{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T22:06:14Z","timestamp":1779228374673,"version":"3.51.4"},"reference-count":138,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009023","name":"Precursory Research for Embryonic Science and Technology","doi-asserted-by":"publisher","award":["JPMJPR23P9"],"award-info":[{"award-number":["JPMJPR23P9"]}],"id":[{"id":"10.13039\/501100009023","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007175","name":"Conseil National de la Recherche Scientifique","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007175","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.csl.2026.101988","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T08:27:06Z","timestamp":1775896026000},"page":"101988","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["The third VoicePrivacy challenge: Preserving emotional expressiveness and linguistic content in voice anonymization"],"prefix":"10.1016","volume":"100","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7125-2382","authenticated-orcid":false,"given":"Natalia","family":"Tomashenko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6645-6524","authenticated-orcid":false,"given":"Xiaoxiao","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1225-7957","authenticated-orcid":false,"given":"Pierre","family":"Champion","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1117-4783","authenticated-orcid":false,"given":"Sarina","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4154-5460","authenticated-orcid":false,"given":"Michele","family":"Panariello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8246-0606","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-1041","authenticated-orcid":false,"given":"Nicholas","family":"Evans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0183-7289","authenticated-orcid":false,"given":"Emmanuel","family":"Vincent","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2883-0324","authenticated-orcid":false,"given":"Massimiliano","family":"Todisco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2026.101988_b1","article-title":"Investigating voice conversion architecture with different bottleneck features for the voice privacy challenge 2024","author":"Akti","year":"2024","journal-title":"VoicePrivacy 2024 Chall."},{"key":"10.1016\/j.csl.2026.101988_b2","doi-asserted-by":"crossref","unstructured":"Akti, S., Nguyen, T.N., Liu, Y., Waibel, A., 2024b. Voice Privacy-Investigating Voice Conversion Architecture with Different Bottleneck Features. In: Proc. SPSC 2024.","DOI":"10.21437\/SPSC.2024-8"},{"key":"10.1016\/j.csl.2026.101988_b3","unstructured":"Ardila, R., Branson, M., Davis, K., Henretty, M., Kohler, M., Meyer, J., Morais, R., Saunders, L., Tyers, F.M., Weber, G., 2020. Common Voice: A Massively-Multilingual Speech Corpus. In: 12th Language Resources and Evaluation Conference. LREC, pp. 4218\u20134222."},{"key":"10.1016\/j.csl.2026.101988_b4","unstructured":"Arjovsky, M., Chintala, S., Bottou, L., 2017. Wasserstein generative adversarial networks. In: International Conference on Machine Learning. ICML, pp. 214\u2013223."},{"key":"10.1016\/j.csl.2026.101988_b5","series-title":"Opinion 05\/2014 on anonymisation techniques","author":"Article 29 Working Party","year":"2014"},{"key":"10.1016\/j.csl.2026.101988_b6","series-title":"Voice conversion with just nearest neighbors","author":"Baas","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b7","series-title":"XLS-R: Self-supervised cross-lingual speech representation learning at scale","author":"Babu","year":"2021"},{"key":"10.1016\/j.csl.2026.101988_b8","series-title":"Privacy disclosure of similarity rank in speech and language processing","author":"B\u00e4ckstr\u00f6m","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b9","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.csl.2026.101988_b10","series-title":"5th Symposium on Security and Privacy in Speech Communication","first-page":"35","article-title":"The influence of non-timbral cues in voice anonymisation and evaluation","author":"Bakari","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b11","series-title":"Proceedings of Odyssey 2004: The Speaker and Language Recognition Workshop","article-title":"A statistical significance test for person authentication","author":"Bengio","year":"2004"},{"key":"10.1016\/j.csl.2026.101988_b12","unstructured":"Bogdanov, D., Won, M., Tovstogan, P., Porter, A., Serra, X., 2019. The MTG-Jamendo Dataset for Automatic Music Tagging. In: ICML 2019 Machine Learning for Music Discovery Workshop."},{"key":"10.1016\/j.csl.2026.101988_b13","series-title":"AudioLM: a language modeling approach to audio generation","author":"Borsos","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b14","first-page":"1517","article-title":"A database of German emotional speech","volume":"vol. 5","author":"Burkhardt","year":"2005"},{"key":"10.1016\/j.csl.2026.101988_b15","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"J. Lang. Resour. Eval."},{"key":"10.1016\/j.csl.2026.101988_b16","series-title":"Proc. SLT","first-page":"409","article-title":"Privacy versus emotion preservation trade-offs in emotion-preserving speaker anonymization","author":"Cai","year":"2024"},{"issue":"4","key":"10.1016\/j.csl.2026.101988_b17","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","article-title":"Crema-d: Crowd-sourced emotional multimodal actors dataset","volume":"5","author":"Cao","year":"2014","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.csl.2026.101988_b18","series-title":"Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques","author":"Champion","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b19","series-title":"Voice anonymisation evaluation using similarity rank disclosure","author":"Chandra","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b20","doi-asserted-by":"crossref","DOI":"10.1109\/TIFS.2025.3592553","article-title":"Any-to-any speaker attribute perturbation for asynchronous voice anonymization","author":"Chen","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"6","key":"10.1016\/j.csl.2026.101988_b21","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.csl.2026.101988_b22","series-title":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","first-page":"103","article-title":"On the properties of neural machine translation: Encoder\u2013decoder approaches","author":"Cho","year":"2014"},{"key":"10.1016\/j.csl.2026.101988_b23","series-title":"2024 IEEE Spoken Language Technology Workshop","first-page":"502","article-title":"Embracing ambiguity and subjectivity using the all-inclusive aggregation rule for evaluating multi-label speech emotion recognition systems","author":"Chou","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b24","doi-asserted-by":"crossref","unstructured":"Chouchane, O., Busch, C., Galdi, C., Evans, N., Todisco, M., 2024. A Comparison of Differential Performance Metrics for the Evaluation of Automatic Speaker Verification Fairness. In: Proc. Odyssey 2024. pp. 209\u2013216.","DOI":"10.21437\/odyssey.2024-30"},{"key":"10.1016\/j.csl.2026.101988_b25","series-title":"Interspeech","first-page":"1086","article-title":"VoxCeleb2: Deep speaker recognition","author":"Chung","year":"2018"},{"key":"10.1016\/j.csl.2026.101988_b26","series-title":"2021 IEEE Automatic Speech Recognition and Understanding Workshop","first-page":"244","article-title":"W2v-BERT: Combining contrastive learning and masked language modeling for self-supervised speech pre-training","author":"Chung","year":"2021"},{"key":"10.1016\/j.csl.2026.101988_b27","series-title":"The VoicePrivacy 2024 Challenge","article-title":"System description for Voice Privacy challenge 2024","author":"Das","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b28","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.csl.2026.101988_b29","unstructured":"Deng, J., Teng, F., Chen, Y., Chen, X., Wang, Z., Xu, W., 2023. {V-Cloak}: Intelligibility-, naturalness-& {Timbre-Preserving}{Real-Time} voice anonymization. In: 32nd USENIX Security Symposium (USENIX Security 23). pp. 5181\u20135198."},{"key":"10.1016\/j.csl.2026.101988_b30","series-title":"Interspeech","first-page":"3830","article-title":"ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification","author":"Desplanques","year":"2020"},{"key":"10.1016\/j.csl.2026.101988_b31","doi-asserted-by":"crossref","unstructured":"Dubey, H., Gopal, V., Cutler, R., Aazami, A., Matusevych, S., Braun, S., Eskimez, S.E., Thakker, M., Yoshioka, T., Gamper, H., Aichner, R., 2022. ICASSP 2022 Deep Noise Suppression Challenge. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 9271\u20139275.","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"10.1016\/j.csl.2026.101988_b32","series-title":"Proceedings of the 18th ACM International Conference on Multimedia","first-page":"1459","article-title":"Opensmile: the munich versatile and fast open-source audio feature extractor","author":"Eyben","year":"2010"},{"key":"10.1016\/j.csl.2026.101988_b33","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1109\/TASLP.2021.3133208","article-title":"FSD50k: An open dataset of human-labeled sound events","volume":"30","author":"Fonseca","year":"2022","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.csl.2026.101988_b34","doi-asserted-by":"crossref","unstructured":"Franzreb, C., Das, A., Polzehl, T., M\u00f6ller, S., 2025. Private kNN-VC: Interpretable Anonymization of Converted Speech. In: Proc. Interspeech.","DOI":"10.21437\/Interspeech.2025-820"},{"issue":"1","key":"10.1016\/j.csl.2026.101988_b35","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TBIOM.2021.3102862","article-title":"Fairness in biometrics: a figure of merit to assess biometric verification systems","volume":"4","author":"Freitas Pereira","year":"2021","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"10.1016\/j.csl.2026.101988_b36","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"Gemmeke","year":"2017"},{"key":"10.1016\/j.csl.2026.101988_b37","series-title":"Interspeech 2023","first-page":"1209","article-title":"MMER: Multimodal multi-task learning for speech emotion recognition","author":"Ghosh","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b38","series-title":"USTC-PolyU system for the VoicePrivacy 2024 challenge","author":"Gu","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b39","unstructured":"Haq, S., Jackson, P.J., Edge, J., 2009. Speaker-dependent audio-visual emotion recognition. In: International Conference on Auditory-Visual Speech Processing. AVSP, pp. 53\u201358."},{"key":"10.1016\/j.csl.2026.101988_b40","article-title":"FaCodec-based anonymization solution enhanced with prosody anonymization","author":"He","year":"2024","journal-title":"VoicePrivacy 2024 Chall."},{"key":"10.1016\/j.csl.2026.101988_b41","series-title":"International Conference on Pattern Recognition","first-page":"431","article-title":"Evaluating proposed fairness models for face recognition algorithms","author":"Howard","year":"2022"},{"key":"10.1016\/j.csl.2026.101988_b42","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.csl.2026.101988_b43","doi-asserted-by":"crossref","unstructured":"Hua, H., Shang, Z., Li, X., Shi, P., Yang, C., Wang, L., Zhang, P., 2024. Emotional Speech Anonymization: Preserving Emotion Characteristics in Pseudo-speaker Speech Generation. In: Proc. SPSC 2024. pp. 55\u201360.","DOI":"10.21437\/SPSC.2024-10"},{"key":"10.1016\/j.csl.2026.101988_b44","series-title":"SecureSpeech: Prompt-based speaker and content protection","author":"Hui","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b45","series-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"10.1016\/j.csl.2026.101988_b46","series-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b47","doi-asserted-by":"crossref","unstructured":"Kahn, J., Rivi\u00e8re, M., Zheng, W., Kharitonov, E., Xu, Q., Mazar\u00e9, P.-E., Karadayi, J., Liptchinsky, V., Collobert, R., Fuegen, C., Likhomanenko, T., Synnaeve, G., Joulin, A., Mohamed, A., Dupoux, E., 2020. Libri-light: A benchmark for ASR with limited or no supervision. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 7669\u20137673.","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"10.1016\/j.csl.2026.101988_b48","first-page":"I","article-title":"Yet another algorithm for pitch tracking","volume":"vol. 1","author":"Kasi","year":"2002"},{"key":"10.1016\/j.csl.2026.101988_b49","unstructured":"Kim, J., Kong, J., Son, J., 2021. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In: International Conference on Machine Learning. ICML, pp. 5530\u20135540."