Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/92542
Title: | Native accent classification via i-vectors and speaker compensation fusion |
Authors: | DeMarco, Andrea Cox, Stephen J. |
Keywords: | Natural language processing (Computer science) Speech processing systems Native language Data structures (Computer science) Dimension reduction (Statistics) -- Data processing Support vector machines Corpora (Linguistics) Discriminant analysis |
Issue Date: | 2013 |
Publisher: | ISCA |
Citation: | DeMarco, A., & Cox, S. J. (2013, May). Native accent classification via i-vectors and speaker compensation fusion. In Interspeech (pp. 1472-1476). |
Abstract: | We present a comprehensive analysis of the use of I-vector based classifiers for the classification of unlabelled acoustic data as native British accents. We demonstrate the different behaviours of various popular dimensionality reduction techniques that have been previously used in problems such as speaker and language classification. Our results show that a fusion of I-vector based systems gives state-of-the-art performance for unlabelled classification of British accent speech data, reaching ∼81% accuracy |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/92542 |
Appears in Collections: | Scholarly Works - InsSSA |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Native_accent_classification_via_i_Vectors_and_speaker_compensation_fusion(2013).pdf | 556.6 kB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.