Class-Discriminative Weighted Distortion Measure for VQ-based Speaker Identification
Tomi Kinnunen,Ismo Kärkkäinen +1 more
TLDR
A weighted distortion measure is introduced that takes into account the correlations between the known models in the speaker database and larger weights are assigned to vectors that have high discriminating power between the speakers and vice versa.Abstract:
We consider the distortion measure in vector quantization based speaker identification system. The model of a speaker is a codebook generated from the set of feature vectors from the speakers voice sample. The matching is performed by evaluating the distortions between the unknown speech sample and the models in the speaker database. In this paper, we introduce a weighted distortion measure that takes into account the correlations between the known models in the database. Larger weights are assigned to vectors that have high discriminating power between the speakers and vice versa.read more
Citations
More filters
Journal ArticleDOI
Real-time speaker identification and verification
TL;DR: This paper focuses on optimizing vector quantization (VQ) based speaker identification, which reduces the number of test vectors by pre-quantizing the test sequence prior to matching, and thenumber of speakers by pruning out unlikely speakers during the identification process.
Spectral Features for Automatic Text-Independent Speaker Recognition
TL;DR: This thesis attempts to see the feature extraction as a whole, starting from understanding the speech production process, what is known about speaker individuality, and then going to the methods adopted directly from the speech recognition task.
Proceedings ArticleDOI
A Speaker Identification System Using MFCC Features with VQ Technique
TL;DR: Feature vectors from speech are extracted by using Mel-Frequency Cepstral Coefficients and Vector Quantization technique is implemented through Linde-Buzo-Gray algorithm to check the accuracy of the developed speaker identification system in non-ideal conditions.
Proceedings ArticleDOI
Real-time speaker identification.
TL;DR: The number of test vectors is reduced by pre-quantizing the test sequence prior to matching, and the number of speakers are reduced by pruning out unlikely speakers during the identification process by optimizing vector quantization (VQ) based speaker identification.
Dissertation
Optimizing Spectral Feature Based Text-Independent Speaker Recognition
TL;DR: In this thesis, the subcomponents of text-independent speaker recognition are studied, and several improvements are proposed for achieving better accuracy and faster processing.
References
More filters
Book
Self-Organizing Maps
TL;DR: The Self-Organising Map (SOM) algorithm was introduced by the author in 1981 as mentioned in this paper, and many applications form one of the major approaches to the contemporary artificial neural networks field, and new technologies have already been based on it.
Book
Fundamentals of speech recognition
TL;DR: This book presents a meta-modelling framework for speech recognition that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of manually modeling speech.
Journal ArticleDOI
An Algorithm for Vector Quantizer Design
Y. Linde,A. Buzo,Robert M. Gray +2 more
TL;DR: An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data.
Book
Vector Quantization and Signal Compression
Allen Gersho,Robert M. Gray +1 more
TL;DR: The author explains the design and implementation of the Levinson-Durbin Algorithm, which automates the very labor-intensive and therefore time-heavy and expensive process of designing and implementing a Quantizer.