},{"key":"10.1016\/j.csl.2026.101988_b50","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Seltzer, M.L., Khudanpur, S., 2017. A study on data augmentation of reverberant speech for robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 5220\u20135224.","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"10.1016\/j.csl.2026.101988_b51","first-page":"17022","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.csl.2026.101988_b52","series-title":"Interspeech 2025","first-page":"2810","article-title":"Children\u2019s Voice Privacy: First Steps and Emerging Challenges","author":"Kulkarni","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b53","series-title":"NTU-NPU system for Voice Privacy 2024 challenge","author":"Kuzmin","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b54","article-title":"Orange SHIVA system description for the Voice Privacy challenge 2024","author":"Le Blouch","year":"2024","journal-title":"VoicePrivacy 2024 Chall."},{"key":"10.1016\/j.csl.2026.101988_b55","doi-asserted-by":"crossref","unstructured":"Le Blouch, O., Bakari, R., Gengembre, N., 2024b. Tuning DISSC for Voice Privacy Challenge 2024. In: Proc. SPSC 2024.","DOI":"10.21437\/SPSC.2024-18"},{"key":"10.1016\/j.csl.2026.101988_b56","article-title":"Exploring vector-quantized variational auto-encoder with prosody parameters for speaker anonymization","author":"Leang","year":"2024","journal-title":"VoicePrivacy 2024 Chall."},{"key":"10.1016\/j.csl.2026.101988_b57","article-title":"System description for Voice Privacy Challenge 2024","author":"Lee","year":"2024","journal-title":"VoicePrivacy 2024 Chall."},{"key":"10.1016\/j.csl.2026.101988_b58","doi-asserted-by":"crossref","unstructured":"Lee, J., Park, T., You, Y., 2024b. Voice Anonymization Using Emotion-Enriched Feature Integration with STT and TTS Models. In: Proc. SPSC 2024. pp. 50\u201354.","DOI":"10.21437\/SPSC.2024-9"},{"key":"10.1016\/j.csl.2026.101988_b59","series-title":"Proc. ICASSP","first-page":"1","article-title":"FreeVC: Towards high-quality text-free one-shot voice conversion","author":"Li","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b60","article-title":"Emotion-enhanced speaker anonymisation using the FreeVC framework","author":"Li","year":"2024","journal-title":"VoicePrivacy 2024 Chall."},{"issue":"5","key":"10.1016\/j.csl.2026.101988_b61","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196391","article-title":"The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English","volume":"13","author":"Livingstone","year":"2018","journal-title":"PLoS One"},{"issue":"4","key":"10.1016\/j.csl.2026.101988_b62","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1109\/TAFFC.2017.2736999","article-title":"Building naturalistic emotionally balanced speech corpus by retrieving emotional speech from existing podcast recordings","volume":"10","author":"Lotfian","year":"2019","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.csl.2026.101988_b63","doi-asserted-by":"crossref","unstructured":"Lux, F., Koch, J., Schweitzer, A., Vu, N.T., 2021. The IMS Toucan system for the Blizzard Challenge 2021. In: Blizzard Challenge Workshop.","DOI":"10.21437\/Blizzard.2021-2"},{"key":"10.1016\/j.csl.2026.101988_b64","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"8048","article-title":"Speaking style conversion in the waveform domain using discrete self-supervised units","author":"Maimon","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b65","series-title":"Speaking style conversion in the waveform domain using discrete self-supervised units","author":"Maimon","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b66","series-title":"Spectral fusion, spectral parsing and the formation of the auditory image","author":"McAdams","year":"1984"},{"key":"10.1016\/j.csl.2026.101988_b67","article-title":"First steps towards voice anonymization for code-switching speech","author":"Meyer","year":"2025","journal-title":"Proc. Interspeech"},{"key":"10.1016\/j.csl.2026.101988_b68","doi-asserted-by":"crossref","unstructured":"Meyer, S., Lux, F., Koch, J., Denisov, P., Tilli, P., Vu, N.T., 2023a. Prosody Is Not Identity: A Speaker Anonymization Approach Using Prosody Cloning. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10096607"},{"key":"10.1016\/j.csl.2026.101988_b69","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2024-1615","article-title":"Probing the feasibility of multilingual speaker anonymization","author":"Meyer","year":"2024","journal-title":"Accept. By Interspeech 2024"},{"key":"10.1016\/j.csl.2026.101988_b70","article-title":"VoicePAT: An efficient open-source evaluation toolkit for voice privacy research","author":"Meyer","year":"2023","journal-title":"IEEE Open J. Signal Process."},{"key":"10.1016\/j.csl.2026.101988_b71","doi-asserted-by":"crossref","unstructured":"Meyer, S., Tilli, P., Denisov, P., Lux, F., Koch, J., Vu, N.T., 2023c. Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy. In: IEEE Spoken Language Technology Workshop. SLT, pp. 912\u2013919.","DOI":"10.1109\/SLT54892.2023.10022601"},{"key":"10.1016\/j.csl.2026.101988_b72","doi-asserted-by":"crossref","first-page":"3819","DOI":"10.1109\/TIFS.2025.3556345","article-title":"A benchmark for multi-speaker anonymization","volume":"20","author":"Miao","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.csl.2026.101988_b73","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"11421","article-title":"SynVox2: Towards a privacy-friendly VoxCeleb2 dataset","author":"Miao","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b74","doi-asserted-by":"crossref","unstructured":"Miao, X., Wang, X., Cooper, E., Yamagishi, J., Tomashenko, N., 2022a. Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditions. In: Proc. Interspeech 2022. pp. 4426\u20134430.","DOI":"10.21437\/Interspeech.2022-11065"},{"key":"10.1016\/j.csl.2026.101988_b75","series-title":"Language-independent speaker anonymization approach using self-supervised pre-trained models","author":"Miao","year":"2022"},{"key":"10.1016\/j.csl.2026.101988_b76","doi-asserted-by":"crossref","first-page":"3681","DOI":"10.1109\/TASLP.2023.3313429","article-title":"Speaker anonymization using orthogonal Householder neural network","volume":"31","author":"Miao","year":"2023","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.csl.2026.101988_b77","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2025.101810","article-title":"Adapting general disentanglement-based speaker anonymization for enhanced emotion preservation","author":"Miao","year":"2025","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101988_b78","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.csl.2019.06.001","article-title":"Preserving privacy in speaker and speech characterisation","volume":"58","author":"Nautsch","year":"2019","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101988_b79","series-title":"Interspeech","first-page":"1698","article-title":"The Privacy ZEBRA: Zero evidence biometric recognition assessment","author":"Nautsch","year":"2020"},{"key":"10.1016\/j.csl.2026.101988_b80","series-title":"Interspeech","first-page":"1718","article-title":"Speech pseudonymisation assessment using voice similarity matrices","author":"No\u00e9","year":"2020"},{"key":"10.1016\/j.csl.2026.101988_b81","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2021.101299","article-title":"Towards a unified assessment framework of speech pseudonymisation","volume":"72","author":"No\u00e9","year":"2022","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101988_b82","series-title":"Interspeech","first-page":"3580","article-title":"Anonymous speaker clusters: Making distinctions between anonymised speech recordings with clustering interface","author":"O\u2019Brien","year":"2021"},{"key":"10.1016\/j.csl.2026.101988_b83","article-title":"The risks and detection of overestimated privacy protection in voice anonymisation","author":"Panariello","year":"2025","journal-title":"SPSC 2025"},{"key":"10.1016\/j.csl.2026.101988_b84","doi-asserted-by":"crossref","unstructured":"Panariello, M., Nespoli, F., Todisco, M., Evans, N., 2024a. Speaker anonymization using neural audio codec language models. