𝔖 Bobbio Scriptorium
✦   LIBER   ✦

On combining classifiers for speaker authentication

✍ Scribed by Leandro Rodrı́guez-Liñares; Carmen Garcı́a-Mateo; José Luis Alba-Castro

Publisher
Elsevier Science
Year
2003
Tongue
English
Weight
368 KB
Volume
36
Category
Article
ISSN
0031-3203

No coin nor oath required. For personal study only.

✦ Synopsis

Speaker veriÿcation and utterance veriÿcation are examples of techniques that can be used for speaker authentication purposes.

Speaker veriÿcation consists of accepting or rejecting the claimed identity of a speaker by processing samples of his=her voice. Usually, these systems are based on HMM models that try to represent the characteristics of the speakers' vocal tracts.

Utterance veriÿcation systems make use of a set of speaker-independent speech models to recognize a certain utterance. If the utterances consist of passwords, this can be used for identity veriÿcation purposes.

Up to now, both techniques have been used separately. This paper is focused on the problem of how to combine these two sources of information. New architectures are presented to join an utterance veriÿcation system and a speaker veriÿcation system in order to improve the performance in a speaker veriÿcation task.

📜 SIMILAR VOLUMES

Combining classifier decisions for robus
Combining classifier decisions for robust speaker identification
✍ Daniel J. Mashao; Marshalleno Skosan 📂 Article 📅 2006 🏛 Elsevier Science 🌐 English ⚖ 232 KB

In this work, we combine the decisions of two classifiers as an alternative means of improving the performance of a speaker recognition system in adverse environments. The difference between these classifiers is in their feature-sets. One system is based on the popular mel-frequency cepstral coeffic

Classifier combination based on confiden
Classifier combination based on confidence transformation
✍ Cheng-Lin Liu 📂 Article 📅 2005 🏛 Elsevier Science 🌐 English ⚖ 222 KB

This paper investigates the effects of confidence transformation in combining multiple classifiers using various combination rules. The combination methods were tested in handwritten digit recognition by combining varying classifier sets. The classifier outputs are transformed to confidence measures