Lynx at the NADI 2026 Shared Task: Exploring ASR Representations and Transcripts for Dialectal Arabic Speech Understanding
Year: 2026
Type: conference-paper
Abstract: Speech conveys complementary information through its linguistic content and acoustic characteristics.Speech-related tasks can exploit either source of information or combine them to improve performance.In this paper, we present Lynx_Id and Lynx_In, our systems for the NADI 2026 Spoken Dialect Identification and Intent Recognition tasks, respectively.Both systems build on an automatic speech recognition (ASR) model.Lynx_Id is a late-fusion system for dialect identification.It combines internal representations from the ASR encoder with predictions derived from the ASR transcript.Lynx_In is a two-branch textbased system that uses ASR transcriptions for intent recognition.One branch predicts the intent among the known classes, while the second acts as a gate to detect out-of-scope utterances.Lynx_Id achieved 53.53% accuracy and ranked third in the Spoken Dialect Identification task, while Lynx_In achieved a weighted F1 score of 76.86% and ranked first in the Intent Recognition task.
Authors: Houdaifa Atou, Issam Ait Yahia, Ismail Berrada
Institution: Université Mohammed VI Polytechnique
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7224308488