Heinrich Dinkel

73 papers A* 1A 15B 1Misc 10Journal 38Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding. CoRR Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Junbo Zhang, Jian Luan
2026	J	`jnl`	DashengTokenizer: One layer is enough for unified audio understanding and generation. CoRR Heinrich Dinkel, Xingwei Sun, Gang Li, Jiahao Mei, Yadong Niu, Jizhong Liu, Xiyang Li, Yifan Liao, Jiahao Zhou, Junbo Zhang, Jian Luan
2026	J	`jnl`	The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models. CoRR Heinrich Dinkel, Jiahao Zhou, Guanbo Wang, Yadong Niu, Junbo Zhang, Yufeng Hao, Ying Liu, Ke Li, Wenwu Wang, Zhiyong Wu, Jian Luan
2025	A	`conf`	Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders. INTERSPEECH Xingwei Sun, Heinrich Dinkel, Yadong Niu, Linzhang Wang, Junbo Zhang, Jian Luan
2025	J	`jnl`	Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders. CoRR Xingwei Sun, Heinrich Dinkel, Yadong Niu, Linzhang Wang, Junbo Zhang, Jian Luan
2025	J	`jnl`	GLAP: General contrastive audio-text pretraining across domains and languages. CoRR Heinrich Dinkel, Zhiyong Yan, Tianzi Wang, Yongqing Wang, Xingwei Sun, Yadong Niu, Jizhong Liu, Gang Li, Junbo Zhang, Jian Luan
2025	A	`conf`	GLCLAP: A Novel Contrastive Learning Pre-trained Model for Contextual Biasing in ASR. INTERSPEECH Yuxiang Kong, Fan Cui, Liyong Guo, Heinrich Dinkel, Lichun Fan, Junbo Zhang, Jian Luan
2025	J	`jnl`	MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks. CoRR Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Xunying Liu, Junbo Zhang, Jian Luan
2025	J	`jnl`	MiDashengLM: Efficient Audio Understanding with General Audio Captions. CoRR Heinrich Dinkel, Gang Li, Jizhong Liu, Jian Luan, Yadong Niu, Xingwei Sun, Tianzi Wang, Qiyang Xiao, Junbo Zhang, Jiahao Zhou
2025	J	`jnl`	Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering. CoRR Gang Li, Jizhong Liu, Heinrich Dinkel, Yadong Niu, Junbo Zhang, Jian Luan
2025	J	`jnl`	The ICME 2025 Audio Encoder Capability Challenge. CoRR Junbo Zhang, Heinrich Dinkel, Qiong Song, Helen Wang, Yadong Niu, Si Cheng, Xiaofeng Xin, Ke Li, Wenwu Wang, Yujun Wang, Jian Luan
2025	A	`conf`	X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance. INTERSPEECH Junbo Zhang, Heinrich Dinkel, Yadong Niu, Chenyu Liu, Si Cheng, Anbei Zhao, Jian Luan
2025	J	`jnl`	X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance. CoRR Junbo Zhang, Heinrich Dinkel, Yadong Niu, Chenyu Liu, Si Cheng, Anbei Zhao, Jian Luan
2024	A	`conf`	Bridging Language Gaps in Audio-Text Retrieval. INTERSPEECH Zhiyong Yan, Heinrich Dinkel, Yongqing Wang, Jizhong Liu, Junbo Zhang, Yujun Wang, Bin Wang
2024	J	`jnl`	Bridging Language Gaps in Audio-Text Retrieval. CoRR Zhiyong Yan, Heinrich Dinkel, Yongqing Wang, Jizhong Liu, Junbo Zhang, Yujun Wang, Bin Wang
2024	Misc	`conf`	CED: Consistent Ensemble Distillation for Audio Tagging. ICASSP Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang
2024	A	`conf`	Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding. INTERSPEECH Jizhong Liu, Gang Li, Junbo Zhang, Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Yujun Wang, Bin Wang
2024	J	`jnl`	Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding. CoRR Jizhong Liu, Gang Li, Junbo Zhang, Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Yujun Wang, Bin Wang
2024	A	`conf`	Scaling up masked audio encoder learning for general audio classification. INTERSPEECH Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Bin Wang
2024	J	`jnl`	Scaling up masked audio encoder learning for general audio classification. CoRR Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Bin Wang
2024	A	`conf`	Streaming Audio Transformers for Online Audio Tagging. INTERSPEECH Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Bin Wang
2023	J	`jnl`	AV-SepFormer: Cross-Attention SepFormer for Audio-Visual Target Speaker Extraction. CoRR Jiuxin Lin, Xinyu Cai, Heinrich Dinkel, Jun Chen, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Zhiyong Wu, Yujun Wang, Helen Meng
