The "SIVA" speech database for speaker verification: description and evaluation
نویسندگان
چکیده
The description and characterization of the Italian speech database SIVA is given. After a brief review of the available corpora designed for speaker verification task, we introduce the “Speaker Identification and Verification Archives: SIVA”, a database that consists actually of more than two thousands calls, collected over the public switched telephone network. A detailed description of speech material, a proposal for an acoustic characterization, and the performances obtained using a speaker verification reference system are presented and discussed herein after.
منابع مشابه
A Comparative Study of Gender and Age Classification in Speech Signals
Accurate gender classification is useful in speech and speaker recognition as well as speech emotion classification, because a better performance has been reported when separate acoustic models are employed for males and females. Gender classification is also apparent in face recognition, video summarization, human-robot interaction, etc. Although gender classification is rather mature in a...
متن کاملAutomatic Speech Emotion and Speaker Recognition based on Hybrid GMM and FFBNN
In this paper we present text dependent speaker recognition with an enhancement of detecting the emotion of the speaker prior using the hybrid FFBN and GMM methods. The emotional state of the speaker influences recognition system. Mel-frequency Cepstral Coefficient (MFCC) feature set is used for experimentation. To recognize the emotional state of a speaker Gaussian Mixture Model (GMM) is used ...
متن کاملBenchmarking Feature Selection Techniques on the Speaker Verification Task
As a part of our preparation for the 2004 NIST Speaker Recognition Evaluation, we evaluated the practical usefulness of five feature ranking and selection methods. Seeking for improvement of the overall performance of our speaker verification system, WCL-1, we studied the relevance and contribution of the individual speech parameters. Furthermore, the choice of an appropriate dimensionality of ...
متن کاملText-dependent speaker verification: Classifiers, databases and RSR2015
The RSR2015 database, designed to evaluate text-dependent speaker verification systems under different durations and lexical constraints has been collected and released by the Human Language Technology (HLT) department at Institute for Infocomm Research (IR) in Singapore. English speakers were recorded with a balanced diversity of accents commonly found in Singapore. More than 151 h of speech d...
متن کاملEvaluation of speech parameterization methods for speaker recognition
Utilizing the well-known 2001 NIST Speaker Recognition Evaluation database, we offer a comparative evaluation of various speech parameterization methods with respect to their usefulness to the speaker verification task. Both Discrete Fourier Transform (DFT) and Discrete Wavelet Packet Transform (DWPT)–based techniques are considered. For each type of the speech features, the speaker recognition...
متن کامل