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

arXiv: https://arxiv.org/abs/2610.13282 · HTML: https://mlsanity.com/paper/2610.13282/

## 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.

## Placed in

- Speech and audio language models / [Audio language models and spoken dialogue](https://mlsanity.com/speech/audio-language-models-and-spoken-dialogue/)

## Builds on (most cited first, 9 of 9)

- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [Leveraging Self-Supervised Learning for Speaker Diarization](https://mlsanity.com/paper/2409.09408/) (2024)
- [GPU-accelerated Guided Source Separation for Meeting Transcription](https://mlsanity.com/paper/2212.05271/) (2022)
- [Interspeech 2025 URGENT Speech Enhancement Challenge](https://mlsanity.com/paper/2505.23212/) (2025)
- [VIBEVOICE-ASR Technical Report](https://mlsanity.com/paper/2601.18184/) (2026)
- [SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription](https://mlsanity.com/paper/2606.02400/) (2026)
- [DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models](https://mlsanity.com/paper/2604.22467/) (2026)
- [Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization](https://mlsanity.com/paper/2510.14551/) (2025)

## 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.