Short message dictation on Symbian series 60 mobile phones

Abstract

Dictation of natural language text on embedded mobile devices is a challenging task. First, it involves memory and CPU-efficient implementation of robust speech recognition algorithms that are generally resource demanding. Secondly, the acoustic and language models employed in the recognizer require the availability of suitable text and speech language resources, typically for a wide set of languages. Thirdly, a proper design of the UI is also essential. The UI has to provide intuitive and easy means for dictation and error correction, and must be suitable for a mobile usage scenario. In this demonstrator, an embedded speech recognition system for short message (SMS) dictation in US English is presented. The system is running on Nokia Series 60 mobile phones (e.g., N70, E60). The system's vocabulary is 23 thousand words. Its Flash and RAM memory footprints are small, 2 and 2.5 megabytes, respectively. After a short enrollment session, most native speakers can achieve a word accuracy of over 90% when dictating short messages in quiet or moderately noisy environments.

Mobile device impairment … similar problems, similar solutions?

“…For example, applications have been proposed (Harada et al 2007) that allow users with motor impairments to create artwork by using the non-speech properties of their voice, and similarly in previous work (Harada et al 2006), a voice-based pointer control technique has been demonstrated. Voice interaction is also used on small devices for speech dialling or editing text messages (Karpov et al 2006) and used by motor impaired (Neto et al 2009) and visually impaired users (Manaris and Harkreader 1998) as a substitute for both the keyboard and mouse. A text entry facility (S12), which 'predicts' the words a user is entering by looking for the most relevant key combination in its internal dictionary (Minneman 1986, Garay-Vitoria andAbascal 2005) has also been adopted to speed up input.…”

The Design Space of Ubiquitous Mobile Input

“…For example, system on a chip designs for speech processing (Ravindran, Smith, Graham, Duangudom, Anderson, & Hasler, 2005) have the potential to bring speech input to interactive text entry on mobile phones. Karpov et al (Karpov, Kiss, Leppanen, Olsen, Oria, Sivadas, & Tian, 2006) have developed a short message (SMS) dictation system for Symbian phones with a vocabulary of 23,000 words. The language model is adapted to words typically used in SMS messages.…”

Automatic Speech Recognition on Mobile Devices and over Communication Networks

“…In this section we describe the work done in Nokia Research Center on low footprint embedded dictation (Karpov et al 2006). The system supports five languages: US English, UK English, French, Spanish and Mandarin Chinese.…”