The NIST 2014 Speaker Recognition i-vector Machine Learning Challenge

By Alan McCree, Douglas A. Reynolds, Daniel Garcia-Romero, Tomi H. Kinnunen, Craig S. Greenberg, D. Bansé, G. Doddington, J. Godfrey, Alvin F. Martin, Mark A. Przybocki. 2014

108 citations recorded by the source corpus.

During late-2013 through mid-2014 NIST coordinated a special machine learning challenge based on the i-vector paradigm widely used by state-of-the-art speaker recognition systems. The i-vector challenge was run entirely online and used as source data fixed-length feature vectors projected into a low-dimensional space (i-vectors) rather than audio recordings. These changes made the challenge more readily accessible, enabled system comparison with consistency in the front-end and in the amount and type of training data, and facilitated exploration of many more approaches than would be possible in a single evaluation as traditionally run by NIST. Compared to the 2012 NIST Speaker Recognition Evaluation, the i-vector challenge saw approximately twice as many participants, and a nearly two orders of magnitude increase in the number of systems submitted for evaluation. Initial results indicate that the leading system achieved a relative improvement of approximately 38% over the baseline system.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

End-to-end text-dependent speaker verification (2015, background): “A common choice is to average the i-vectors [19] or d-vectors [15, 4] of these utterances.”
Deep Metric Learning: A Survey (2019, unknown): “NIST i-vector [78] Triplet Network [87] 2.”
Curie: A method for protecting SVM Classifier from Poisoning Attack (2016, unknown): “Machine learning techniques are widely used in areas such as biometric authentication [14], speaker identiﬁcation [12], malware detection in mobile platforms [17] etc.”
Improving speaker recognition performance in the domain adaptation challenge using deep neural networks (2014, background): “Recently, NIST has proposed an i-vector challenge (IVC) [15] in which an unlabeled IND dataset is provided but no OOD data is given.”