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 4725\u20134729.","DOI":"10.1109\/ICASSP48485.2024.10447871"},{"key":"10.1016\/j.csl.2026.101988_b85","doi-asserted-by":"crossref","first-page":"3477","DOI":"10.1109\/TASLP.2024.3430530","article-title":"The VoicePrivacy 2022 challenge: Progress and perspectives in voice anonymisation","volume":"32","author":"Panariello","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.csl.2026.101988_b86","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S., 2015. LibriSpeech: an ASR corpus based on public domain audio books. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 5206\u20135210.","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"10.1016\/j.csl.2026.101988_b87","doi-asserted-by":"crossref","unstructured":"Pappagari, R., Wang, T., Villalba, J., Chen, N., Dehak, N., 2020. X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 7169\u20137173.","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"10.1016\/j.csl.2026.101988_b88","series-title":"Interspeech","first-page":"1099","article-title":"Speaker anonymisation using the McAdams coefficient","author":"Patino","year":"2021"},{"key":"10.1016\/j.csl.2026.101988_b89","unstructured":"Peng, Y., Dalmia, S., Lane, I., Watanabe, S., 2022. Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding. In: International Conference on Machine Learning. ICML, pp. 17627\u201317643."},{"key":"10.1016\/j.csl.2026.101988_b90","series-title":"Interspeech","first-page":"3743","article-title":"Semi-orthogonal low-rank matrix factorization for deep neural networks.","author":"Povey","year":"2018"},{"key":"10.1016\/j.csl.2026.101988_b91","doi-asserted-by":"crossref","unstructured":"Qian, J., Han, F., Hou, J., Zhang, C., Wang, Y., Li, X.-Y., 2018. Towards privacy-preserving speech data publishing. In: IEEE Conference on Computer Communications. INFOCOM, pp. 1079\u20131087.","DOI":"10.1109\/INFOCOM.2018.8486250"},{"key":"10.1016\/j.csl.2026.101988_b92","series-title":"International Conference on Machine Learning","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","author":"Qian","year":"2022"},{"key":"10.1016\/j.csl.2026.101988_b93","series-title":"2024 IEEE Spoken Language Technology Workshop","first-page":"727","article-title":"End-to-end streaming model for low-latency speech anonymization","author":"Quamer","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b94","series-title":"International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b95","series-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"10.1016\/j.csl.2026.101988_b96","unstructured":"Ren, Y., Hu, C., Tan, X., Qin, T., Zhao, S., Zhao, Z., Liu, T.-Y., 2020. FastSpeech 2: Fast and High-Quality End-to-End Text to Speech. In: International Conference on Learning Representations. ICLR."},{"issue":"2","key":"10.1016\/j.csl.2026.101988_b97","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1109\/TAFFC.2021.3104170","article-title":"Audio-visual automatic group affect analysis","volume":"14","author":"Sharma","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.csl.2026.101988_b98","first-page":"92","article-title":"Safeguarding speech content style: Enhancing privacy beyond speaker identity","author":"Sinha","year":"2024","journal-title":"Proc. SPSC 2024"},{"key":"10.1016\/j.csl.2026.101988_b99","series-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"10.1016\/j.csl.2026.101988_b100","doi-asserted-by":"crossref","first-page":"2383","DOI":"10.1109\/TASLP.2022.3190741","article-title":"Privacy and utility of x-vector based speaker anonymization","volume":"30","author":"Srivastava","year":"2022","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.101988_b101","series-title":"Interspeech","first-page":"1713","article-title":"Design choices for X-Vector based speaker anonymization","author":"Srivastava","year":"2020"},{"key":"10.1016\/j.csl.2026.101988_b102","doi-asserted-by":"crossref","unstructured":"Srivastava, B.M.L., Vauquier, N., Sahidullah, M., Bellet, A., Tommasi, M., Vincent, E., 2020b. Evaluating Voice Conversion-based Privacy Protection against Informed Attackers. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 2802\u20132806.","DOI":"10.1109\/ICASSP40776.2020.9053868"},{"key":"10.1016\/j.csl.2026.101988_b103","article-title":"System description: Speaker anonymization system with sentiment transfer and feature interpolation","author":"Tan","year":"2024","journal-title":"VoicePrivacy 2024 Chall."