Frontend-Assisted Large Audio-Language Models for SLT2026 SmartGlasses Challenge
Yushi Wang, Zeyan Song, Xiaobin Rong, Chengwei Liu, Jun Gao, Jing Lu
Abstract
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.
Create a lesson
Related papers
OpenPA: Forced-alignment-free Multi-granular Pronunciation Assessment with Mixed-transcript Adaptation
Fu-An Chao, Bi-Cheng Yan, Berlin Chen
OpenSVBench: Diagnosing Speaker Verification Generalization Across Deployment Scenarios
Qituan Shangguan, Bosen Xu, Shuai Wang
Vocal Intensity Conversion with Continuous SPL Control via Adversarial Training
Quentin Le Tellier, Albert Rilliard, Olivier Perrotin et al.
Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization
Xu He, Homayoon Beigi
Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR
Thai Quoc On, Homayoon Beigi
E3-System: Expressive EmoData, Explicitly Controllable, Easy-to-Use TTS
Yiqiao Huang, Xiaolong Lin, Zhenpeng Zhan et al.