@misc{speechmapS01,
  title = {{Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens}},
  author = {Xinsheng Wang and Mingqi Jiang and Ziyang Ma and Ziyu Zhang and Songxiang Liu and Linqin Li and Zheng Liang and Qixi Zheng and Rui Wang and Xiaoqin Feng and Weizhen Bian and Zhen Ye and Sitong Cheng and Ruibin Yuan and Zhixian Zhao and Xinfa Zhu and Jiahao Pan and Liumeng Xue and Pengcheng Zhu and Yunlin Chen and Zhifei Li and Xie Chen and Lei Xie and Yike Guo and Wei Xue},
  year = {2025},
  url = {https://arxiv.org/abs/2503.01710v1},
  note = {Primary source checked 2026-10-26; S01},
  eprint = {2503.01710v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS02,
  title = {{IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech}},
  author = {Siyi Zhou and Yiquan Zhou and Yi He and Xun Zhou and Jinchao Wang and Wei Deng and Jingchen Shu},
  year = {2025},
  url = {https://arxiv.org/abs/2506.21619v2},
  note = {Primary source checked 2026-10-26; S02},
  eprint = {2506.21619v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS03,
  title = {{DisCo-Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec}},
  author = {Tao Li and Wenshuo Ge and Zhichao Wang and Zihao Cui and Yong Ma and Yingying Gao and Chao Deng and Shilei Zhang and Junlan Feng},
  year = {2025},
  url = {https://arxiv.org/abs/2512.13251v3},
  note = {Primary source checked 2026-10-26; S03},
  eprint = {2512.13251v3},
  archivePrefix = {arXiv}
}

@misc{speechmapS04,
  title = {{Fish Audio S2 Technical Report}},
  author = {Shijia Liao and Yuxuan Wang and Songting Liu and Yifan Cheng and Ruoyi Zhang and Tianyu Li and Shidong Li and Yisheng Zheng and Xingwei Liu and Qingzheng Wang and Zhizhuo Zhou and Jiahua Liu and Xin Chen and Dawei Han},
  year = {2026},
  url = {https://arxiv.org/abs/2603.08823v2},
  note = {Primary source checked 2026-10-26; S04},
  eprint = {2603.08823v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS05,
  title = {{FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations}},
  author = {Yoonhyung Lee and Hyunsin Park and Jinhwan Park and Jinkyu Lee},
  year = {2026},
  url = {https://arxiv.org/abs/2605.24618v1},
  note = {Primary source checked 2026-10-26; S05},
  eprint = {2605.24618v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS06,
  title = {{FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation}},
  author = {Feiyu Shen and Fenglong Xie and Junjie Li and Kun Xie and Lei Xie and Xu Tang and Xuelong Geng and Yan Jia and Yao Hu and Yichen Han and Yichen Wu and Ziqi Dai and Junjie Chen and Kai Huang and Manzhen Wei and Yixuan Li},
  year = {2026},
  url = {https://arxiv.org/abs/2608.24168v2},
  note = {Primary source checked 2026-10-26; S06},
  eprint = {2608.24168v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS07,
  title = {{Fish Audio Drama 3 Technical Report}},
  author = {Dawei Han and Shidong Li and Shijia Liao and Jiahua Liu and Songting Liu and Qingzheng Wang and Yuxuan Wang and Xin Chen and Yifan Cheng and Tianyu Li and Gangin Park and Xuehao Yang and Chang Zeng and Haoyang Zhang and Ruoyi Zhang and Xiangyu Zhang},
  year = {2026},
  url = {https://arxiv.org/abs/2610.18010v2},
  note = {Primary source checked 2026-10-26; S07},
  eprint = {2610.18010v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS08,
  title = {{Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling}},
  author = {Zhijie Huang and Stephen McIntosh and Daisuke Saito and Nobuaki Minematsu},
  year = {2026},
  url = {https://arxiv.org/abs/2602.00594v2},
  note = {Primary source checked 2026-10-26; S08},
  eprint = {2602.00594v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS09,
  title = {{Scaling Speech Tokenizers with Diffusion Autoencoders}},
  author = {Yuancheng Wang and Zhenyu Tang and Yun Wang and Arthur Hinsvark and Yingru Liu and Yinghao Li and Kainan Peng and Junyi Ao and Mingbo Ma and Mike Seltzer and Qing He and Xubo Liu},
  year = {2026},
  url = {https://arxiv.org/abs/2602.06602v1},
  note = {Primary source checked 2026-10-26; S09},
  eprint = {2602.06602v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS10,
  title = {{XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs}},
  author = {Yitian Gong and Luozhijie Jin and Kuangwei Chen and Dong Zhang and Ruifan Deng and Xiaogui Yang and Xin Zhang and Zhaoye Fei and Qinyuan Cheng and Shimin Li and Xipeng Qiu},
  year = {2026},
  url = {https://aclanthology.org/2026.acl-long.423/},
  note = {Primary source checked 2026-10-26; S10},
  doi = {10.18653/v1/2026.acl-long.423},
  booktitle = {ACL 2026}
}

