cs.SD语音【1】We Augmented Whisper With kNN and You Won't Believe What Came Next标题：我们用kNN增强耳语，你不会相信接下来会发生什么链接：https://arxiv.org/abs/2410.18850作者：Maya K. Nachesa, Vlad Niculae备注：6 pages incl. appendix, 2 figures, 6 tables 【2】 Wavetable Synthesis Using CVAE for Timbre Control Based on Semantic Label标题：基于语义标签的基于CVAE的音色控制波表合成链接：https://arxiv.org/abs/2410.18628作者：Tsugumasa Yutani, Yuya Yamamoto, Shuyo Nakatani, Hiroko Terasawa备注：6 pages, 4 figures, Accepted at APSIPA ASC 2024 【3】 STTATTS: Unified Speech-To-Text And Text-To-Speech Model标题：STTATTS：统一的语音到文本和文本到语音模型链接：https://arxiv.org/abs/2410.18607作者：Hawau Olamide Toyin, Hao Li, Hanan Aldarmaki备注：11 pages, 4 Figures, EMNLP 2024 Findings 【4】 A contrastive-learning approach for auditory attention detection标题：听觉注意力检测的对比学习方法链接：https://arxiv.org/abs/2410.18395作者：Seyed Ali Alavi Bajestan, Mark Pitt, Donald S. Williamson 【5】 A Unimodal Speaker-Level Membership Inference Detector for Contrastive Pretraining标题：用于对比预训练的单模式说话者级隶属度推断检测器链接：https://arxiv.org/abs/2410.18371作者：Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Shitong Shao, Zhiqiang Wang 【6】 Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model标题：上下文偏置以改善特定领域的自定义词汇音频转录，而无需对Whisper模型进行显式微调链接：https://arxiv.org/abs/2410.18363作者：Vishakha Lall, Yisi Liu 【7】 Unified Microphone Conversion: Many-to-Many Device Mapping via Feature-wise Linear Modulation标题：统一麦克风转换：通过逐流线性调制实现多对多设备映射链接：https://arxiv.org/abs/2410.18322作者：Myeonghoon Ryu, Hongseok Oh, Suji Lee, Han Park备注：Currently under review for ICASSP 2025 【8】 Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches标题：使用基于元音的合奏学习方法从语音中识别稳健且可解释的抑郁症链接：https://arxiv.org/abs/2410.18298作者：Kexin Feng, Theodora Chaspari备注：accepted at the IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI 2024) 【9】 Optimizing the role of human evaluation in LLM-based spoken document summarization systems标题：优化基于LLM的口语文档摘要系统中人工评估的作用链接：https://arxiv.org/abs/2410.18218作者：Margaret Kroll, Kelsey Kraus备注：None 【10】 Melody Construction for Persian lyrics using LSTM recurrent neural networks标题：使用LSTM循环神经网络构建波斯语歌词的旋律链接：https://arxiv.org/abs/2410.18203作者：Farshad Jafari, Farzad Didehvar, Amin Gheibi 【11】 Music102: An $D_{12}$-equivariant transformer for chord progression accompaniment标题：Music 102：用于和弦进行伴奏的$D_{12}$-等变Transformer链接：https://arxiv.org/abs/2410.18151作者：Weiliang Luo备注：10 pages, 3 figures eess.AS音频处理【1】 A Survey on Speech Large Language Models标题：语音大语言模型研究链接：https://arxiv.org/abs/2410.18908作者：Jing Peng, Yucheng Wang, Yu Xi, Xv Li, Kai Yu 【2】 We Augmented Whisper With kNN and You Won't Believe What Came Next标题：我们用kNN增强耳语，你不会相信接下来会发生什么链接：https://arxiv.org/abs/2410.18850作者：Maya K. Nachesa, Vlad Niculae备注：6 pages incl. appendix, 2 figures, 6 tables 【3】 Wavetable Synthesis Using CVAE for Timbre Control Based on Semantic Label标题：基于语义标签的基于CVAE的音色控制波表合成链接：https://arxiv.org/abs/2410.18628作者：Tsugumasa Yutani, Yuya Yamamoto, Shuyo Nakatani, Hiroko Terasawa备注：6 pages, 4 figures, Accepted at APSIPA ASC 2024 【4】 STTATTS: Unified Speech-To-Text And Text-To-Speech Model标题：STTATTS：统一的语音到文本和文本到语音模型链接：https://arxiv.org/abs/2410.18607作者：Hawau Olamide Toyin, Hao Li, Hanan Aldarmaki备注：11 pages, 4 Figures, EMNLP 2024 Findings 【5】 A contrastive-learning approach for auditory attention detection标题：听觉注意力检测的对比学习方法链接：https://arxiv.org/abs/2410.18395作者：Seyed Ali Alavi Bajestan, Mark Pitt, Donald S. Williamson 【6】 A Unimodal Speaker-Level Membership Inference Detector for Contrastive Pretraining标题：用于对比预训练的单模式说话者级隶属度推断检测器链接：https://arxiv.org/abs/2410.18371作者：Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Shitong Shao, Zhiqiang Wang 【7】 Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model标题：上下文偏置以改善特定领域的自定义词汇音频转录，而无需对Whisper模型进行显式微调链接：https://arxiv.org/abs/2410.18363作者：Vishakha Lall, Yisi Liu 【8】 Unified Microphone Conversion: Many-to-Many Device Mapping via Feature-wise Linear Modulation标题：统一麦克风转换：通过逐流线性调制实现多对多设备映射链接：https://arxiv.org/abs/2410.18322作者：Myeonghoon Ryu, Hongseok Oh, Suji Lee, Han Park备注：Currently under review for ICASSP 2025 【9】 Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches标题：使用基于元音的合奏学习方法从语音中识别稳健且可解释的抑郁症链接：https://arxiv.org/abs/2410.18298作者：Kexin Feng, Theodora Chaspari备注：accepted at the IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI 2024)
【10】 Optimizing the role of human evaluation in LLM-based spoken document summarization systems标题：优化基于LLM的口语文档摘要系统中人工评估的作用链接：https://arxiv.org/abs/2410.18218作者：Margaret Kroll, Kelsey Kraus备注：None 【11】 Melody Construction for Persian lyrics using LSTM recurrent neural networks标题：使用LSTM循环神经网络构建波斯语歌词的旋律链接：https://arxiv.org/abs/2410.18203作者：Farshad Jafari, Farzad Didehvar, Amin Gheibi
【12】 Music102: An $D_{12}$-equivariant transformer for chord progression accompaniment标题：Music 102：用于和弦进行伴奏的$D_{12}$-等变Transformer链接：https://arxiv.org/abs/2410.18151作者：Weiliang Luo备注：10 pages, 3 figures 机器翻译由腾讯交互翻译提供，仅供参考
每日语音速递
