collaborators

5 papers

cs.SD2026

DashengTokenizer: One layer is enough for unified audio understanding and generation

Heinrich Dinkel, Xingwei Sun, Gang Li +8

This paper introduces DashengTokenizer, a continuous audio tokenizer engineered for joint use in both understanding and generation tasks. Unlike conventional approaches, which trai…

eess.AS2026

ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding

Yadong Niu, Tianzi Wang, Heinrich Dinkel +6

General audio understanding is a fundamental goal for large audio-language models, with audio captioning serving as a cornerstone task for their development. However, progress in t…

cs.SD2026

The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models

Heinrich Dinkel, Jiahao Zhou, Guanbo Wang +8

This paper presents the Interspeech 2026 Audio Encoder Capability Challenge, a benchmark specifically designed to evaluate and advance the performance of pre-trained audio encoders…

cs.LG2025

On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding

Jiahao Zhou, Chengliang Lin, Dingji Li +2

Semantic top-K selection with cross-encoder rerankers underpins on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. Howeve…

cs.SD2025

MiDashengLM: Efficient Audio Understanding with General Audio Captions

Heinrich Dinkel, Gang Li, Jizhong Liu +7

Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper intr…