@misc{speechmapS11,
  title = {{ReLMCodec: Designing Predictable Speech Tokens from Pre-Quantization Phoneme Structure}},
  author = {Zixiang Wan and Xusheng Yang and Zheng Wang and Peiji Yang},
  year = {2026},
  url = {https://arxiv.org/abs/2608.08286v1},
  note = {Primary source checked 2026-10-26; S11},
  eprint = {2608.08286v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS12,
  title = {{A Comprehensive Study of Content Representations for Speech Synthesis}},
  author = {Diego Torres and Axel Roebel and Nicolas Obin},
  year = {2026},
  url = {https://arxiv.org/abs/2609.30975v1},
  note = {Primary source checked 2026-10-26; S12},
  eprint = {2609.30975v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS13,
  title = {{Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization}},
  author = {Jeeyoung Yun and Seohwan Yun and Sungwoong Kim},
  year = {2026},
  url = {https://arxiv.org/abs/2610.01492v1},
  note = {Primary source checked 2026-10-26; S13},
  eprint = {2610.01492v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS14,
  title = {{Where Does Timbre Hide? Localizing Speaker Information in Speech Signals}},
  author = {Yiquan Zhou and Yixuan Wang and Xiaozhe Qi and Xin Gao and Shihao Li},
  year = {2026},
  url = {https://arxiv.org/abs/2610.29150v1},
  note = {Primary source checked 2026-10-26; S14},
  eprint = {2610.29150v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS15,
  title = {{CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training}},
  author = {Zhihao Du and Changfeng Gao and Yuxuan Wang and Fan Yu and Tianyu Zhao and Hao Wang and Xiang Lv and Hui Wang and Chongjia Ni and Xian Shi and Keyu An and Guanrou Yang and Yabin Li and Yanni Chen and Zhifu Gao and Qian Chen and Yue Gu and Mengzhe Chen and Yafeng Chen and Shiliang Zhang and Wen Wang and Jieping Ye},
  year = {2025},
  url = {https://arxiv.org/abs/2505.17589v2},
  note = {Primary source checked 2026-10-26; S15},
  eprint = {2505.17589v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS16,
  title = {{Qwen3-TTS Technical Report}},
  author = {Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
  year = {2026},
  url = {https://arxiv.org/abs/2601.15621v1},
  note = {Primary source checked 2026-10-26; S16},
  eprint = {2601.15621v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS17,
  title = {{VoxCPM2 Technical Report}},
  author = {Yixuan Zhou and Guoyang Zeng and Xin Liu and Xiang Li and Renjie Yu and Jiancheng Gui and Jiaheng Wu and Ziyang Wang and Xudong Shen and Runchuan Ye and Zhisheng Zhang and Jiuyang Zhou and Bingsong Bai and Weiyue Sun and Mengyuan Deng and Qundong Shi and Zhiyong Wu and Zhiyuan Liu},
  year = {2026},
  url = {https://arxiv.org/abs/2606.06928v1},
  note = {Primary source checked 2026-10-26; S17},
