{"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/unsupervised-learning-of-disentangled-and","title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","arxiv_id":"1709.07902","date":"2017-09-22","proceeding":"NeurIPS 2017 12","authors":["Wei-Ning Hsu","Yu Zhang","James Glass"],"abstract":"We present a factorized hierarchical variational autoencoder, which learns\ndisentangled and interpretable representations from sequential data without\nsupervision. Specifically, we exploit the multi-scale nature of information in\nsequential data by formulating it explicitly within a factorized hierarchical\ngraphical model that imposes sequence-dependent priors and sequence-independent\npriors to different sets of latent variables. The model is evaluated on two\nspeech corpora to demonstrate, qualitatively, its ability to transform speakers\nor linguistic content by manipulating different sets of latent variables; and\nquantitatively, its ability to outperform an i-vector baseline for speaker\nverification and reduce the word error rate by as much as 35% in mismatched\ntrain/test scenarios for automatic speech recognition tasks.","url_abs":"http://arxiv.org/abs/1709.07902v1","url_pdf":"http://arxiv.org/pdf/1709.07902v1.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":[{"paper_slug":"unsupervised-learning-of-disentangled-and","repo_url":"https://github.com/BurnhamG/PyTorch-ScalableFHVAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-learning-of-disentangled-and","repo_url":"https://github.com/wnhsu/FactorizedHierarchicalVAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-learning-of-disentangled-and","repo_url":"https://github.com/wnhsu/ScalableFHVAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.07902","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}