The speech is the primary mode of communication among human being and also the most earthy and efficient form of interchanging information among human. Speech recognition by machine is one of the most interesting areas for research from the last many decades. Basically, speech recognition is the process of automatic extracting and finding out the linguistic information conveyed by a speech signal using computers. Speech processing and recognition is an intensive field of research due to the broad variety of applications. Speech recognition is involved in our daily life activities like mobile applications, weather forecasting, agriculture, healthcare, speech assisted computer games, telephone assistance systems, biometric recognition, etc. Scientists and researchers have been trying to develop software which can easily hear, understand and speak to the users. Processing of speech signal can be categorized into three main parts, Speech recognition, which allows the machine to understand words, phrases, and sentences that human speaks, Natural language processing, which allows the machine to understand the need of users, Speech synthesis, with the help of which machines can speak.
    In this design comparison of recognition rate on the basis of domination of vowel and consonant sound in Spoken Hindi Hybrid Paired Words (SHHPW) has been carried out, with approximately 365 utterances as database; Linear Prediction Cepstral Coefficient (LPCC) and Mel-frequency cepstral coefficient(MFCC)  is used as a feature extraction method and Artificial Neural Networks (ANN) as a classifier.

Reference Paper: Broad Acoustic Classification of Spoken Hindi Hybrid Paired Words using Artificial Neural Networks
Author’s Name:  Anand Singh, Dinesh Kumar Rajoriya, and Vikash Singh
Source: International Journal of Computer Applications

Request source code for academic purpose, fill REQUEST FORM or contact +91 7904568456 by WhatsApp or, fee applicable.

SIMULATION VIDEO DEMO