Speaker recognition is the task of establishing identity of an individual based on his/her voice. It has a significant potential as a convenient biometric method for telephony applications and does not require sophisticated or dedicated hardware. <br /

Automatic Speaker Recognition: Modelling, Feature Extraction and Effects of Clinical Environment

The relative importance of the temporal characteristics of speech for text-dependent and text-constrained speaker verification is investigated. A novel scheme is proposed using a common set of Gaussian components to form various HMM and GMM configurations, establishing a systematic transition from text-dependent to text-constrained speaker verification, and resulting in a novel alternative to conventional GMM-UBM training. Experimental results indicate that the intra-word temporal characteristics of speech do not contribute significantly to performance, however the inter-word temporal characteristics can be used during both enrollment and testing to improve verification performance.

A study of the relative importance of temporal characteristics in text dependent and text constrained speaker verification

This research presents new text-independent speaker recognition system with multivariate tools such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA) embedded into the recognition system after the feature extraction step. The proposed approach evaluates the performance of such a recognition system when trained and used in clean and noisy environments. Additive white Gaussian noise and convolutive noise are added. Experiments were carried out to investigate the robust ability of PCA and ICA using the designed approach. The application of ICA improved the performance of the speaker recognition model when compared to PCA. Experimental results show that use of ICA enabled extraction of higher order statistics thereby capturing speaker dependent statistical cues in a text-independent recognition system. The results show that ICA has a better de-correlation and dimension reduction property than PCA. To simulate a multi environment system, we trained our model such that every time a new speech signal was read, it was contaminated with different types of noises and stored in the database. Results also show that ICA outperforms PCA under adverse environments. This is verified by computing recognition accuracy rates obtained when the designed system was tested for different train and test SNR conditions with additive white Gaussian noise and test delay conditions with echo effect.

Text-independent speaker recognition

Speaker Identification (SI) approaches based on discriminative Vector Quantization (VQ) and data fusion techniques are presented in this dissertation. The SI approaches based on Discriminative VQ (DVQ) proposed in this dissertation are the DVQ for SI (DVQSI), the DVQSI with Unique speech feature vector space segmentation for each speaker pair (DVQSI-U), and the Adaptive DVQSI (ADVQSI) methods. The difference of the probability distributions of the speech feature vector sets from various speakers (or speaker groups) is called the interspeaker variation between speakers (or speaker groups). The interspeaker variation is the measure of template differences between speakers (or speaker groups). All DVQ based techniques presented in this contribution take advantage of the interspeaker variation, which are not exploited in the previous proposed techniques by others that employ traditional VQ for SI (VQSI). All DVQ based techniques have two modes, the training mode and the testing mode. In the training mode, the speech feature vector space is first divided into a number of subspaces based on the interspeaker variations. Then, a discriminative weight is calculated for each subspace of each speaker or speaker pair in the SI group based on the interspeaker variation. The subspaces with higher interspeaker variations play more important roles in SI than the ones with lower interspeaker variations by assigning larger discriminative weights. In the testing mode, discriminative weighted average VQ distortions instead of equally weighted average VQ distortions are used to make the SI decision. The DVQ based techniques lead to higher SI accuracies than VQSI.

/pdf/speaker-identification-based-on-discriminative-vector-omgzv6q4ow.pdf

Speaker Identification Based On Discriminative Vector Quantization And Data Fusion

In this paper, we present a detailed review of the approaches for speaker verification. Speaker verification is a binary class problem of either accepting or rejecting a claimant speaker on the basis of the matching accuracy of the claimant’s test utterance with his/her train utterance. It has been observed that text-independent speaker verification gives much more flexibility as compared to text-dependent speaker verification. However, it is easier to attain better verification accuracy in the text-dependent mode as compared to its counterpart. In addition, our focus has been on giving an overview of the most popular databases available for this purpose as well as on the various feature extraction methods and modeling tools used in the speaker verification systems.

Speaker Verification Systems: A Comprehensive Review

This paper compares a mixture-Gaussian vector quantisation (VQ) method, ergodic continuous hidden Markov models (CHMMs) and phone-level left-to-right CHMMs for text-independent speaker recognition. These three methods represent a progression of phonetic specificity prior to the generation of probabilities against which speakers are compared. The mixture-Gaussian VQ uses a single distribution for all phones, the ergodic CHMM uses several distributions which have been shown in a previous text-independent speaker recognition study to represent broad phonetic classes, and the phone-based left-to-right CHMM uses many distributions representing the specific phones in the test utterance. Our experiments with speaker recognition on 40 TIMIT speakers show that the recognition rates of the mixture-Gaussian VQ, ergodic CHMMs and phone-based left-to-right CHMMs are 87.5%, 87.5% and 100% respectively. >

B. Millar

Papers

A comparative study of mixture-Gaussian VQ, ergodic HMMs and left-to-right HMMs for speaker recognition