{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pate-aae-incorporating-adversarial","title":"PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification","arxiv_id":"2104.01271","date":"2021-04-02","proceeding":null,"authors":["Chao-Han Huck Yang","Sabato Marco Siniscalchi","Chin-Hui Lee"],"abstract":"We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. The AAE architecture allows us to obtain good synthetic speech leveraging upon a discriminative training of latent vectors. Such synthetic speech is used to build a privacy-preserving classifier when non-sensitive data is not sufficiently available in the public domain. This classifier follows the PATE scheme that uses an ensemble of noisy outputs to label the synthetic samples and guarantee $\\varepsilon$-differential privacy (DP) on its derived classifiers. Our proposed framework thus consists of an AAE-based generator and a PATE-based classifier (PATE-AAE). Evaluated on the Google Speech Commands Dataset Version II, the proposed PATE-AAE improves the average classification accuracy by +$2.11\\%$ and +$6.60\\%$, respectively, when compared with alternative privacy-preserving solutions, namely PATE-GAN and DP-GAN, while maintaining a strong level of privacy target at $\\varepsilon$=0.01 with a fixed $\\delta$=10$^{-5}$.","url_abs":"https://arxiv.org/abs/2104.01271v2","url_pdf":"https://arxiv.org/pdf/2104.01271v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"keyword-spotting","task_name":"Keyword Spotting"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keyword-spotting-on-google-speech-commands","task":"Keyword Spotting","dataset":"Google Speech Commands","model":"PATE-AAE (Differentially-Private)","rank_in_archive_order":39,"of":42,"metrics":{"10-keyword Speech Commands dataset":"92.37"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.01271","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}