  eprint = {2606.06928v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS18,
  title = {{End-to-End Training for Discrete Token LLM based TTS System}},
  author = {Changfeng Gao and Yong Ren and Jun Yuan and Ye Bai and Zhao You and ShiDong Shang},
  year = {2026},
  url = {https://arxiv.org/abs/2606.09234v1},
  note = {Primary source checked 2026-10-26; S18},
  eprint = {2606.09234v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS19,
  title = {{Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm}},
  author = {Bajian Xiang and Cheng Wen and Han Zhao and Hao Wang and Haoxu Wang and Jiawei Jin and Jiayan Cui and Jie Chen and Mengxi Nie and Tianyu Zhao and Weiqin Li and Xiang Lv and Xiangang Li and Yang Xiang and Yang Zhou},
  year = {2026},
  url = {https://arxiv.org/abs/2607.23938v1},
  note = {Primary source checked 2026-10-26; S19},
  eprint = {2607.23938v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS20,
  title = {{Luna-TTS Family Technical Report}},
  author = {Feng Yin and Shuai Shi and Junjie Zheng and Kechenying Zhou and Yiqiu Wang and Chenyang He and Qiuhua Jiang and Mengxiao Bi and Yanmin Qian and Mingxin Chen and Xun Gong and Tianteng Gu and Bing Han and Peng Jiang and Chenda Li and Haiyang Sun and Han Wang and Wei Wang and Yi Wang and Leying Zhang and Wangyou Zhang and Chushu Zhou},
  year = {2026},
  url = {https://arxiv.org/abs/2608.11593v1},
  note = {Primary source checked 2026-10-26; S20},
  eprint = {2608.11593v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS21,
  title = {{The Evolving Bottleneck in Speech Generation: Interface Co-design and Staged Alignment from CosyVoice to Qwen-Audio-3.0-TTS}},
  author = {Qian Chen and Xiangang Li and Xiang Lv and Han Zhao and Tianyu Zhao},
  year = {2026},
  url = {https://arxiv.org/abs/2609.16514v1},
  note = {Primary source checked 2026-10-26; S21},
  eprint = {2609.16514v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS22,
  title = {{LoCA: Local Credit Assignment for Reinforcement Learning of Autoregressive Flow-Matching TTS}},
  author = {Jie Liu and Junyu Zhou and Junhao Zhong and WeiSen Tang and Rukai Cai and Haoyue Zhan and Ruiqi Xing and Ling Long},
  year = {2026},
  url = {https://arxiv.org/abs/2610.28035v1},
  note = {Primary source checked 2026-10-26; S22},
  eprint = {2610.28035v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS23,
  title = {{MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis}},
  author = {Ziyue Jiang and Yi Ren and Ruiqi Li and Shengpeng Ji and Boyang Zhang and Zhenhui Ye and Chen Zhang and Bai Jionghao and Xiaoda Yang and Jialong Zuo and Yu Zhang and Rui Liu and Xiang Yin and Zhou Zhao},
  year = {2025},
  url = {https://arxiv.org/abs/2502.18924v4},
  note = {Primary source checked 2026-10-26; S23},
  eprint = {2502.18924v4},
  archivePrefix = {arXiv}
}

