Runyan Yang — accepted AI-conference papers

2026

Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation

ICASSP 2026poster

While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of structured intermediate supervision. To address this, we propose a unified knowledge distillation framew…

Cited by 0 Source ↗PDF ↗Scholar ↗

2021

Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Text Data

Changfeng Gao, Gaofeng Cheng, Runyan Yang, Han Zhu, Pengyuan Zhang, Yonghong Yan

ICASSP 2021accepted

This paper presents a method to pre-train transformer-based encoder-decoder automatic speech recognition (ASR) models using sufficient target-domain text. During pre-training, we train the transformer decoder as a conditional language model with empty or artifical states, rather than the real encode…

Cited by 0 Source ↗Scholar ↗