},{"key":"10.1016\/j.csl.2026.101988_b104","article-title":"SEF-MK: Speaker-embedding-free voice anonymization through multi-k-means quantization","author":"Tang","year":"2025","journal-title":"Proc. ASRU"},{"issue":"1","key":"10.1016\/j.csl.2026.101988_b105","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1038\/s43856-024-00609-5","article-title":"Addressing challenges in speaker anonymization to maintain utility while ensuring privacy of pathological speech","volume":"4","author":"Tayebi Arasteh","year":"2024","journal-title":"Commun. Med."},{"key":"10.1016\/j.csl.2026.101988_b106","doi-asserted-by":"crossref","unstructured":"Thienpondt, J., Demuynck, K., 2023. ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings. In: IEEE Automatic Speech Recognition and Understanding Workshop. ASRU, pp. 1\u20138.","DOI":"10.1109\/ASRU57964.2023.10389750"},{"key":"10.1016\/j.csl.2026.101988_b107","series-title":"The VoicePrivacy 2024 challenge evaluation plan","author":"Tomashenko","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b108","series-title":"The first VoicePrivacy Attacker Challenge evaluation plan","author":"Tomashenko","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b109","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"The First VoicePrivacy Attacker Challenge","author":"Tomashenko","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b110","series-title":"Privacy attacks on voice anonymization systems: Overview and key findings from the first VoicePrivacy attacker challenge","author":"Tomashenko","year":"2026"},{"key":"10.1016\/j.csl.2026.101988_b111","series-title":"Interspeech","first-page":"1693","article-title":"Introducing the VoicePrivacy Initiative","author":"Tomashenko","year":"2020"},{"key":"10.1016\/j.csl.2026.101988_b112","series-title":"The VoicePrivacy 2020 Challenge evaluation plan","author":"Tomashenko","year":"2020"},{"key":"10.1016\/j.csl.2026.101988_b113","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Analysis of speech temporal dynamics in the context of speaker verification and voice anonymization","author":"Tomashenko","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b114","series-title":"Interspeech 2025","article-title":"Exploiting context-dependent duration features for voice anonymization attack systems","author":"Tomashenko","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b115","series-title":"The VoicePrivacy 2022 Challenge evaluation plan","author":"Tomashenko","year":"2022"},{"key":"10.1016\/j.csl.2026.101988_b116","series-title":"The VoicePrivacy 2022 Challenge","author":"Tomashenko","year":"2022"},{"key":"10.1016\/j.csl.2026.101988_b117","series-title":"Supplementary material to the paper. The VoicePrivacy 2020 Challenge: Results and findings","author":"Tomashenko","year":"2021"},{"key":"10.1016\/j.csl.2026.101988_b118","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2022.101362","article-title":"The VoicePrivacy 2020 Challenge: Results and findings","volume":"74","author":"Tomashenko","year":"2022","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101988_b119","series-title":"Target speaker anonymization in multi-speaker recordings","author":"Tomashenko","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b120","series-title":"Interspeech 2025","first-page":"3229","article-title":"Legally validated evaluation framework for voice anonymization","author":"Vauquier","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b121","series-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Veaux","year":"2019"},{"key":"10.1016\/j.csl.2026.101988_b122","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3263585","article-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","author":"Wagner","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.csl.2026.101988_b123","series-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"10.1016\/j.csl.2026.101988_b124","doi-asserted-by":"crossref","unstructured":"Wang, D., Deng, L., Yeung, Y.T., Chen, X., Liu, X., Meng, H., 2021. VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion. In: Proc. Interspeech. pp. 1344\u20131348.","DOI":"10.21437\/Interspeech.2021-283"},{"key":"10.1016\/j.csl.2026.101988_b125","unstructured":"Wang, Y., Stanton, D., Zhang, Y., Ryan, R.