- Research Field
-
No content
- Paper Publications more+
- [1] 基于预训练模型的半监督说话人验证系统.清华大学学报(自然科学版),2024,1-8. [2] 面向闽南方言的自监督模型迁移学习.厦门大学学报(自然科学版),2024,63(04):687-693. [3] HQY.THE XMUSPEECH SYSTEM FOR AUDIO-VISUAL TARGET SPEAKER EXTRACTION IN MISP 2023 CHALLENGE<bold> </bo....2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings,39-40. [4] HQY.DYNAMIC LANGUAGE GROUP-BASED MOE: ENHANCING EFFICIENCY AND FLEXIBILITY FOR CODE-SWITCHING SPEECH ....arXiv,2024, [5] HQY,LL,MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis.THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 16,18117-18125. [6] HQY.LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation.arXiv,2024, [7] HQY.IMPROVING MULTI-SPEAKER ASR WITH OVERLAP-AWARE ENCODING AND MONOTONIC ATTENTION.ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,12416-12420. [8] HQY.MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis.Proceedings of the AAAI Conference on Artificial Intelligence,2024,38(16):18117-18125. [9] HQY.COMMUNITY DETECTION GRAPH CONVOLUTIONAL NETWORK FOR OVERLAP-AWARE SPEAKER DIARIZATION.arXiv,2023, [10] HQY.Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge.arXiv,2023,
- Patents
- [1] HQY , 一种基于矫正流模型的高质量语音合成方法 [2] HQY , 一种基于交叉蒸馏的端到端语音识别模型压缩方法 [3] HQY , 低资源语音识别中的一种损失权重自适应元学习方法 [4] HQY , 基于加权有限状态转换器的文本内容添加标点方法 [5] 文本提示型声纹门禁系统 [6] HQY , 一种利用短时时频值的自适应端点检测方法 [7] HQY , 文本提示型声纹门禁系统 [8] HQY , 电话声纹门禁系统
- Published Books
- [1] 洪青阳,李琳,《语音识别：原理与应用》.[Monograph].电子工业出版社,2026
- Research Projects more+
- [1] 端侧ASR的NPU版本研发,在研,深圳鼎信通达股份有限公司,HQY,洪青阳,李琳,黄胡恺,陈培杰,吴炜杰,余洪涌 [2] 语音交互关键技术研究项目,已结题,华为技术有限公司,HQY,余洪涌,洪青阳,童峰,李剑汶,徐文皓,刘凯,雷文钿,郭慧阳,江伟华,周跃海,李琳 [3] 自由场语音交互关键后端技术研究项目,在研,华为技术有限公司,HQY,赵淼,雷文钿,李琳,洪青阳,徐素霞,张宁,曹冬林,余洪涌,刘凯,肖乐,郭慧阳,周健峰,曹秀岭,黎荣晋,颜世江 [4] 闽南语智能语音对话系统,在研,厦门闽韵信息技术有限公司,HQY,雷文钿,洪青阳,肖乐,徐素霞,许彬彬,郭慧阳,张宁,李琳,刘玲燕 [5] 基于图结构建模的说话人日志研究,在研,信息科学部,HQY,洪青阳,李琳,赖丽旻 [6] 端到端语音识别的模型训练与解码优化,已结题,成都鼎桥通信技术有限公司,HQY,洪青阳,李琳,胡文轩,廖德欣,李松,徐素霞,颜婉玲 [7] 闽南话智能语音系统,在研,HQY,洪青阳,李琳,许彬彬,余洪涌,雷文钿,颜世江,陈屹婷,颜婉玲,陈越 [8] 耳内声纹二期项目,在研,华为终端有限公司,HQY,洪青阳,李琳,赵淼,周健峰,江涛,李铮,陆昊,李静,郅艺铭,李松,欧阳贝贝,颜婉玲,余洪涌 [9] 声纹和短词唤醒技术合作项目,已结题,深圳市海思半导体有限公司,HQY,洪青阳,李琳,童峰,曹冬林,余洪涌,雷文钿,徐素霞,赵淼,周健峰,颜世江,夏仕鹏,陈越,颜婉玲 [10] 复杂场景下的说话人特征提取及识别研究,已验收,HQY,洪青阳,李琳,黎荣晋,周健峰,赵淼,颜世江,尚凤仪,肖乐,张宁