IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.最新文献_第4页

Automatic evaluation methods of a speech translation system's capability 语音翻译系统能力的自动评价方法

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034661

F. Sugaya, K. Yasuda, T. Takezawa, S. Yamamoto

{"title":"Automatic evaluation methods of a speech translation system's capability","authors":"F. Sugaya, K. Yasuda, T. Takezawa, S. Yamamoto","doi":"10.1109/ASRU.2001.1034661","DOIUrl":"https://doi.org/10.1109/ASRU.2001.1034661","url":null,"abstract":"The main goal of the paper is to propose automatic schemes for the translation paired comparison method, which was proposed by the authors to evaluate precisely a speech translation system's capability. In the method, the outputs of the speech translation system are subjectively compared with the results of native Japanese taking the Test of English for International Communication (TOEIC), which is used as a measure of a person's speech translation capability. Experiments are conducted on TDMT, which is a subsystem of the Japanese-to-English speech translation system ATR-MATRIX developed at ATR Interpreting Telecommunications Research Laboratories. The winning rate of TDMT shows a good correlation with the TOEIC scores of the examinees. A regression analysis on the subjective results shows that the translation capability of TDMT matches a person scoring around 700 on the TOEIC. The automatic evaluation methods use DP-based similarity, which is calculated by DP distances between a translation output and multiple translation answers. The answers are collected by two methods: paraphrasing and query from a parallel corpus. In both types of collection, the similarity shows the same good correlation with the TOEIC scores of the examinees as the subjective winning rate. Regression analysis using similarity shows that the system's matched point is around 750. We also show effects of paraphrased data.","PeriodicalId":118671,"journal":{"name":"IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134325812","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}

引用次数: 0

Vocabulary independent speech recognition using particles 词汇独立语音识别使用粒子

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034650

E. Whittaker, J.M. Van Thong, P. Moreno

引用次数: 12

Piecewise-linear transformation-based HMM adaptation for noisy speech 基于分段线性变换的HMM自适应噪声语音

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034612

Zhipeng Zhang, S. Furui

引用次数: 34

Estimated rank pruning and Java-based speech recognition 估计秩修剪和基于java的语音识别

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034669

N. Jevtic, A. Klautau, A. Orlitsky

引用次数: 8

Finite-state transducers for speech-input translation 语音输入翻译的有限状态换能器

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034664

F. Casacuberta

{"title":"Finite-state transducers for speech-input translation","authors":"F. Casacuberta","doi":"10.1109/ASRU.2001.1034664","DOIUrl":"https://doi.org/10.1109/ASRU.2001.1034664","url":null,"abstract":"Nowadays, hidden Markov models (HMMs) and n-grams are the basic components of the most successful speech recognition systems. In such systems, HMMs (the acoustic models) are integrated into a n-gram or a stochastic finite-state grammar (the language model). Similar models can be used for speech translation, and HMMs (the acoustic models) can be integrated into a finite-state transducer (the translation model). Moreover, the translation process can be performed by searching for an optimal path of states in the integrated network. The output of this search process is a target word sequence associated to the optimal path. In speech translation, HMMs can be trained from a source speech corpus, and the translation model can be learned automatically from a parallel training corpus. This approach has been assessed in the framework of the EUTRANS project, founded by the European Union. Extensive speech-input experiments have been carried out with translations from Spanish to English and from Italian to English translation, in an application involving the interaction (by telephone) of a customer with a receptionist at the front-desk of a hotel. A summary of the most relevant results are presented in this paper.","PeriodicalId":118671,"journal":{"name":"IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115720114","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}

引用次数: 33

Trend tying in the segmental-feature HMM 细分特征HMM的趋势

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034585

Young-Sun Yun

引用次数: 0

Multiple time resolutions for derivatives of Mel-frequency cepstral coefficients mel频率倒谱系数导数的多时间分辨率

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034583

G. Stemmer, C. Hacker, E. Noth, H. Niemann

引用次数: 10

Construction of model-space constraints 模型空间约束的构造

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034591

Patrick Nguyen, Luca Rigazio, C. Wellekens, J. Junqua

引用次数: 3

Histogram based normalization in the acoustic feature space 声学特征空间中基于直方图的归一化

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034579

S. Molau, Michael Pitz, H. Ney

引用次数: 70

ASR in portable wireless devices 便携式无线设备中的ASR

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. Pub Date : 2001-12-09 DOI: 10.1109/ASRU.2001.1034597

Olli Viikki

引用次数: 17