activity
20182026
most citedData Augmentation For Children's Speech Recognition -- The "Ethiopian" System For The SLT 2021 Children Speech Recognition Challenge

11 citations · 16 across the 14 of their papers we have counts for

collaborators
Showing cs.SDShow all

16 papers · 1 filter

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…

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.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…

cs.SD2025

GLAP: General contrastive audio-text pretraining across domains and languages

Heinrich Dinkel, Zhiyong Yan, Tianzi Wang +7

Contrastive Language Audio Pretraining (CLAP) is a widely-used method to bridge the gap between audio and text domains. Current CLAP methods enable sound and music retrieval in Eng…

cs.SD2025

X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance

Junbo Zhang, Heinrich Dinkel, Yadong Niu +4

We introduces X-ARES (eXtensive Audio Representation and Evaluation Suite), a novel open-source benchmark designed to systematically assess audio encoder performance across diverse…

cs.SD2025

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

Gang Li, Jizhong Liu, Heinrich Dinkel +3

Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively…