{"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-speech-domain-adaptation-based","title":"Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition","arxiv_id":"1904.06086","date":"2019-04-12","proceeding":null,"authors":["Jong-Hyeon Park","Myungwoo Oh","Hyung-Min Park"],"abstract":"In general, the performance of automatic speech recognition (ASR) systems is\nsignificantly degraded due to the mismatch between training and test\nenvironments. Recently, a deep-learning-based image-to-image translation\ntechnique to translate an image from a source domain to a desired domain was\npresented, and cycle-consistent adversarial network (CycleGAN) was applied to\nlearn a mapping for speech-to-speech conversion from a speaker to a target\nspeaker. However, this method might not be adequate to remove corrupting noise\ncomponents for robust ASR because it was designed to convert speech itself. In\nthis paper, we propose a domain adaptation method based on generative\nadversarial nets (GANs) with disentangled representation learning to achieve\nrobustness in ASR systems. In particular, two separated encoders, context and\ndomain encoders, are introduced to learn distinct latent variables. The latent\nvariables allow us to convert the domain of speech according to its context and\ndomain representation. We improved word accuracies by 6.55~15.70\\% for the\nCHiME4 challenge corpus by applying a noisy-to-clean environment adaptation for\nrobust ASR. In addition, similar to the method based on the CycleGAN, this\nmethod can be used for gender adaptation in gender-mismatched recognition.","url_abs":"http://arxiv.org/abs/1904.06086v1","url_pdf":"http://arxiv.org/pdf/1904.06086v1.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-speech-domain-adaptation-based","repo_url":"https://github.com/vivivic/speech-domain-adaptation-DRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"robust-speech-recognition","task_name":"Robust Speech Recognition"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}