Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 3
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

A speaker recognition system based on joint factor analysis (JFA) is proposed to improve whispering speakers’ recognition rate under channel mismatch. The system estimated separately the eigenvoice and the eigenchannel before calculating the corresponding speaker and the channel factors. Finally, a channel-free speaker model was built to describe accurately a speaker using model compensation. The test results from the whispered speech databases obtained under eight different channels showed that the correct recognition rate of a recognition system based on JFA was higher than that of the Gaussian Mixture Model-Universal Background Model. In particular, the recognition rate in cellphone channel tests increased significantly.

Go to article

Authors and Affiliations

Gang Lv
Heming Zhao
Download PDF Download RIS Download Bibtex

Abstract

Despite the growing importance of packet switching systems, there is still a shortage of thorough analyses of VoIP transmission effect on speech and speaker recognition performance. Voice over IP transmission systems use packet switching. There is no guarantee of delivery. The main disadvantage of VoIP is a packet loss which has a major impact on the performance experienced by the users of the network. There are several techniques to mask the effects of a packet loss, referred to as packet loss concealment. In this study, the effect of voice transmission over IP on automatic speaker verification system performance was investigated. The analyzed system was based on MAP-EM-GMM modelling methods. Four various speech codecs of H.323 standard were investigated with special emphasis placed on the packet loss phenomenon and various packet loss concealment techniques.
Go to article

Authors and Affiliations

Waldemar Maciejko
Download PDF Download RIS Download Bibtex

Abstract

Biometrics provide an alternative to passwords and pins for authentication. The emergence of machine learning algorithms provides an easy and economical solution to authentication problems. The phases of speaker verification protocol are training, enrollment of speakers and evaluation of unknown voice. In this paper, we addressed text independent speaker verification using Siamese convolutional network. Siamese networks are twin networks with shared weights. Feature space can be learnt easily by training these networks even if similar observations are placed in proximity. Extracted features from Siamese then can be classified using difference or correlation measures. We have implemented a customized scoring scheme that utilizes Siamese’ capability of applying distance measures with the convolutional learning. Experiments made on cross language audios of multi-lingual speakers confirm the capability of our architecture to handle gender, age and language independent speaker verification. Moreover, our designed Siamese network, SpeakerNet, provided better results than the existing speaker verification approaches by decreasing the equal error rate to 0.02.

Go to article

Authors and Affiliations

Hafsa Habib
Huma Tauseef
Muhammad Abuzar Fahiem
Saima Farhan
Ghousia Usman

This page uses 'cookies'. Learn more