2023	Misc	`conf`	Av-Sepformer: Cross-Attention Sepformer for Audio-Visual Target Speaker Extraction. ICASSP Jiuxin Lin, Xinyu Cai, Heinrich Dinkel, Jun Chen, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Zhiyong Wu, Yujun Wang, Helen Meng
2023	J	`jnl`	CED: Consistent ensemble distillation for audio tagging. CoRR Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang
2023	A	`conf`	Focus on the Sound around You: Monaural Target Speaker Extraction via Distance and Speaker Information. INTERSPEECH Jiuxin Lin, Peng Wang, Heinrich Dinkel, Jun Chen, Zhiyong Wu, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2023	J	`jnl`	Focus on the Sound around You: Monaural Target Speaker Extraction via Distance and Speaker Information. CoRR Jiuxin Lin, Peng Wang, Heinrich Dinkel, Jun Chen, Zhiyong Wu, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2023	J	`jnl`	Streaming Audio Transformers for Online Audio Tagging. CoRR Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2023	J	`jnl`	Understanding temporally weakly supervised training: A case study for keyword spotting. CoRR Heinrich Dinkel, Weiji Zhuang, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2023	Misc	`conf`	Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers. ICASSP Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang
2023	J	`jnl`	Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers. CoRR Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang
2022	—	`conf`	An Empirical Study of Weakly Supervised Audio Tagging Embeddings for General Audio Representations. Odyssey Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2022	J	`jnl`	An empirical study of weakly supervised audio tagging embeddings for general audio representations. CoRR Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2022	Misc	`conf`	Category-Adapted Sound Event Enhancement with Weakly Labeled Data. ICASSP Guangwei Li, Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu
2022	Misc	`conf`	Pseudo Strong Labels for Large Scale Weakly Supervised Audio Tagging. ICASSP Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2022	J	`jnl`	Pseudo strong labels for large scale weakly supervised audio tagging. CoRR Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang
2022	A	`conf`	UniKW-AT: Unified Keyword Spotting and Audio Tagging. INTERSPEECH Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang
2022	J	`jnl`	UniKW-AT: Unified Keyword Spotting and Audio Tagging. CoRR Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang
2021	—	`conf`	A Contrastive Semi-Supervised Learning Framework For Anomaly Sound Detection. DCASE Xinyu Cai, Heinrich Dinkel
2021	—	`conf`	A Lightweight Approach for Semi-Supervised Sound Event Detection with Unsupervised Data Augmentation. DCASE Xinyu Cai, Heinrich Dinkel
2021	A	`conf`	A Lightweight Framework for Online Voice Activity Detection in the Wild. Interspeech Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu
2021	—	`conf`	Audio Caption in a Car Setting with a Sentence-Level Loss. ISCSLP Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu
2021	A*	`conf`	DEPA: Self-Supervised Audio Embedding for Depression Detection. ACM Multimedia Pingyue Zhang, Mengyue Wu, Heinrich Dinkel, Kai Yu
2021	Misc	`conf`	Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning. ICASSP Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Zeyu Xie, Kai Yu
2021	J	`jnl`	Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning. CoRR Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Zeyu Xie, Kai Yu
2021	Misc	`conf`	Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events. ICASSP Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu
2021	J	`jnl`	Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events. CoRR Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu
2021	J	`jnl`	Towards Duration Robust Weakly Supervised Sound Event Detection. IEEE ACM Trans. Audio Speech Lang. Process. Heinrich Dinkel, Mengyue Wu, Kai Yu
