{"title":"端到端手语拼写识别的无标记数据多任务训练","authors":"Bowen Shi, Karen Livescu","doi":"10.1109/ASRU.2017.8268962","DOIUrl":null,"url":null,"abstract":"We address the problem of automatic American Sign Language fingerspelling recognition from video. Prior work has largely relied on frame-level labels, hand-crafted features, or other constraints, and has been hampered by the scarcity of data for this task. We introduce a model for fingerspelling recognition that addresses these issues. The model consists of an auto-encoder-based feature extractor and an attention-based neural encoder-decoder, which are trained jointly. The model receives a sequence of image frames and outputs the fingerspelled word, without relying on any frame-level training labels or hand-crafted features. In addition, the auto-encoder subcomponent makes it possible to leverage unlabeled data to improve the feature learning. The model achieves 11.6% and 4.4% absolute letter accuracy improvement respectively in signer-independent and signer-adapted fingerspelling recognition over previous approaches that required frame-level training labels.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition\",\"authors\":\"Bowen Shi, Karen Livescu\",\"doi\":\"10.1109/ASRU.2017.8268962\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We address the problem of automatic American Sign Language fingerspelling recognition from video. Prior work has largely relied on frame-level labels, hand-crafted features, or other constraints, and has been hampered by the scarcity of data for this task. We introduce a model for fingerspelling recognition that addresses these issues. The model consists of an auto-encoder-based feature extractor and an attention-based neural encoder-decoder, which are trained jointly. The model receives a sequence of image frames and outputs the fingerspelled word, without relying on any frame-level training labels or hand-crafted features. In addition, the auto-encoder subcomponent makes it possible to leverage unlabeled data to improve the feature learning. The model achieves 11.6% and 4.4% absolute letter accuracy improvement respectively in signer-independent and signer-adapted fingerspelling recognition over previous approaches that required frame-level training labels.\",\"PeriodicalId\":290868,\"journal\":{\"name\":\"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"volume\":\"47 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-10-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASRU.2017.8268962\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2017.8268962","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition
We address the problem of automatic American Sign Language fingerspelling recognition from video. Prior work has largely relied on frame-level labels, hand-crafted features, or other constraints, and has been hampered by the scarcity of data for this task. We introduce a model for fingerspelling recognition that addresses these issues. The model consists of an auto-encoder-based feature extractor and an attention-based neural encoder-decoder, which are trained jointly. The model receives a sequence of image frames and outputs the fingerspelled word, without relying on any frame-level training labels or hand-crafted features. In addition, the auto-encoder subcomponent makes it possible to leverage unlabeled data to improve the feature learning. The model achieves 11.6% and 4.4% absolute letter accuracy improvement respectively in signer-independent and signer-adapted fingerspelling recognition over previous approaches that required frame-level training labels.