Article Preview
TopLiterature Review
With the technology advances, machines are able to speak, hear, and “understand” via a speech interface (Furman et al., 1999). The five broad technology areas of the field of speech processing for man-machine communication are given by Drygajlo (2003): speech recognition, speech synthesis, spoken dialogue, speaker recognition, and speech compression.
In last years, various applications based on voice recognition and voice-enabled user-interfaces that will provide a natural interaction are integrated in mobile devices. They are preferred in the following cases: users with various disabilities, users who are in an eyes-busy, hands-busy situation, users who don't have access to a keyboard and/or a monitor and user who are not aware of computer skills (Nielsen, 2003).
Voice-activated intelligent assistants, such as Siri, Google Now, S Voice, Cortana and Alexa are prevalent on mobile devices. In 2011, Apple's Siri started the trend providing a voice-enabled user-interface which users could get answers to a variety of questions, find information, or perform tasks. Awareness was created about that smartphones could speak (Riccardi, 2014). Then, Google’s Voice Search, Samsung’s S Voice, Microsoft’s Cortana and Amazon’s Alexa followed this development. Such tools are very important in terms of saving time and improving the effectiveness of search (Bengtson, 2014). According to Riccardi (2014), all of them have the ability to interpret Natural Language with spoken interaction and providing responses. They can perform many actions: sending e-mail and text messages, opening an application, making calls, setting alarm, find information on the Web, etc. Some of them (Google Now and Cortana) can make proactive recommendations such as predicting and alerting the user about weather, meetings, traffic, airlines information (Riccardi, 2014).