@misc{speechmapS24,
  title = {{ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching}},
  author = {Han Zhu and Wei Kang and Zengwei Yao and Liyong Guo and Fangjun Kuang and Zhaoqing Li and Weiji Zhuang and Long Lin and Daniel Povey},
  year = {2025},
  url = {https://arxiv.org/abs/2506.13053v3},
  note = {Primary source checked 2026-10-26; S24},
  eprint = {2506.13053v3},
  archivePrefix = {arXiv}
}

@misc{speechmapS25,
  title = {{ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching}},
  author = {Han Zhu and Wei Kang and Liyong Guo and Zengwei Yao and Fangjun Kuang and Weiji Zhuang and Zhaoqing Li and Zhifeng Han and Dong Zhang and Xin Zhang and Xingchen Song and Lingxuan Ye and Long Lin and Daniel Povey},
  year = {2025},
  url = {https://arxiv.org/abs/2507.09318v2},
  note = {Primary source checked 2026-10-26; S25},
  eprint = {2507.09318v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS26,
  title = {{VibeVoice Technical Report}},
  author = {Zhiliang Peng and Jianwei Yu and Wenhui Wang and Yaoyao Chang and Yutao Sun and Li Dong and Yi Zhu and Weijiang Xu and Hangbo Bao and Zehua Wang and Shaohan Huang and Yan Xia and Furu Wei},
  year = {2025},
  url = {https://arxiv.org/abs/2508.19205v1},
  note = {Primary source checked 2026-10-26; S26},
  eprint = {2508.19205v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS27,
  title = {{VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency}},
  author = {Nikita Torgashov and Gustav Eje Henter and Gabriel Skantze},
  year = {2025},
  url = {https://arxiv.org/abs/2509.15969v2},
  note = {Primary source checked 2026-10-26; S27},
  eprint = {2509.15969v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS28,
  title = {{VoXtream2: Full-stream TTS with dynamic speaking rate control}},
  author = {Nikita Torgashov and Gustav Eje Henter and Gabriel Skantze},
  year = {2026},
  url = {https://arxiv.org/abs/2603.13518v1},
  note = {Primary source checked 2026-10-26; S28},
  eprint = {2603.13518v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS29,
  title = {{MOSS-TTS Technical Report}},
  author = {Yitian Gong and Botian Jiang and Yiwei Zhao and Yucheng Yuan and Kuangwei Chen and Yaozhou Jiang and Cheng Chang and Dong Hong and Mingshu Chen and Ruixiao Li and Yiyang Zhang and Yang Gao and Hanfu Chen and Ke Chen and Songlin Wang and Xiaogui Yang and Yuqian Zhang and Kexin Huang and ZhengYuan Lin and Kang Yu and Ziqi Chen and Jin Wang and Zhaoye Fei and Qinyuan Cheng and Shimin Li and Xipeng Qiu},
  year = {2026},
  url = {https://arxiv.org/abs/2603.18090v2},
  note = {Primary source checked 2026-10-26; S29},
  eprint = {2603.18090v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS30,
  title = {{Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios}},
  author = {Changhao Pan and Rui Yang and Han Wang and Zhuan Zhou and Xuming He and Wenxiang Guo and Ziyue Jiang and Ruiqi Li and Yu Zhang and Chenyuhao Wen and Ke Lei and Xiang Yin and Jingyu Lu and Zhiyuan Zhu and Zhou Zhao},
  year = {2026},
  url = {https://arxiv.org/abs/2605.28618v1},
  note = {Primary source checked 2026-10-26; S30},
  eprint = {2605.28618v1},
  archivePrefix = {arXiv}
}

@misc{speechmapS31,
  title = {{TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context}},
  author = {Fritz Cremer and Jonathan Cremer},
  year = {2026},
  url = {https://arxiv.org/abs/2609.08703v2},
  note = {Primary source checked 2026-10-26; S31},
  eprint = {2609.08703v2},
  archivePrefix = {arXiv}
}

@misc{speechmapS32,
  title = {{StreamAlign: Streaming Text-Aligned Speech Tokenization}},
  author = {Kang-wook Kim and Jinyoung Park and Jinsoo Kim and Sehun Lee and Sang Hoon Woo and Gunhee Kim},
  year = {2026},
  url = {https://arxiv.org/abs/2609.09719v1},
  note = {Primary source checked 2026-10-26; S32},
  eprint = {2609.09719v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD01,
  title = {{ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech}},
  author = {Xin Wang and Héctor Delgado and Hemlata Tak and Jee-weon Jung and Hye-jin Shim and Massimiliano Todisco and Ivan Kukanov and Xuechen Liu and Md Sahidullah and Tomi Kinnunen and Nicholas Evans and Kong Aik Lee and Junichi Yamagishi and Myeonghun Jeong and Ge Zhu and Yongyi Zang and You Zhang and Soumi Maiti and Florian Lux and Nicolas Müller and Wangyou Zhang and Chengzhe Sun and Shuwei Hou and Siwei Lyu and Sébastien Le Maguer and Cheng Gong and Hanjie Guo and Liping Chen and Vishwanath Singh},
  year = {2025},
  url = {https://arxiv.org/abs/2502.08857v4},
  note = {Primary source checked 2026-10-26; D01},
  eprint = {2502.08857v4},
  archivePrefix = {arXiv}
}

