今日论文合集：cs.SD语音10篇，eess.AS音频处理10篇。cs.SD语音【1】 CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding标题：CoNeTTE：一种高效的音频字幕系统，通过任务嵌入利用多个数据集链接：https://arxiv.org/abs/2309.00454作者：Étienne Labbé,Thomas Pellegrini,Julien Pinquier机构：IRIT, Universit´e de Toulouse, CNRS, Toulouse INP, UT, Toulouse, France【2】 Towards Contrastive Learning in Music Video Domain标题：浅谈音乐视频领域的对比学习链接：https://arxiv.org/abs/2309.00347作者：Karel Veldkamp,Mariya Hendriksen,Zoltán Szlávik,Alexander Keijser备注：6 pages, 2 figures, 2 tables【3】 Mi-Go: Test Framework which uses YouTube as Data Source for Evaluating Speech Recognition Models like OpenAI's Whisper标题：MI-GO：使用YouTube作为评估语音识别模型(如OpenAI的Whisper)的数据源的测试框架链接：https://arxiv.org/abs/2309.00329作者：Tomasz Wojnar,Jaroslaw Hryszko,Adam Roman机构：Jagiellonian University, Division of Software Engineering, Łojasiewicza ,-, Krakow, Poland备注：25 pages, 9 tables, 3 figures【4】 Enhancing the vocal range of single-speaker singing voice synthesis with melody-unsupervised pre-training标题：用旋律无监督预训练提高单人歌唱嗓音合成的音域链接：https://arxiv.org/abs/2309.00284作者：Shaohuan Zhou,Xu Li,Zhiyong Wu,Ying Shan,Helen Meng机构：Shenzhen International Graduate School, Tsinghua University, Shenzhen, China, ARC Lab, Tencent PCG, The Chinese University of Hong Kong, Hong Kong SAR, China【5】 Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder标题：在流形变编码器中利用动态模块跳跃改进视觉启发关键词检测链接：https://arxiv.org/abs/2309.00140作者：Alexandre Bittar,Paul Dixon,Mohammad Samragh,Kumari Nishu,Devang Naik机构：Apple【6】 QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning标题：QS-TTS：基于矢量量化自监督语音表示学习的半监督文语合成链接：https://arxiv.org/abs/2309.00126作者：Haohan Guo,Fenglong Xie,Jiawen Kang,Yujia Xiao,Xixin Wu,Helen Meng机构：Department of Systems Engineering andEngineering Management, Chinese University of Hong Kong【7】 CPSP: Learning Speech Concepts From Phoneme Supervision标题：CPSP：从音素监督中学习语音概念链接：https://arxiv.org/abs/2309.00424作者：Chunyu Qiang,Hao Li,Yixin Tian,Ruibo Fu,Tao Wang,Longbiao Wang,Jianwu Dang机构：Tianjin University, Tianjin, China, Kuaishou Technology Co., Ltd, Beijing, China, Institute of Automation, Chinese Academy of Sciences, Beijing, China【8】 Remixing-based Unsupervised Source Separation from Scratch标题：基于混合的无监督信源从头开始分离链接：https://arxiv.org/abs/2309.00376作者：Kohei Saijo,Tetsuji Ogawa机构：Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan备注：Interspeech2023, 5pages, 2figures, 2tables【9】 The FruitShell French synthesis system at the Blizzard 2023 Challenge标题：暴雪2023挑战赛中的FruitShell法语合成系统链接：https://arxiv.org/abs/2309.00223作者：Xin Qi,Xiaopeng Wang,Zhiyong Wang,Wang Liu,Mingming Ding,Shuchen Shi机构：ShuchenShi 4 1State Key Laboratory of Multimodal Artificial Intelligence Systems, China 2School of Artificial Intelligence, University of Chinese Academy of Sciences, China 3Anhui Province Key Laboratory of Multimodal Cognitive Computation【10】 RepCodec: A Speech Representation Codec for Speech Tokenization标题：RepCodec：一种用于语音标记化的语音表示编解码器链接：https://arxiv.org/abs/2309.00169作者：Zhichao Huang,Chutong Meng,Tom