most citedJoint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning

18 citations · 18 across the 2 of their papers we have counts for

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2026

Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models

Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim +7

Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order. This gap arises because existing…