Oriental COCOSDA ... International Conference on Speech Database and Assessments : [proceedings]. International Conference on Speech Database and Assessments最新文献
Pub Date : 2014-09-01DOI: 10.1109/ICSDA.2014.7051411
M. Riley
This talk will describe the use of weighted transducers in speech and language processing. Weighted transducers are automata where each transition has an input label, an output label, and a weight. They have key applications in speech recognition and synthesis, machine translation, optical character recognition, pattern matching, string processing, machine learning, information extraction and retrieval among others. We give a brief history of the field, an overview of the theory and algorithms of weighted finite-state and pushdown transducers, a discussion of available software libraries, a description of applications to speech recognition, speech synthesis, machine translation and NLP, and a short overview of current research problems.
{"title":"Keynote 3: Weighted transducers in speech and language processing","authors":"M. Riley","doi":"10.1109/ICSDA.2014.7051411","DOIUrl":"https://doi.org/10.1109/ICSDA.2014.7051411","url":null,"abstract":"This talk will describe the use of weighted transducers in speech and language processing. Weighted transducers are automata where each transition has an input label, an output label, and a weight. They have key applications in speech recognition and synthesis, machine translation, optical character recognition, pattern matching, string processing, machine learning, information extraction and retrieval among others. We give a brief history of the field, an overview of the theory and algorithms of weighted finite-state and pushdown transducers, a discussion of available software libraries, a description of applications to speech recognition, speech synthesis, machine translation and NLP, and a short overview of current research problems.","PeriodicalId":91941,"journal":{"name":"Oriental COCOSDA ... International Conference on Speech Database and Assessments : [proceedings]. International Conference on Speech Database and Assessments","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79198541","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}
Pub Date : 2014-09-01DOI: 10.1109/ICSDA.2014.7051410
N. Minematsu
English is the only language available for global communication but its form is altered easily and variously depending on the mother tongue of speakers and their environment of learning English. It is true that internationalization of things always alters them due to local cultures. English pronunciation is not exceptional and, if we take two users of English, their pronunciation will show different characteristics, called accents. Today, we often hear the term of World Englishes (WE), where it is claimed that there is no standard English and that American English (AE) and British English (BE) are just two major examples of accented English. While everybody agrees that English is a very useful tool, he/she will also agree that, in international contexts, accents can often cause miscommunications. In this talk, the presenter will show the results obtained in two on-going projects related to the diversity of pronunciation of WE.
{"title":"Keynote 2: Perceptual and structural analysis of pronunciation diversity of World Englishes","authors":"N. Minematsu","doi":"10.1109/ICSDA.2014.7051410","DOIUrl":"https://doi.org/10.1109/ICSDA.2014.7051410","url":null,"abstract":"English is the only language available for global communication but its form is altered easily and variously depending on the mother tongue of speakers and their environment of learning English. It is true that internationalization of things always alters them due to local cultures. English pronunciation is not exceptional and, if we take two users of English, their pronunciation will show different characteristics, called accents. Today, we often hear the term of World Englishes (WE), where it is claimed that there is no standard English and that American English (AE) and British English (BE) are just two major examples of accented English. While everybody agrees that English is a very useful tool, he/she will also agree that, in international contexts, accents can often cause miscommunications. In this talk, the presenter will show the results obtained in two on-going projects related to the diversity of pronunciation of WE.","PeriodicalId":91941,"journal":{"name":"Oriental COCOSDA ... International Conference on Speech Database and Assessments : [proceedings]. International Conference on Speech Database and Assessments","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76774562","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}
Pub Date : 2014-09-01DOI: 10.1109/ICSDA.2014.7051409
D. Burnham
Information technology has always been an area of rapid change. Two recent developments in information technology have changed the nature of research across the spectrum of disciplines and also, to a large extent, developments in the commercial and government sector: Big Data and Resource Sharing. The growth in capacity for storing and accessing data has allowed the establishment of very large databases and corpora. In turn, this has prompted developments in methods for the collection of large data and its subsequent analysis. The growing move to open source and open access, in a wide range of settings and meanings, has led to a growing awareness of the benefits of data sharing. In these contexts, in this paper I describe two platforms that we have developed over the last 4 years: AusTalk, a 3000 hour auditory-visual corpus of Australian English, and Alveo, an extensible Virtual Laboratory housing corpora and analysis tools glued together by a versatile workflow engine. I will describe the genesis and operation of each of these in some detail and set out the advantages they and resources like these provide in (i) research in the wide ranges of disciplines in Human Communication Science, and (ii) facilitating collaboration across disciplines, across institutions, and across languages, and across national boundaries in our region, and well beyond.