Ko机构：ByteDanceeess.AS音频处理【1】 CPSP: Learning Speech Concepts From Phoneme Supervision标题：CPSP：从音素监督中学习语音概念链接：https://arxiv.org/abs/2309.00424作者：Chunyu Qiang,Hao Li,Yixin Tian,Ruibo Fu,Tao Wang,Longbiao Wang,Jianwu Dang机构：Tianjin University, Tianjin, China, Kuaishou Technology Co., Ltd, Beijing, China, Institute of Automation, Chinese Academy of Sciences, Beijing, China【2】 Remixing-based Unsupervised Source Separation from Scratch标题：基于混合的无监督信源从头开始分离链接：https://arxiv.org/abs/2309.00376作者：Kohei Saijo,Tetsuji Ogawa机构：Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan备注：Interspeech2023, 5pages, 2figures, 2tables【3】 The FruitShell French synthesis system at the Blizzard 2023 Challenge标题：暴雪2023挑战赛中的FruitShell法语合成系统链接：https://arxiv.org/abs/2309.00223作者：Xin Qi,Xiaopeng Wang,Zhiyong Wang,Wang Liu,Mingming Ding,Shuchen Shi机构：ShuchenShi 4 1State Key Laboratory of Multimodal Artificial Intelligence Systems, China 2School of Artificial Intelligence, University of Chinese Academy of Sciences, China 3Anhui Province Key Laboratory of Multimodal Cognitive Computation【4】 RepCodec: A Speech Representation Codec for Speech Tokenization标题：RepCodec：一种用于语音标记化的语音表示编解码器链接：https://arxiv.org/abs/2309.00169作者：Zhichao Huang,Chutong Meng,Tom Ko机构：ByteDance【5】 CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding标题：CoNeTTE：一种高效的音频字幕系统，通过任务嵌入利用多个数据集链接：https://arxiv.org/abs/2309.00454作者：Étienne Labbé,Thomas Pellegrini,Julien Pinquier机构：IRIT, Universit´e de Toulouse, CNRS, Toulouse INP, UT, Toulouse, France【6】 Towards Contrastive Learning in Music Video Domain标题：浅谈音乐视频领域的对比学习链接：https://arxiv.org/abs/2309.00347作者：Karel Veldkamp,Mariya Hendriksen,Zoltán Szlávik,Alexander Keijser备注：6 pages, 2 figures, 2 tables【7】 Mi-Go: Test Framework which uses YouTube as Data Source for Evaluating Speech Recognition Models like OpenAI's Whisper标题：MI-GO：使用YouTube作为评估语音识别模型(如OpenAI的Whisper)的数据源的测试框架链接：https://arxiv.org/abs/2309.00329作者：Tomasz Wojnar,Jaroslaw Hryszko,Adam Roman机构：Jagiellonian University, Division of Software Engineering, Łojasiewicza ,-, Krakow, Poland备注：25 pages, 9 tables, 3 figures【8】 Enhancing the vocal range of single-speaker singing voice synthesis with melody-unsupervised pre-training标题：用旋律无监督预训练提高单人歌唱嗓音合成的音域链接：https://arxiv.org/abs/2309.00284作者：Shaohuan Zhou,Xu Li,Zhiyong Wu,Ying Shan,Helen Meng机构：Shenzhen International Graduate School, Tsinghua University, Shenzhen, China, ARC Lab, Tencent PCG, The Chinese University of Hong Kong, Hong Kong SAR, China【9】 Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder标题：在流形变编码器中利用动态模块跳跃改进视觉启发关键词检测链接：https://arxiv.org/abs/2309.00140作者：Alexandre Bittar,Paul Dixon,Mohammad Samragh,Kumari Nishu,Devang Naik机构：Apple【10】 QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning标题：QS-TTS：基于矢量量化自监督语音表示学习的半监督文语合成链接：https://arxiv.org/abs/2309.00126作者：Haohan Guo,Fenglong Xie,Jiawen Kang,Yujia Xiao,Xixin Wu,Helen Meng机构：Department of Systems Engineering andEngineering Management, Chinese University of Hong Kong机器翻译，仅供参考
每日语音速递