-S., Battenberg, E., Shor, J., Xiao, Y., Ren, F., Jia, Y., Saurous, R.A., 2018. Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis. In: International Conference on Machine Learning. ICML, pp. 5180\u20135189."},{"key":"10.1016\/j.csl.2026.101988_b126","doi-asserted-by":"crossref","unstructured":"Williams, J., Pizzi, K., Das, S., No\u00e9, P.-G., 2022. New challenges for content privacy in speech and audio. In: Proc. SPSC 2022. pp. 1\u20136.","DOI":"10.21437\/SPSC.2022-1"},{"key":"10.1016\/j.csl.2026.101988_b127","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"12491","article-title":"Anonymizing speaker voices: Easy to imitate, difficult to recognize?","author":"Williams","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b128","doi-asserted-by":"crossref","unstructured":"Williams, J., Yamagishi, J., Valentini-Botinhao, C., Bonastre, J.-F., et al., 2021. Revisiting Speech Content Privacy. In: Proc. SPSC 2021. pp. 42\u201346.","DOI":"10.21437\/SPSC.2021-9"},{"issue":"4","key":"10.1016\/j.csl.2026.101988_b129","doi-asserted-by":"crossref","first-page":"2810","DOI":"10.1109\/TAFFC.2022.3221801","article-title":"Estimating the uncertainty in emotion class labels with utterance-specific dirichlet priors","volume":"14","author":"Wu","year":"2022","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.csl.2026.101988_b130","series-title":"HLTCOE JHU submission to the Voice Privacy challenge 2024","author":"Xinyuan","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b131","series-title":"NPU-NTU system for Voice Privacy 2024 challenge","author":"Yao","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b132","series-title":"Interspeech 2025","first-page":"3219","article-title":"EASY: Emotion-aware Speaker Anonymization via Factorized Distillation","author":"Yao","year":"2025"},{"key":"10.1016\/j.csl.2026.101988_b133","series-title":"MUSA: Multi-lingual speaker anonymization via serial disentanglement","author":"Yao","year":"2024"},{"key":"10.1016\/j.csl.2026.101988_b134","doi-asserted-by":"crossref","unstructured":"Zadeh, A.B., Liang, P.P., Poria, S., Cambria, E., Morency, L.-P., 2018. Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. In: 56th Annual Meeting of the ACL (Volume 1: Long Papers). pp. 2236\u20132246.","DOI":"10.18653\/v1\/P18-1208"},{"key":"10.1016\/j.csl.2026.101988_b135","doi-asserted-by":"crossref","unstructured":"Zanon Boito, M., Besacier, L., Tomashenko, N., Est\u00e8ve, Y., 2022. A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems. In: Proc. Interspeech 2022. pp. 1278\u20131282.","DOI":"10.21437\/Interspeech.2022-353"},{"key":"10.1016\/j.csl.2026.101988_b136","series-title":"Interspeech","first-page":"1526","article-title":"LibriTTS: A corpus derived from LibriSpeech for text-to-speech","author":"Zen","year":"2019"},{"key":"10.1016\/j.csl.2026.101988_b137","unstructured":"Zhang, J., Liu, S., Hou, J., Wang, Z., Yu, H., Li, X.-Y., 2025. {SpeechGuard}: Recoverable and Customizable Speech Privacy Protection. In: 34th USENIX Security Symposium (USENIX Security 25). pp. 5931\u20135948."},{"key":"10.1016\/j.csl.2026.101988_b138","doi-asserted-by":"crossref","unstructured":"Zhou, K., Sisman, B., Liu, R., Li, H., 2021. Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 920\u2013924.","DOI":"10.1109\/ICASSP39728.2021.9413391"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000513?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000513?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T21:12:41Z","timestamp":1779225161000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230826000513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":138,"alternative-id":["S0885230826000513"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2026.101988","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"The third VoicePrivacy challenge: Preserving emotional expressiveness and linguistic content in voice anonymization","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2026.101988","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"101988"}}