cs.CLNov 8, 2026

TID System for Speech-COSER Challenge 2026: ASR Track

Authors: Fernando López, Jordi Luque

Organizations: Telefónica Innovación Digital, Spain · Universidad Autónoma de Madrid, Spain

Abstract

We describe the system submitted by Telefónica Innovación Digital to the Speech-COSER Challenge 2026, which features spontaneous speech from elderly speakers recorded in rural Spain. For ASR, we perform CTC-based pseudo-forced alignment scores audio-text match quality to guide a two-stage LoRA curriculum, followed by post-hoc magnitude pruning of the LoRA matrices to enhance generalization. An ensemble of seven systems combined via ROVER achieves 36.25% unnormalized and 22.17% normalized WER.

Figures & tables

Explore similar work

CardsList
  1. TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs

    Apr 9, 2026Jing Peng, Chenghao Wang, Yi Yang +5Connectionist Temporal ClassificationSpeech Language Models

  2. The VoiceMOS Challenge 2026: Evaluating Speech Enhancement, Emotional TTS and Accented TTS Systems

    Sep 12, 2026Wen-Chin Huang, Wei Wang, Marvin Sach +4Speech Quality AssessmentTTS Evaluation

  3. ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech

    Jun 20, 2026Wei Xue, Junlan Feng, Shilei Zhang +9TTS SynthesisTTS Evaluation