@misc{speechmapD02,
  title = {{AUDDT: A Unified Benchmark Toolkit for Audio and Speech Deepfake Detectors}},
  author = {Yi Zhu and Heitor R. Guimarães and Arthur Pimentel and Tiago Falk},
  year = {2025},
  url = {https://arxiv.org/abs/2509.21597v2},
  note = {Primary source checked 2026-10-26; D02},
  eprint = {2509.21597v2},
  archivePrefix = {arXiv}
}

@misc{speechmapD03,
  title = {{TwinShift: Benchmarking Audio Deepfake Detection across Synthesizer and Speaker Shifts}},
  author = {Jiyoung Hong and Yoonseo Chung and Seungyeon Oh and Juntae Kim and Jiyoung Lee and Sookyung Kim and Hyunsoo Cho},
  year = {2025},
  url = {https://arxiv.org/abs/2510.23096v1},
  note = {Primary source checked 2026-10-26; D03},
  eprint = {2510.23096v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD04,
  title = {{ASVspoof 5: Evaluation of Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech}},
  author = {Xin Wang and Héctor Delgado and Nicholas Evans and Xuechen Liu and Tomi Kinnunen and Hemlata Tak and Kong Aik Lee and Ivan Kukanov and Md Sahidullah and Massimiliano Todisco and Junichi Yamagishi},
  year = {2026},
  url = {https://arxiv.org/abs/2601.03944v3},
  note = {Primary source checked 2026-10-26; D04},
  eprint = {2601.03944v3},
  archivePrefix = {arXiv}
}

@misc{speechmapD05,
  title = {{A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection}},
  author = {Hashim Ali and Nithin Sai Adupa and Surya Subramani and Hafiz Malik},
  year = {2026},
  url = {https://arxiv.org/abs/2603.01482v1},
  note = {Primary source checked 2026-10-26; D05},
  eprint = {2603.01482v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD06,
  title = {{When Spoof Detectors Travel: Evaluation Across 66 Languages in the Low-Resource Language Spoofing Corpus}},
  author = {Kirill Borodin and Vasiliy Kudryavtsev and Maxim Maslov and Mikhail Gorodnichev and Grach Mkrtchian},
  year = {2026},
  url = {https://arxiv.org/abs/2603.02364v4},
  note = {Primary source checked 2026-10-26; D06},
  eprint = {2603.02364v4},
  archivePrefix = {arXiv}
}

@misc{speechmapD07,
  title = {{Generalizable Detection of Audio Deepfakes}},
  author = {Jose A. Lopez and Georg Stemmer and Héctor Cordourier Maruri},
  year = {2025},
  url = {https://arxiv.org/abs/2507.01750v1},
  note = {Primary source checked 2026-10-26; D07},
  eprint = {2507.01750v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD08,
  title = {{Continual Audio Deepfake Detection via Universal Adversarial Perturbation}},
  author = {Wangjie Li and Lin Li and Qingyang Hong},
  year = {2025},
  url = {https://arxiv.org/abs/2511.19974v1},
  note = {Primary source checked 2026-10-26; D08},
  eprint = {2511.19974v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD09,
  title = {{Audio Deepfake Detection in the Age of Advanced Text-to-Speech models}},
  author = {Robin Singh and Aditya Yogesh Nair and Fabio Palumbo and Florian Barbaro and Anna Dyka and Lohith Rachakonda},
  year = {2026},
  url = {https://arxiv.org/abs/2601.20510v1},
  note = {Primary source checked 2026-10-26; D09},
  eprint = {2601.20510v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD10,
  title = {{CoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection}},
  author = {Kunyu Feng and Yuxiang Wang and Li Wang and Wan Lin and Zhizheng Wu},
  year = {2026},
  url = {https://arxiv.org/abs/2609.19818v3},
  note = {Primary source checked 2026-10-26; D10},
  eprint = {2609.19818v3},
  archivePrefix = {arXiv}
}

