Search

This paper explores speaker identification based on the speaker adaptation via multilinear decomposition of a speaker model.Tucker decomposition of the third order mean Tensor of training speaker yields three subspaces corresponding to each mode. The mean of the mixtures for speakers is expressed as a product of the mixture space and a weight matrix comprising of the other two spaces.We update only the mean of the mixtures for the adaptation stage . During testing, log likelihood is used to identify the scores for the test speakers.Experiments conducted on the TIMIT and NIST 2003 databases shows comparable performance with the baseline even in channel mismatch conditions of the development and enrollment dataset. Furthermore, using higher order tensors, we can easily adapt this problem to include noise and environment factors as well.

One of the major reasons for the performance degradation of a speaker verification (SV) system in real-world conditions is its inability to spot speech regions due to the presence of noise. This work focuses on the role of voice activity detection (VAD) methods in alleviating such shortcomings. The experiments are conducted on the core-core task of the speakers in the wild (SITW) challenge. Two VAD approaches are explored in this work. One of them is the recently proposed self-adaptive VAD and the other is based on vowel-like region (VLR) detection. For evaluating the effectiveness of these approaches, the SV systems are developed using the i-vector framework in the front-end and probabilistic linear discriminant analysis (PLDA) in the back-end. The self-adaptive VAD based system shows better performance compared to the VLR based system in high SNR condition. Under degraded conditions, the VLR based method is relatively more robust compared to self-adaptive VAD. Exploiting these complementary features, significant improvements in the SV performances are noted with the fusion of scores of the two systems.

In this work, the details of AMRITA-TCS and IITGUWAHATI speaker recognition systems submitted to the Speakers in the Wild (SITW) speaker recognition challenge are presented. The AMRITA-TCS system is a fusion of i-vector with a backend probabilistic linear discriminant analysis (i-PLDA) system and a cosine distance features (CDF) with backend support vector machine classifier (CDF-SVM) system, developed using the short term cepstral features, mel frequency cepstral coefficients (MFCC) and power normalized cepstral coefficients (PNCC), respectively. The IITGUWAHATI system is an i-PLDA system using MFCC with a vowel like region (VLR) based feature selection (i-PLDA-VLR). The experimental results reported in this work are based on the core-core condition of the challenge. Finally, a fusion of AMRITA-TCS and IITGUWAHATI speaker recognition systems is carried out that enhances the performance than each of the subsystems.

This work projects the importance of phonetic match between train and test session for a text-independent framework under limited test data condition. The robustness of text-independent speaker verification (SV) tends to fall down with the reduction of the amount of speech involved. From a deployable application oriented system point of view, the amount of speech involved, is expected to be less to ensure user comfort. Keeping this as a priority and based on the literature studies in this direction, a framework is proposed for the development of a text constrained text-independent SV system that emulates the anatomy of the text-dependent framework. This framework recommends having a text constrained speaker model developed using limited data of around 10 sec. The same content is spoken by the user during testing. A baseline system is built over a data collected in a practical scenario where sufficient train and limited test data is used. On evaluating the two systems over i-vector based SV system, the text constrained model based topology is found to work exceedingly well as compared to the conventional method under limited data condition. Further, it was observed that having the phonetic content of the test session in the training session helps in improving the baseline system performance.

Segmentation of line, word and character are one of the critical phases of optical character recognition (OCR). Due to the imperfection in segmentation, most of the recognition system produce poor recognition rate. In this paper we are discussing some novel approach for line, word and character segmentation of printed Manipuri document. Few works has been done for optical character recognition on other Indian script however in case of Manipuri language it is almost negligible. To the best of our knowledge this is the first report on segmentation of documents containing Manipuri script forms. So keeping these things in mind here, in this paper we are discussing some approach to succeed in the above mentioned task. Here first we are discussing about the structure of Manipuri language, and then we discuss some idea for segmentation of line, word and character from degraded Manipuri document. Finally we discuss about various existing recognition technique.

This paper presents a comparative study of the normalization techniques used at feature level in voice password based speaker verification system. The input sample speech is recorded at different instants of time and environment. Hence, there is a variation in the input sample due to the environmental interference, noise, emotions etc. The input sample is a human voice with unique passwords taken/recorded at three different instants of time or day. This input sample is processed using sampling, pre-emphasis, MFCC feature extraction and DTW. In order to enhance the features we have used three different popular feature normalization techniques namely MVN (Mean and Variance Normalization), CMN (Cepstral Mean Normalization) and PCA(Principal Component Analysis) and analyzed the result of each technique individually. The objective of this paper is to compare the performance and efficiency of these techniques and evaluate which of these gives the best verification rate. According to our findings CMN gives the best results.