Speech Recognition Native Module Environment Inherent in Mobiles Devices Blanca E. Carvajal-G´ amez 1(B ) , Erika Hern´ andez Rubio 2 , Amilcar Meneses Viveros 3 , and Francisco J. Hern´ andez-Casta˜ neda 2 1 Instituto Polit´ ecnico Nacional, Unidad Profesional Interdisciplinaria y Tecnolog´ ıa Avanzada, M´ exico D.F., Mexico becarvajal@ipn.mx 2 Instituto Polit´ ecnico Nacional, SEPI-ESCOM, M´ exico D.F., Mexico ehernandezru@ipn.mx 3 Departamento de Computaci´on, CINVESTAV-IPN, M´ exico D.F., Mexico ameneses@cs.cinvestav.mx Abstract. Applications on mobile devices have been characterized for their usability. The voice is a natural means of interaction between users and mobile devices. Traditional speech recognition algorithms work in controlled media are targeted to specific population groups (e.g. age, gender or language to name of few), and also require a lot of computa- tional resources so that the algorithms are effective. Therefore, pattern recognition is performed in mobile applications as web services. However, this type of solution generates high dependence on Internet connectivity, so it is desirable to have an embedded module for this task that does not consume many computational resources and have a good level of effectiveness. This paper presents an embedded mobile systems for voice recognition module is presented. This module works in noisy environ- ments, it works for any age of users and has proved that it can work for several languages. 1 Introduction Applications on mobile devices have been characterized for their usability [1]. Developers try that interaction means for mobile devices are natural to the user [2]. Actually, the most common means of interaction based on gestures on touch screens [3]. It has explored the interaction through voice applications such as search and on tasks requiring multimodal interactions [4, 5]. In hardware complies with those demands of speech recognition applica- tions, because we can utilize parallel and pipelined architectures [6], which either reduce power with low operation frequency or speed up there cogni- tion. With such knowledge, comprehensible human-like speech recognition can be obtained [6]. In automatic speech recognition systems (ASR) can be sorted into the fol- lowing three categories [7]: c  Springer International Publishing Switzerland 2015 M. Antona and C. Stephanidis (Eds.): UAHCI 2015, Part I, LNCS 9175, pp. 267–278, 2015. DOI: 10.1007/978-3-319-20678-3 26