activity
20242026
most citedWhen LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection

1 citations · 1 across the 9 of their papers we have counts for

collaborators
Showing cs.SDShow all

2 papers · 1 filter

cs.SD2026

StepAudio 3 Realtime Technical Report

Bin Lin, Bo Zhao, Boyang Zhang +87

Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a…

cs.SD2026

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition

Qingjian Lin, Yuxin Li, Haoyang Zhang +14

Audio-encoder-LLM-decoder architectures have become the dominant paradigm for modern automatic speech recognition (ASR), improving transcription quality through large-scale languag…