Factors Influencing Voice Message Service Acceptance among Mobile Phone Users in Nigeria (Published)
The aim of this study is to empirically establish a framework of consumers’ attitude and intention towards mobile advertising in Nigeria with particular focus on Voice Message Service (VMS). This study became necessary given that context specific studies conducted in the area of voice message service based mobile advertising since the advent of Global System for Mobile Communication (GSM) in Nigeria are lacking. The study replicated and extended a Chinese-based research model to a different context, namely Nigeria. We adapted constructs from the IDT, TAM, TRA, and by extension the TPB to under-pin the study’s conceptual framework. The unit of analysis comprised active mobile phone users in Nigeria. Two-stage multiple regression analysis was used in the modeling. The result from a convenience sample of 2,509 respondents in six geopolitical zones of Nigeria show that the three key factors affecting consumers’ attitude towards voice message service based mobile advertisements are compatibility, trialability and image. On the other hand, the study also revealed that the behavioral intentions of mobile phone users in Nigeria towards voice message service are as a result of attitude and perceived behavioral control. Interestingly, the voice message service based mobile advertising acceptance model was posited by the study. Overall, the study concludes that service providers and advertisers in Nigeria may need to revise their business models in line with these findings to reach out to their teeming VMS based mobile advertising consumers. A key recommendation is that the regulator in the telecom industry in Nigeria should mandate service providers to profile mobile phone users that subscribed to their network to be able to send them targeted VMS ads.
This paper describes a method of modeling the characteristics of a singing voice from polyphonic audio signals, in the context of Sri Lankan Music. The main problem in modeling the characteristics of a singing voice is the negative influences caused by accompaniment sounds. Hence the proposed method consists of a procedure to reduce the effect of accompaniment sound. It extracts the predominant melody frequencies of the music file and then resynthesize it. Melody is extracted only on the vocal-parts of the music file to achieve better accuracy. Features vectors are then extracted from the predominant melody frequencies, which are then subjected to supervised leaning approaches with different classifier, using Principal Component Analysis as feature selection algorithms. The models trained with 10-fold cross validation and different combinations of experiments are done to critically analyze the performance of the proposed method for Singer Identification.