{"title":"Keynote 1: Big Data and Resource Sharing: A speech corpus and a Virtual Laboratory for facilitating human communication science research","authors":"D. Burnham","doi":"10.1109/ICSDA.2014.7051409","DOIUrl":"https://doi.org/10.1109/ICSDA.2014.7051409","url":null,"abstract":"Information technology has always been an area of rapid change. Two recent developments in information technology have changed the nature of research across the spectrum of disciplines and also, to a large extent, developments in the commercial and government sector: Big Data and Resource Sharing. The growth in capacity for storing and accessing data has allowed the establishment of very large databases and corpora. In turn, this has prompted developments in methods for the collection of large data and its subsequent analysis. The growing move to open source and open access, in a wide range of settings and meanings, has led to a growing awareness of the benefits of data sharing. In these contexts, in this paper I describe two platforms that we have developed over the last 4 years: AusTalk, a 3000 hour auditory-visual corpus of Australian English, and Alveo, an extensible Virtual Laboratory housing corpora and analysis tools glued together by a versatile workflow engine. I will describe the genesis and operation of each of these in some detail and set out the advantages they and resources like these provide in (i) research in the wide ranges of disciplines in Human Communication Science, and (ii) facilitating collaboration across disciplines, across institutions, and across languages, and across national boundaries in our region, and well beyond.","PeriodicalId":91941,"journal":{"name":"Oriental COCOSDA ... International Conference on Speech Database and Assessments : [proceedings]. International Conference on Speech Database and Assessments","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75106000","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}
Pub Date : 1900-01-01DOI: 10.1109/O-COCOSDA202257103.2022.9997940
Ronghao Gu, Xiaoli Ji, Yuhan Zhu
Under the aid of experimental phonology, the present study investigated the influence of working memory on Chinese EFL learners’ intonation production through an intonation perception experiment. The major findings were as follows: 1) Chinese EFL learners had better performance for Statement than for Yes-No question and are difficult to realize final focus in Statement and medial focus in Yes-No question; 2) Chinese EFL learners’ performance in pitch pattern was negatively influenced by working memory and procedural memory, while their performance in boundary tone was positively affected by working memory and declarative memory.
{"title":"The Influence Of Working Memory On Intonation Production Of Chinese Efl Learners","authors":"Ronghao Gu, Xiaoli Ji, Yuhan Zhu","doi":"10.1109/O-COCOSDA202257103.2022.9997940","DOIUrl":"https://doi.org/10.1109/O-COCOSDA202257103.2022.9997940","url":null,"abstract":"Under the aid of experimental phonology, the present study investigated the influence of working memory on Chinese EFL learners’ intonation production through an intonation perception experiment. The major findings were as follows: 1) Chinese EFL learners had better performance for Statement than for Yes-No question and are difficult to realize final focus in Statement and medial focus in Yes-No question; 2) Chinese EFL learners’ performance in pitch pattern was negatively influenced by working memory and procedural memory, while their performance in boundary tone was positively affected by working memory and declarative memory.","PeriodicalId":91941,"journal":{"name":"Oriental COCOSDA ... International Conference on Speech Database and Assessments : [proceedings]. International Conference on Speech Database and Assessments","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74207706","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}
Oriental COCOSDA ... International Conference on Speech Database and Assessments : [proceedings]. International Conference on Speech Database and Assessments
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：