Pub Date : 2007-03-05DOI: 10.1109/RIVF.2007.369139
N. Yamsang, S. Udomhunsakul
Evaluation of the quality of image compression still remains an important issue. In this work, we propose the new objective measurements, which are developed from five traditionally simple measurements (Mean Square Error, Edge Measurement, Correlation Measurement, Visual Human System and Spectral Measurement). In our study, we evaluated the quality of the compressed gray-scale images using both objective and subjective tests. We found the relationship between objective and subjective measurements from the distribution data that can be modeled and defined by exponential least square method. From the experimental results, the reliabilities (Correlation coefficient) of our new proposed measurements are better than five traditionally simple measurements.
{"title":"Distribution Model between Objective Measurement and Subjective Measurement","authors":"N. Yamsang, S. Udomhunsakul","doi":"10.1109/RIVF.2007.369139","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369139","url":null,"abstract":"Evaluation of the quality of image compression still remains an important issue. In this work, we propose the new objective measurements, which are developed from five traditionally simple measurements (Mean Square Error, Edge Measurement, Correlation Measurement, Visual Human System and Spectral Measurement). In our study, we evaluated the quality of the compressed gray-scale images using both objective and subjective tests. We found the relationship between objective and subjective measurements from the distribution data that can be modeled and defined by exponential least square method. From the experimental results, the reliabilities (Correlation coefficient) of our new proposed measurements are better than five traditionally simple measurements.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115851029","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 : 2007-03-05DOI: 10.1109/RIVF.2007.369165
S. Tangruamsub, P. Punyabukkana, A. Suchato
This paper illustrates the use of acoustic modeling of three different structures, including syllables, fillers and keywords, for keyword spotting. Filler models and syllable models are applied to capture out-of-vocabulary words, while keyword models extract significant words from speech utterances. Grammatical details are utilized with syllable models to add extra domain constraints. This improves the system's ability to detect non-keyword vocabularies. Filler models associating with syllable models reduce false alarm of keyword detection. Three kinds of filler models are described. Different types of filler models perform differently in keyword spotting of utterances with only one keyword and ones with multiple keywords. Experiments are conducted on a telephone call transferring via Thai spoken language domain. The proposed method is compared with a limited vocabulary speech recognition and keyword spotting using a reward function. For single- keyword utterances, the best accuracy obtained using the proposed method is approximately 70%, which is better than the ones from LVSR and spotting via reward functions. For multiple-keyword utterances, the best precision and recall rates are 72% and 65%, respectively. These are marginally better than ones obtained from limited vocabulary speech recognition, while typical reward function approach yields the rates of less than 50%.
{"title":"Thai Speech Keyword Spotting using Heterogeneous Acoustic Modeling","authors":"S. Tangruamsub, P. Punyabukkana, A. Suchato","doi":"10.1109/RIVF.2007.369165","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369165","url":null,"abstract":"This paper illustrates the use of acoustic modeling of three different structures, including syllables, fillers and keywords, for keyword spotting. Filler models and syllable models are applied to capture out-of-vocabulary words, while keyword models extract significant words from speech utterances. Grammatical details are utilized with syllable models to add extra domain constraints. This improves the system's ability to detect non-keyword vocabularies. Filler models associating with syllable models reduce false alarm of keyword detection. Three kinds of filler models are described. Different types of filler models perform differently in keyword spotting of utterances with only one keyword and ones with multiple keywords. Experiments are conducted on a telephone call transferring via Thai spoken language domain. The proposed method is compared with a limited vocabulary speech recognition and keyword spotting using a reward function. For single- keyword utterances, the best accuracy obtained using the proposed method is approximately 70%, which is better than the ones from LVSR and spotting via reward functions. For multiple-keyword utterances, the best precision and recall rates are 72% and 65%, respectively. These are marginally better than ones obtained from limited vocabulary speech recognition, while typical reward function approach yields the rates of less than 50%.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"37 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125874721","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 : 2006-09-26DOI: 10.1109/RIVF.2007.369142
A. d’Aspremont, L. Ghaoui
We first formulate the problem of optimally scheduling air traffic low with sector capacity constraints as a mixed integer linear program. We then use semidefinite relaxation techniques to form a convex relaxation of that problem. Finally, we present a randomization algorithm to further improve the quality of the solution. Because of the specific structure of the air traffic flow problem, the relaxation has a single semidefinite constraint of size dn where d is the maximum delay and n the number of flights.
{"title":"A Semidefinite Relaxation for Air Traffic Flow Scheduling","authors":"A. d’Aspremont, L. Ghaoui","doi":"10.1109/RIVF.2007.369142","DOIUrl":"https://doi.org/10.1109/RIVF.2007.369142","url":null,"abstract":"We first formulate the problem of optimally scheduling air traffic low with sector capacity constraints as a mixed integer linear program. We then use semidefinite relaxation techniques to form a convex relaxation of that problem. Finally, we present a randomization algorithm to further improve the quality of the solution. Because of the specific structure of the air traffic flow problem, the relaxation has a single semidefinite constraint of size dn where d is the maximum delay and n the number of flights.","PeriodicalId":158887,"journal":{"name":"2007 IEEE International Conference on Research, Innovation and Vision for the Future","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131658437","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}
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：