Embedded Speech Recognition Applications in Mobile Phones: Status, Trends, and Challenges

Abstract

Voice centric interfaces are widely available in modern mobile phones, including low-cost versions. The applications have evolved from speaker-dependent name dialing, which require user enrollment of frequently dialed names, to speaker-independent capabilities including continuous digit dialing, command and control of phone functions, and name dialing directly from the phone’s contacts directory. Recently available advances include capabilities like voice-enabled SMS, e-mail, and even mobile search with voice. This evolution has been enabled by advances in speech recognition robustness, network capabilities, and increased computational power in small devices. Systems may now be used in hands-busy/eyes-busy conditions including speakerphone and bluetooth scenarios. In this paper, we will provide an overview of embedded speech recognition centric applications in mobile phones, specifically focusing on current status, industry trends, and challenges in customer acceptance. Although voice interfaces are natural and attractive in theory a majority of users do not use the voice-enabled features available in their mobile phones. We will discuss some of the reasons for this user behavior and recommend actions to be taken.