{"title":"Evaluation of perceived speech quality for VoIP codecs under different loudness and background noise condition","authors":"Suparnakanti Das, Paromita Choudhury","doi":"10.1145/3369740.3372774","DOIUrl":null,"url":null,"abstract":"The quality of received voice signal plays a major role in case of VoIP communication. This becomes more important under the aegis of IoT, which uses a lot of voice-enabled automation. The quality of the perceived signal depends on different parameters. In this paper, we have tried to evaluate the perceived quality of commonly used VoIP codecs in presence of background Noise at different loudness level. The evaluation of the speech signal was carried out in real scenario with different background signals. Harvard sentences are used as the baseline speech signals. On introduction of background signals at various loudness level, the resultant reference speech signal is packetized and transmitted over network though VoIP phones. The test speech signal is then constructed from the received VoIP packets. Objective speech quality measure, PESQ, is further employed to assess the quality of the test speech signal. Results show that VoIP speech using PCMU and Speex8K codecs are the most consistent in terms of perceived quality performance at different loudness condition.","PeriodicalId":240048,"journal":{"name":"Proceedings of the 21st International Conference on Distributed Computing and Networking","volume":"80 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 21st International Conference on Distributed Computing and Networking","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3369740.3372774","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
The quality of received voice signal plays a major role in case of VoIP communication. This becomes more important under the aegis of IoT, which uses a lot of voice-enabled automation. The quality of the perceived signal depends on different parameters. In this paper, we have tried to evaluate the perceived quality of commonly used VoIP codecs in presence of background Noise at different loudness level. The evaluation of the speech signal was carried out in real scenario with different background signals. Harvard sentences are used as the baseline speech signals. On introduction of background signals at various loudness level, the resultant reference speech signal is packetized and transmitted over network though VoIP phones. The test speech signal is then constructed from the received VoIP packets. Objective speech quality measure, PESQ, is further employed to assess the quality of the test speech signal. Results show that VoIP speech using PCMU and Speex8K codecs are the most consistent in terms of perceived quality performance at different loudness condition.