriptions. In addition, we investigate the effect of speech frontend processing, including a rule-based Guided Source Separation method and a data-driven speech separation model, both of which improve performance on the validation set. Considering inference stability, our final submission uses the fine-tuned SoulX-Transcriber system, achieving a tcpCER of 6.22 on the test set.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Audio language models and spoken dialogue, one of 11 directions in Speech and audio language models. Builds on 9 of its 12 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

9 of 12 references.

References · 9

  1. 2025Qwen3-Omni Technical Reportcited by 578
  2. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 275
  3. 2024Leveraging Self-Supervised Learning for Speaker Diarizationcited by 49
  4. 2022GPU-accelerated Guided Source Separation for Meeting Transcriptioncited by 33
  5. 2025Interspeech 2025 URGENT Speech Enhancement Challengecited by 30
  6. 2026VIBEVOICE-ASR Technical Reportcited by 29
  7. 2026SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcriptioncited by 5
  8. 2026DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Modelscited by 4
  9. 2025Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarizationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The SLT 2026 SmartGlasses Challenge: Benchmarking Egocentric Multi-Talker Speech Recognition and Understanding with Audio-Language Models
  2. 2026Sink or SWIM: Tackling Real-Time ASR at Scale
  3. 2026Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge
  4. 2025Elevating Robust Multi-Talker ASR by Decoupling Speaker Separation and Speech Recognition
  5. 2026Pushing the Boundaries of Streaming Multi-Speaker ASR: A Systematic Study of Architectural Trade-offs
  6. 2026The tttAI System for the TSA-ASR Task of the SmartGlasses Challenge 2026
  7. 2022Deliberation Model for On-Device Spoken Language Understanding
  8. 2025Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios