Text and Language-Independent Speaker Recognition Using Suprasegmental Features and Support Vector Machines
17 Aug 2009-Vol. 40, pp 307-317
TL;DR: The presence of the speaker-specific suprasegmental information in the Linear Prediction (LP) residual signal is demonstrated and support Vector Machine is used to classify the patterns in the variance of the autocorrelation sequence for the speaker recognition task.
Abstract: In this paper, presence of the speaker-specific suprasegmental information in the Linear Prediction (LP) residual signal is demonstrated. The LP residual signal is obtained after removing the predictable part of the speech signal. This information, if added to existing speaker recognition systems based on segmental and subsegmental features, can result in better performing combined system. The speaker-specific suprasegmental information can not only be perceived by listening to the residual, but can also be seen in the form of excitation peaks in the residual waveform. However, the challenge lies in capturing this information from the residual signal. Higher order correlations among samples of the residual are not known to be captured using standard signal processing and statistical techniques. The Hilbert envelope of residual is shown to further enhance the excitation peaks present in the residual signal. A speaker-specific pattern is also observed in the autocorrelation sequence of the Hilbert envelope, and further in the statistics of this autocorrelation sequence. This indicates the presence of the speaker-specific suprasegmental information in the residual signal. In this work, no distinction between voiced and unvoiced sounds is done for extracting these features. Support Vector Machine (SVM) is used to classify the patterns in the variance of the autocorrelation sequence for the speaker recognition task.
Citations
More filters
Posted Content•
TL;DR: This paper introduces iQIYI-VID, the largest video dataset for multi-modal person identification, and proposed a Multi- modal Attention module to fuse multi-Modal features that can improve person identification considerably.
Abstract: Person identification in the wild is very challenging due to great variation in poses, face quality, clothes, makeup and so on. Traditional research, such as face recognition, person re-identification, and speaker recognition, often focuses on a single modal of information, which is inadequate to handle all the situations in practice. Multi-modal person identification is a more promising way that we can jointly utilize face, head, body, audio features, and so on. In this paper, we introduce iQIYI-VID, the largest video dataset for multi-modal person identification. It is composed of 600K video clips of 5,000 celebrities. These video clips are extracted from 400K hours of online videos of various types, ranging from movies, variety shows, TV series, to news broadcasting. All video clips pass through a careful human annotation process, and the error rate of labels is lower than 0.2\%. We evaluated the state-of-art models of face recognition, person re-identification, and speaker recognition on the iQIYI-VID dataset. Experimental results show that these models are still far from being perfect for the task of person identification in the wild. We proposed a Multi-modal Attention module to fuse multi-modal features that can improve person identification considerably. We have released the dataset online to promote multi-modal person identification research.
30 citations
Cites methods from "Text and Language-Independent Speak..."
...Speaker recognition has been approached by applying a variety of machine learning models [4, 5, 12], either standard or specifically designed, to speech features such as MFCC [34]....
[...]
...The CNN model is trained as a classification model using the Dev part of Voxceleb2 dataset [5] with 5994 speakers, 14% of the data is used as evaluation while the rest as training data....
[...]
References
More filters
Book•
16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
Abstract: From the Publisher:
This book represents the most comprehensive treatment available of neural networks from an engineering perspective. Thorough, well-organized, and completely up to date, it examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks. Written in a concise and fluid manner, by a foremost engineering textbook author, to make the material more accessible, this book is ideal for professional engineers and graduate students entering this exciting field. Computer experiments, problems, worked examples, a bibliography, photographs, and illustrations reinforce key concepts.
29,130 citations
01 Jan 1998
TL;DR: Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Abstract: A comprehensive look at learning and generalization theory. The statistical theory of learning and generalization concerns the problem of choosing desired functions on the basis of empirical data. Highly applicable to a variety of computer science and robotics fields, this book offers lucid coverage of the theory as a whole. Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
26,531 citations
01 Apr 1975
TL;DR: This paper gives an exposition of linear prediction in the analysis of discrete signals as a linear combination of its past values and present and past values of a hypothetical input to a system whose output is the given signal.
Abstract: This paper gives an exposition of linear prediction in the analysis of discrete signals The signal is modeled as a linear combination of its past values and present and past values of a hypothetical input to a system whose output is the given signal In the frequency domain, this is equivalent to modeling the signal spectrum by a pole-zero spectrum The major part of the paper is devoted to all-pole models The model parameters are obtained by a least squares analysis in the time domain Two methods result, depending on whether the signal is assumed to be stationary or nonstationary The same results are then derived in the frequency domain The resulting spectral matching formulation allows for the modeling of selected portions of a spectrum, for arbitrary spectral shaping in the frequency domain, and for the modeling of continuous as well as discrete spectra This also leads to a discussion of the advantages and disadvantages of the least squares error criterion A spectral interpretation is given to the normalized minimum prediction error Applications of the normalized error are given, including the determination of an "optimal" number of poles The use of linear prediction in data compression is reviewed For purposes of transmission, particular attention is given to the quantization and encoding of the reflection (or partial correlation) coefficients Finally, a brief introduction to pole-zero modeling is given
4,206 citations
01 Sep 1997
TL;DR: A tutorial on the design and development of automatic speaker-recognition systems is presented and a new automatic speakers recognition system is given that performs with 98.9% correct decalcification.
Abstract: A tutorial on the design and development of automatic speaker-recognition systems is presented. Automatic speaker recognition is the use of a machine to recognize a person from a spoken phrase. These systems can operate in two modes: to identify a particular person or to verify a person's claimed identity. Speech processing and the basic components of automatic speaker-recognition systems are shown and design tradeoffs are discussed. Then, a new automatic speaker-recognition system is given. This recognizer performs with 98.9% correct decalcification. Last, the performances of various systems are compared.
1,686 citations
TL;DR: High performance speaker identification and verification systems based on Gaussian mixture speaker models: robust, statistically based representations of speaker identity, evaluated on four publically available speech databases.
1,335 citations