Multi-task learning (MTL) for deep neural network (DNN) multilingual acoustic models has been shown to be effective for learning parameters that are common or shared between multiple languages[1, 2]. In the MTL paradigm, the number of parameters in the output layer is large and scales with the number of languages used in training. This output layer becomes a computational bottleneck. For mono-lingual DNNs, low-rank matrix factorization (LRMF) of weight matrices have yielded large computational savings[3, 4]. The LRMF proposed in this work for MTL, is for the original language-specific block matrices to "share" a common matrix, with resulting low-rank language specific block matrices. The impact of LRMF is presented in two scenarios, namely: (a) improving performance in a target language when auxiliary languages are included during multi-lingual training; and (b) cross-language transfer to an unseen language with only 1 hour of transcribed training data. A 44% parameter reduction in the final layer, manifests itself in providing a lower memory footprint and faster training times. An experimental study shows that the LRMF multi-lingual DNN provides competitive performance compared to a full-rank multi-lingual DNN in both scenarios.<\/p>\n","protected":false},"excerpt":{"rendered":"
Multi-task learning (MTL) for deep neural network (DNN) multilingual acoustic models has been shown to be effective for learning parameters that are common or shared between multiple languages[1, 2]. In the MTL paradigm, the number of parameters in the output layer is large and scales with the number of languages used in training. This output […]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,89,3],"tags":[1782,14,1673,1025,34,20,848,1390],"class_list":["post-13812","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-computer-science","tag-cuda","tag-deep-learning","tag-machine-learning","tag-neural-networks","tag-nvidia","tag-speech-recognition","tag-tesla-k20"],"views":2425,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/13812","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=13812"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/13812\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=13812"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=13812"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=13812"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}