Development of robust speech recognition middleware on microprocessor

Abstract

14 ms / frame -0.6 sec 1000We have developed speech recognition middleware on a RISC microprocessor which has robust processing functions against environmental noise and speaker ditkences. The speech recognition middleware enables developers and users to use a speech recognition process fbr m n y possible speech applications, such as car navigation system and handheld PCs. In this paper, we report implemntation issues ofspeech recognition process in middleware of microprocessors and propose robust noise handling hnctions using ANC(Adaptive Noise Cancellation) and noise adapt\ve models. We also propose a new speaker adaptation algorithm, in which the relationships among HMMs(Hidden Markov Models) transkr vectors are provided as a set of pre-trained interpolation coefficients. Experimental evaluations on 1000-word vocabulary speech recognition showed promising results h r both robust processing functions ofthe proposed noise handling methods and the proposed speaker adaptation method.

Robust speech recognition for car environment noise

“…The authors have developed [2][3][4] speech recognition middleware using the SH Micon as the platform. In a real environment, environmental noise is a factor degrading speech recognition performance.…”

“…The SuperH microprocessor (abbreviated as SH Micon) has been widely used as the CPU of car navigation systems, portable information terminals, and others. The authors have developed [2][3][4] speech recognition middleware using the SH Micon as the platform. In a real environment, environmental noise is a factor degrading speech recognition performance.…”

Robust speech dialog interface for car telematics service

“…In our evaluation, two types of robust speech recognition methods against noise have been developed. The first one is a noise inserted acoustic model and the second is the Spectral Subtraction (SS) method [1][2].…”

“…In this paper, we first report on embedded speech middleware [1][2] which enables sophisticated HMIs for multimedia systems. The speech middleware has been used widely for car navigation systems, mobile information equipment, and game machines.…”