@misc{speechmapD11,
  title = {{Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection}},
  author = {Yuankun Xie and Xiaoxuan Guo and Xiaopeng Wang and Siqing Qin and Shaole Li and Kong Aik Lee},
  year = {2026},
  url = {https://arxiv.org/abs/2609.37586v1},
  note = {Primary source checked 2026-10-26; D11},
  eprint = {2609.37586v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD12,
  title = {{Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection}},
  author = {Miao He and Peng Cheng and Zhongjie Ba and Qing Wen and Li Lu and Xin Yang and Kui Ren},
  year = {2026},
  url = {https://arxiv.org/abs/2610.05264v1},
  note = {Primary source checked 2026-10-26; D12},
  eprint = {2610.05264v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD13,
  title = {{Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection}},
  author = {Jianqiao Cui and Haoxian Zhu and Hanbiao Meng and Yanghao Zhang},
  year = {2026},
  url = {https://arxiv.org/abs/2610.16049v1},
  note = {Primary source checked 2026-10-26; D13},
  eprint = {2610.16049v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD14,
  title = {{PartialEdit: Identifying Partial Deepfakes in the Era of Neural Speech Editing}},
  author = {You Zhang and Baotong Tian and Lin Zhang and Zhiyao Duan},
  year = {2025},
  url = {https://www.isca-archive.org/interspeech_2025/zhang25g_interspeech.html},
  note = {Primary source checked 2026-10-26; D14}
}

@misc{speechmapD15,
  title = {{Split and Conquer Partial Deepfake Speech}},
  author = {Inbal Rimon and Oren Gal and Haim Permuter},
  year = {2026},
  url = {https://arxiv.org/abs/2604.02913v1},
  note = {Primary source checked 2026-10-26; D15},
  eprint = {2604.02913v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD16,
  title = {{Half-Truth Audio Detection and Localisation: A Lightweight Cross-Attentive Architecture and a Cross-Corpus Diagnostic Study}},
  author = {S. Sutharya and Remya K. Sasi},
  year = {2026},
  url = {https://arxiv.org/abs/2605.29531v3},
  note = {Primary source checked 2026-10-26; D16},
  eprint = {2605.29531v3},
  archivePrefix = {arXiv}
}

@misc{speechmapD17,
  title = {{What Do Deepfake Speech Detectors Actually Hear?}},
  author = {Vojtěch Staněk and Veronika Jirmusová and Anton Firc and Kamil Malinka and Jakub Reš and Martin Perešíni},
  year = {2026},
  url = {https://arxiv.org/abs/2606.10912v1},
  note = {Primary source checked 2026-10-26; D17},
  eprint = {2606.10912v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD18,
  title = {{Zero-Shot Temporal Localisation of Audio Deepfakes in Multi-Speaker Conversations}},
  author = {Soumyadeep Roy},
  year = {2026},
  url = {https://arxiv.org/abs/2609.10051v1},
  note = {Primary source checked 2026-10-26; D18},
  eprint = {2609.10051v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD19,
  title = {{SoK: How Robust is Audio Watermarking in Generative AI models?}},
  author = {Yizhu Wen and Ashwin Innuganti and Aaron Bien Ramos and Hanqing Guo and Qiben Yan},
  year = {2025},
  url = {https://arxiv.org/abs/2503.19176v2},
  note = {Primary source checked 2026-10-26; D19},
  eprint = {2503.19176v2},
  archivePrefix = {arXiv}
}

