{"title":"Voice activated editing of diagnostic ECGs","authors":"C. Lassvik, J. Tranesjo, N. Areskog","doi":"10.1109/CIC.1989.130487","DOIUrl":null,"url":null,"abstract":"In Sweden the editing of unconfirmed, automatically classified reports in a computer-based ECG management system is often done by physicians with relatively little typewriter experience. It is suggested that input devices other than the terminal keyboard might speed up and make more enjoyable the editing procedure for these physicians. A voice recognition system was tested and showed approximately a 10% failure in recognizing a short list of various ECG statements. The main reasons for this were a nonoptimal microphone technique and many phonetically similar phrases. After minimizing these sources of error, a clinical trial of the voice recognizing system connected to a commercial ECG management system was performed. Preliminary results show that ECG editing using a voice recognition system is feasible, but that technical difficulties must be overcome to achieve a clinically useful system.<<ETX>>","PeriodicalId":161494,"journal":{"name":"[1989] Proceedings. Computers in Cardiology","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1989-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"[1989] Proceedings. Computers in Cardiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIC.1989.130487","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In Sweden the editing of unconfirmed, automatically classified reports in a computer-based ECG management system is often done by physicians with relatively little typewriter experience. It is suggested that input devices other than the terminal keyboard might speed up and make more enjoyable the editing procedure for these physicians. A voice recognition system was tested and showed approximately a 10% failure in recognizing a short list of various ECG statements. The main reasons for this were a nonoptimal microphone technique and many phonetically similar phrases. After minimizing these sources of error, a clinical trial of the voice recognizing system connected to a commercial ECG management system was performed. Preliminary results show that ECG editing using a voice recognition system is feasible, but that technical difficulties must be overcome to achieve a clinically useful system.<>