The purpose of this paper is to describe a speech and character combined recognition engine (SCCRE) developed for working on personal digital assistants (PDAs) or on mobile devices. Also, the architecture of a distributed recognition system for providing a more convenient user interface is discussed.
In SCCRE, feature extraction for speech and for character is carried out separately, but the recognition is performed in an engine. The client recognition engine essentially employs a continuous hidden Markov model (CHMM) structure and this CHMM structure consists of variable parameter topology in order to minimize the number of model parameters and to reduce recognition time. This model also adopts the proposed successive state and mixture splitting (SSMS) method for generating context independent model. SSMS optimizes the number of mixtures through splitting in mixture domain and the number of states through splitting in time domain.
The recognition results show that the developed engine can reduce the total number of Gaussian up to 40 per cent compared with the fixed parameter models at the same recognition performance when applied to speech recognition for mobile devices. It shows that SSMS can reduce the size of memory for models to 65 per cent and that for processing to 82 per cent. Moreover, the recognition time decreases 17 per cent with the SMS model while maintaining the recognition rate.
The proposed system will be very useful for many on‐line multimodal interfaces such as PDAs and mobile applications.
