In this paper we propose an unsupervised approach to speaker segmentation using autoassociative neural network (AANN). Speaker segmentation aims at finding speaker change points in a speech signal which is an important preprocessing step to audio indexing, spoken document retrieval and multi speaker diarization. The method extracts the speaker specific information from the Mel frequency cepstra...

In this paper, a novel method using 3D Convolutional Neural Network (3D-CNN) architecture has been proposed for speaker verification in the text-independent setting. At the development phase, a CNN is trained to classify speakers at the utterance-level. In the enrollment stage, the trained network is utilized to directly create a speaker model for each speaker based on the extracted features. F...

Human Voice is characteristic for an individual. The ability to recognize the speaker by his/her voice can be a valuable biometric tool with enormous commercial as well as academic potential. Commercially, it can be utilized for ensuring secure access to any system. Academically, it can shed light on the speech processing abilities of the brain as well as speech mechanism. In fact, this feature...

Research has shown that corrective information is produced with higher prosodic prominence than non-corrective information. However, it remains unclear how corrective prosody is realized in different communicative settings. We conducted two production experiments to investigate whether interlocutors’ prosodic realization of corrective focus depends on each other’s knowledge state. Participants ...

This paper deals with the task of speaker recognition in fourwire training and two-wire testing conditions. Instead of performing blind speaker diarization before the recognition stage, we directly perform the recognition on the nonsegmented (or imperfectly diarized) speech. We present an analysis of the problem with respect to three different speaker recognition systems and propose improved re...

Current text–to–speech systems are developed using studio-recorded speech in a neutral style or based on acted emotions. However, the proliferation of media sharing sites would allow developing a new generation of speech–based systems which could cope with spontaneous and styled speech. This paper proposes an architecture to deal with realistic recordings and carries out some experiments on uns...

This paper addresses the problem of speaker characterization in the speaker-dependent speech recognition problem. Speaker Adaptation and Normalization techniques are designed to reduce the mismatch introduced by inter-speaker variability. Yet there is another source of mismatch introduced by intra-speaker variability. Indeed, the speaking style of a speaker depends on the nature of the speech u...

One of the problems of the speaker-independent continuous speech recognition systems is their inability to cope with the inter-speaker variability. When we find test speakers with different characteristics from the ones presented in the training pool we observe a large degradation on the system performance. To overcome this problem speaker-adaptation techniques may be used to provide near speak...

A speaker verification system automatically accepts or rejects a claimed identity of a speaker based on a speech sample. Recently, a major progress was made in speaker verification which leads to mass market adoption, such as in smartphone and in online commerce for user authentication. A major concern when deploying speaker verification technology is whether a system is robust against spoofing...

This paper introduces the performance evaluation of statististical approaches for Automatic-text-independent Speaker Recognition system. Automatic-text-independent Speaker Recognition system is to quickly and accurately identify the person from his/her voice. The study on the effect of feature vector size for good speaker recognition demonstrates that the feature vector size in the range of 18-...