2021	J	`jnl`	Towards duration robust weakly supervised sound event detection. CoRR Heinrich Dinkel, Mengyue Wu, Kai Yu
2021	J	`jnl`	Voice Activity Detection in the Wild: A Data-Driven Approach Using Teacher-Student Training. IEEE ACM Trans. Audio Speech Lang. Process. Heinrich Dinkel, Shuai Wang, Xuenan Xu, Mengyue Wu, Kai Yu
2021	J	`jnl`	Voice activity detection in the wild: A data-driven approach using teacher-student training. CoRR Heinrich Dinkel, Shuai Wang, Xuenan Xu, Mengyue Wu, Kai Yu
2020	—	`conf`	A CRNN-GRU Based Reinforcement Learning Approach to Audio Captioning. DCASE Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu
2020	A	`conf`	Dual-Adversarial Domain Adaptation for Generalized Replay Attack Detection. INTERSPEECH Hongji Wang, Heinrich Dinkel, Shuai Wang, Yanmin Qian, Kai Yu
2020	Misc	`conf`	Duration Robust Weakly Supervised Sound Event Detection. ICASSP Heinrich Dinkel, Kai Yu
2020	J	`jnl`	End-to-end spoofing detection with raw waveform CLDNNs. CoRR Heinrich Dinkel, Nanxin Chen, Yanmin Qian, Kai Yu
2020	J	`jnl`	GPVAD: Towards noise robust voice activity detection via weakly supervised sound event detection. CoRR Heinrich Dinkel, Yefei Chen, Mengyue Wu, Kai Yu
2020	—	`conf`	Multiple Sound Sources Localization from Coarse to Fine. ECCV (20) Rui Qian, Di Hu, Heinrich Dinkel, Mengyue Wu, Ning Xu, Weiyao Lin
2020	J	`jnl`	Multiple Sound Sources Localization from Coarse to Fine. CoRR Rui Qian, Di Hu, Heinrich Dinkel, Mengyue Wu, Ning Xu, Weiyao Lin
2020	A	`conf`	Voice Activity Detection in the Wild via Weakly Supervised Sound Event Detection. INTERSPEECH Yefei Chen, Heinrich Dinkel, Mengyue Wu, Kai Yu
2019	Misc	`conf`	Audio Caption: Listen and Tell. ICASSP Mengyue Wu, Heinrich Dinkel, Kai Yu
2019	J	`jnl`	Audio Caption: Listen and Tell. CoRR Mengyue Wu, Heinrich Dinkel, Kai Yu
2019	A	`conf`	Cross-Domain Replay Spoofing Attack Detection Using Domain Adversarial Training. INTERSPEECH Hongji Wang, Heinrich Dinkel, Shuai Wang, Yanmin Qian, Kai Yu
2019	J	`jnl`	Depa: Self-supervised audio embedding for depression detection. CoRR Heinrich Dinkel, Pingyue Zhang, Mengyue Wu, Kai Yu
2019	J	`jnl`	Duration robust sound event detection. CoRR Heinrich Dinkel, Kai Yu
2019	J	`jnl`	Text-based Depression Detection: What Triggers An Alert. CoRR Heinrich Dinkel, Mengyue Wu, Kai Yu
2019	A	`conf`	The SJTU Robust Anti-Spoofing System for the ASVspoof 2019 Challenge. INTERSPEECH Yexin Yang, Hongji Wang, Heinrich Dinkel, Zhengyang Chen, Shuai Wang, Yanmin Qian, Kai Yu
2019	J	`jnl`	What does a Car-ssette tape tell? CoRR Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu
2018	—	`conf`	Covariance Based Deep Feature for Text-Dependent Speaker Verification. IScIDE Shuai Wang, Heinrich Dinkel, Yanmin Qian, Kai Yu
2018	J	`jnl`	Investigating Raw Wave Deep Neural Networks for End-to-End Speaker Spoofing Detection. IEEE ACM Trans. Audio Speech Lang. Process. Heinrich Dinkel, Yanmin Qian, Kai Yu
2017	J	`jnl`	Deep Feature Engineering for Noise Robust Spoofing Detection. IEEE ACM Trans. Audio Speech Lang. Process. Yanmin Qian, Nanxin Chen, Heinrich Dinkel, Zhizheng Wu
2017	Misc	`conf`	End-to-end spoofing detection with raw waveform CLDNNS. ICASSP Heinrich Dinkel, Nanxin Chen, Yanmin Qian, Kai Yu
2017	B	`conf`	Small-footprint convolutional neural network for spoofing detection. IJCNN Heinrich Dinkel, Yanmin Qian, Kai Yu
2016	—	`conf`	Overview of BTAS 2016 speaker anti-spoofing competition. BTAS Pavel Korshunov, Sébastien Marcel, Hannah Muckenhirn, André R. Gonçalves, A. G. Souza Mello, Ricardo Paranhos Velloso Violato, Flávio Olmos Simões, Mário Uliani Neto, Marcus de Assis Angeloni, José Augusto Stuchi, Heinrich Dinkel, Nanxin Chen, Yanmin Qian, Dipjyoti Paul, Goutam Saha, Md. Sahidullah
2015	A	`conf`	Robust deep feature for spoofing detection - the SJTU system for ASVspoof 2015 challenge. INTERSPEECH Nanxin Chen, Yanmin Qian, Heinrich Dinkel, Bo Chen, Kai Yu