This paper presents a new approach for designing a speaker recognition system based on mel frequency cepstral coefficients (MFCCs) and voice activity detector (VAD). VAD has been employed to suppress the background noise and distinguish between silence and voice activity. MFCCs were extracted from the detected voice sample and are compared with the database for recognition of the speaker. A new criteria for detection is proposed which gives very good performance in noisy environment

Speaker recognition is the process of recognizing the speaker based on characteristics such as pitch ,tone in the speech wave.Background noise influences the overall efficiency of speaker recognition system and is still considered as one of the most challenging issue in Speaker Recognition System (SRS). In this paper mel-frequency cepstral coefficients (MFCC) feature is used along with Vector Quantisation(VQ)-LBG [Linde, Buzo and Gray, 1980] algorithm for designing SRS. MFCC feature is extracted from the input speech and then vector quantization of the extracted MFCC features is done using VQLBG algorithm. It reduces the dimensionality of the input vector .These MFCCs are used as the speaker features for matching via Support Vector Machine (SVM) method. The experimental results show that the proposed textdependent speaker identification system gives an accuracy rate of 95.0%.

No abstract

Phoneme is the smallest analogous unit of sound employed to form meaningful contrast between utterances. Hidden Markov Model (HMM), Gaussian Mixture model (GMM) and Artificial Neural Network (ANN) have been used in this paper to measure the accuracy and performance of recognition system using toolkits HTK, Sphinx3 and Quicknet, which are freely available for academic works. In this paper the performance of an ASR System based on Accuracy has been compared with TIMIT database.

Hyperthermia is a thermal therapy for cancer treatment in which body temperature is exposed to elevated temperature of 40-42 o C. Microwave ablation has a potential to be sensitive to changes in the dielectric tissue parameters which results in damaging abnormal tissues. In order to produce heat in the focused area microwave signals are adjusted in time, frequency and strength. The commonly used frequencies in microwave imaging systems are 415MHZ and 2.45GHZ which are transmitted from the antennas enclosing the relevant body part. This paper presents a highly efficient E-Shape micro strip patch microwave antenna operated at 2.45 GHz which can be used in various applicators for hyperthermia treatment system. The simulation is done on IE3D simulator. The results are compared at two feeding points 1 and 2 for the frequency 2.45GHZ. It gives return loss of-19.3dB, bandwidth of 6.2dB and the antenna efficiency of 92% for feeding point 1 which proves to be highly effective in communication.