Academic Journals Database
Disseminating quality controlled scientific knowledge

Comparison Of LDM and LMS for an Application of a Speech

Author(s): V.A.Mane | K.P.Paradeshi | S.A.Harage | M.S.Ingavale

Journal: Signal Processing : An International Journal
ISSN 1985-2339

Volume: 3;
Issue: 4;
Start page: 130;
Date: 2011;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: White Noise | Error Covariance Matrix | kalman Gain | LMS Cross Correlation

Automatic speech recognition (ASR) has moved from science-fiction fantasy to daily reality forcitizens of technological societies. Some people seek it out, preferring dictating to typing, orbenefiting from voice control of aids such as wheel-chairs. Others find it embedded in their Hitechgadgetry – in mobile phones and car navigation systems, or cropping up in what would have untilrecently been human roles such as telephone booking of cinema tickets. Wherever you may meetit, computer speech recognition is here, and it’s here to stay.Most of the automatic speech recognition (ASR) systems are based on Gaussian Mixtures model.The output of these models depends on subphone states. We often measure and transform thespeech signal in another form to enhance our ability to communicate. Speech recognition is theconversion from acoustic waveform into written equivalent message information. The nature ofspeech recognition problem is heavily dependent upon the constraints placed on the speaker,speaking situation and message context. Various speech recognition systems are available. Thesystem which detects the hidden conditions of speech is the best model. LMS is one of the simplealgorithm used to reconstruct the speech and linear dynamic model is also used to recognize thespeech in noisy atmosphere..This paper is analysis and comparison between the LDM and a simpleLMS algorithm which can be used for speech recognition purpose.

Tango Rapperswil
Tango Rapperswil

     Affiliate Program