@misc{speechmapD20,
  title = {{RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations}},
  author = {Hieu-Thi Luong and Xuechen Liu and Ivan Kukanov and Zheng Xin Chai and Kong Aik Lee},
  year = {2026},
  url = {https://arxiv.org/abs/2605.09568v3},
  note = {Primary source checked 2026-10-26; D20},
  eprint = {2605.09568v3},
  archivePrefix = {arXiv}
}

@misc{speechmapD21,
  title = {{MixFake: Benchmarking and Enhancing Audio Deepfake Detection in Diverse Real-world Mixed Audio}},
  author = {Qingcao Li and Yipeng Lin and Weichen Lian and Zhongjie Ba and Peng Cheng and Zhichao Lian},
  year = {2026},
  url = {https://arxiv.org/abs/2605.23201v2},
  note = {Primary source checked 2026-10-26; D21},
  eprint = {2605.23201v2},
  archivePrefix = {arXiv}
}

@misc{speechmapD22,
  title = {{Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors}},
  author = {Nicolas M. Müller and Aditya Tirumala Bukkapatnam and Zohaib Ahmed},
  year = {2026},
  url = {https://arxiv.org/abs/2606.29544v1},
  note = {Primary source checked 2026-10-26; D22},
  eprint = {2606.29544v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD23,
  title = {{AffectDF: The Most Comprehensive Benchmark for Speech Deepfake Detection against Emotionally Expressive Attacks}},
  author = {Aurosweta Mahapatra and Xiutian Zhao and Shreeram Suresh Chandra and Zihan Zhang and Zongyang Du and Ismail Rasim Ulgen and Kong Aik Lee and Nicholas Andrews and Carlos Busso and Berrak Sisman},
  year = {2026},
  url = {https://arxiv.org/abs/2608.05507v1},
  note = {Primary source checked 2026-10-26; D23},
  eprint = {2608.05507v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD24,
  title = {{AT-ADD: A Benchmark and Challenge for Robust and All-Type Audio Deepfake Detection}},
  author = {Yuankun Xie and Haonan Cheng and Jiayi Zhou and Xiaoxuan Guo and Tao Wang and Changhao Zhang and Jian Liu and Weiqiang Wang and Ruibo Fu and Xiaopeng Wang and Hengyan Huang and Xiaoying Huang and Long Ye and Guangtao Zhai and Kong Aik Lee},
  year = {2026},
  url = {https://arxiv.org/abs/2608.23437v2},
  note = {Primary source checked 2026-10-26; D24},
  eprint = {2608.23437v2},
  archivePrefix = {arXiv}
}

@misc{speechmapD25,
  title = {{On the Robustness of Audio Deepfake Detection under Audio Watermarking}},
  author = {Zi Qian Yong and Ajinkya Kulkarni and Julia Lau and Hwa Hui Tew and Shu Min Leong and Raphael Phan and Sébastien Marcel},
  year = {2026},
  url = {https://arxiv.org/abs/2608.24159v1},
  note = {Primary source checked 2026-10-26; D25},
  eprint = {2608.24159v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD26,
  title = {{GenTraceBench: A Benchmark for Tracing Audio Deepfakes Across Pre- and Post-training Stages}},
  author = {Li Wang and Kunyu Feng and Wan Lin and Dekun Chen and Qinke Ni and Xueyao Zhang and Lei Wang and Jie Shi and Haizhou Li and Zhizheng Wu},
  year = {2026},
  url = {https://arxiv.org/abs/2609.21738v1},
  note = {Primary source checked 2026-10-26; D26},
  eprint = {2609.21738v1},
  archivePrefix = {arXiv}
}

@misc{speechmapD27,
  title = {{Detection-Guided Adaptive Purification with Diffusion Models for Robust Audio Deepfake Detection}},
  author = {Muhammed Salih Kayhan and Qiben Yan},
  year = {2026},
  url = {https://arxiv.org/abs/2610.10752v1},
  note = {Primary source checked 2026-10-26; D27},
  eprint = {2610.10752v1},
  archivePrefix = {arXiv}
}