{"title":"Keynote speech 3: Toward simultaneous, natural and multimodal speech-to-speech translation","authors":"Satoshi Nakamura","doi":"10.1109/ICSDA.2015.7357853","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357853","url":null,"abstract":"Spoken language technologies enable to support natural oral communication. Language barrier between different language speaking people is one of the biggest communication problems for human being. Speech-to-speech translation had been studied in order to break the language barrier. In this talk, I would like to introduce brief history of the speech-to-speech translation research and state-of-the-art speech translation system. Then I would introduce new challenges toward a simultaneous speech-to-speech translation including simultaneous incremental machine translation, joint-optimization of ASR and MT modules, Speech-to-speech translation preserving para/non-linguistic information and multimodal speech translation with a talking face.","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123475877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Message from the technical program committee chair","authors":"Hongwei Ding","doi":"10.1109/ICSDA.2015.7357845","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357845","url":null,"abstract":"With the unwavering efforts and continuous support by Professor Satoshi Nakamura and the O-COCOSDA steering committee chaired by him, the 18th Oriental COCOSDA/CASLRE continues to be an IEEE Co-sponsored conference and its influence keeps growing.","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"14 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120910711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Keynote speech 1: Artificial intelligence needs a language cognitive revolution","authors":"Yu Hu","doi":"10.1109/ICSDA.2015.7357851","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357851","url":null,"abstract":"This report will first review the breakthrough in the history of human intelligence. Seventy thousand years ago, Homo sapiens achieved “singularity” intellectual breakthrough, the key of this breakthrough is the language-based cognitive revolution they had achieved. Likewise, artificial intelligence also need a language cognitive revolution to achieve a breakthrough. How to break through cognitive intelligence? This report will introduce the breakthrough and initial results in cognitive intelligence IFLYTEK has achieved combined with the research plans, objectives of IFLYTEK Hyper Brain. At the same time, set forth how to use the “ripple effect” to achieve the core technology of artificial intelligence iterative optimization, in the background of the current big data, cloud computing, mobile Internet deeply applied, and to promote a higher level of artificial intelligence.","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133701696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Keynote speech 2: Ontology-supported special corpus of illocution, emotion and prosody","authors":"Yueguo Gu","doi":"10.1109/ICSDA.2015.7357852","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357852","url":null,"abstract":"In saying something, given the right circumstances, the speaker is said to have performed an illocutionary act (or simply illocution), which gives birth to a special meaning technically called illocutionary force. For example, when a toddler, seeing a jeep approaching, says to its mother, “吉普! 吉普!”, it is performing an illocutionary act of wanting , — “I want to be with the jeep!” A few minutes later, when the toddler sees the jeep driving away, he cries out: “吉普! 吉普”. This time he performs another illocutionary act of wanting, — “I don't want the jeep to go away!” Each instance is associated with an occurrent emotion — the first happiness, and the second sadness, and a particular configuration of prosodic features (e.g., pitch, tempo, nasalization, lengthening of a syllable, etc.).","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116148524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Keynote speech 4: Extraction of linguistic and paralinguistic information from audio-visual data","authors":"Shrikanth S. Narayanan","doi":"10.1109/ICSDA.2015.7357854","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357854","url":null,"abstract":"Audio-visual data have been a key enabler of human observational research and practice. The confluence of sensing, communication and computing technologies is allowing capture and access to data, in diverse forms and modalities, in ways that were unimaginable even a few years ago. Importantly, these data afford the analysis and interpretation of multimodal cues of verbal and non-verbal human behavior. These signals carry crucial information about not only a person's intent and identity but also underlying attitudes and emotions. Automatically capturing these cues, although vastly challenging, offers the promise of not just efficient data processing but in tools for discovery that enable hitherto unimagined insights. Recent computational approaches that have leveraged judicious use of both data and knowledge have yielded significant advances in this regards, for example in deriving rich information from multimodal sources including human speech, language, and videos of visual behavior. This talk will focus on some of the advances and challenges in gathering such data and creating algorithms for machine processing of such cues. It will also introduce some of the freely available data resources for research.","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128444185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Message from the conference chair","authors":"Kaibao Hu","doi":"10.1109/ICSDA.2015.7357844","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357844","url":null,"abstract":"On behalf of the Organizing Committee of the Conference and School of Foreign Languages (SFL), Shanghai Jiao Tong University, it is my great pleasure to welcome you all to the 18th Oriental COCOSDA/CASLRE (The International Committee for Co-ordination and Standardization of Speech Databases and Assessment Techniques / Conference on Asian Spoken Language Resources and Evaluation). We have about 100 delegates from almost 20 countries/regions representing here today. It is certainly a tremendous honor to host O-COCOSDA/CASLRE 2015.","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127193071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Message of the O-COCOSDA Convener","authors":"Satoshi Nakamura","doi":"10.1109/ICSDA.2015.7357843","DOIUrl":"https://doi.org/10.1109/ICSDA.2015.7357843","url":null,"abstract":"Welcome to Oriental-COCOSDA/CASLRE (Conference on Asian Spoken Language Research and Evaluation) 2014 in Phuket, Thailand. This is the 17th annual conference of Oriental-COCOSDA, the Oriental chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment. I would like to thank the colleagues from Thailand headed by Conference Chair Chai Wutiwiwatchai, Thanaruk Theeramunkong and Montri Karnjanadecha for making the event possible this time in Thailand. I also very much appreciate for all of the organization committee for the great efforts of the managements.","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125990839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Respiration features of Chinese learners under self-narration task - The case of learners from Korea, Japan, America and Thailand","authors":"Yujun Wang, Yuan Jia, Ai-jun Li","doi":"10.1109/ICSDA.2013.6709902","DOIUrl":"https://doi.org/10.1109/ICSDA.2013.6709902","url":null,"abstract":"Through the methods of physiological experiment in combination with acoustical experiment, the present research investigates the respiration and acoustic features of the Chinese learners during the task of self-narration. Twenty-four Chinese learners from Korea, Japan, America and Thailand are assigned to narrate in Mandarin Chinese. The spontaneous speech respiration which is greatly influenced by the physiological condition, cognitive processing, context and mood state tends to make the respiration curve to be complex. In this condition, compared with Chinese native speakers, different respiratory units have significant differences in inspiration/expiration duration, amplitude and slope in terms of respiratory parameters. The frequency of the abnormal pause is large in great extent, and the position of the abnormal pause is rather flexible, so its different categories correspond to the different respiration forms.","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125115416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE), Gurgaon, India, November 25-27, 2013","authors":"","doi":"10.1109/o-cocosda/caslre32229.2013","DOIUrl":"https://doi.org/10.1109/o-cocosda/caslre32229.2013","url":null,"abstract":"","PeriodicalId":401065,"journal":{"name":"International Conference Oriental COCOSDA held jointly with Conference on Asian Spoken Language Research and Evaluation","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134386576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}