Brendan Baker
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Brendan Baker has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Sridha Sridharan
Queensland University of Technology
5 shared publications - Mitchell McLaren
Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia
2 shared publications Robert Vogt
Speech & Audio Laboratory, Queensland University of Technology, Brisbane, Australia
2 shared publications- Eddie Wong
Speech and Audio Research Laboratory, Queensland University of Technology, GPO Box 2434, 2 George St, Brisbane, Australia, QLD 4001
1 shared publication Robbie Vogt
Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia
1 shared publicationRoy Wallace
Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia
1 shared publication
Latest Publications
- 3 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 19 (6) , 1677-1687
Discriminative Optimization of the Figure of Merit for Phonetic Spoken Term Detection
This paper proposes to improve spoken term detection (STD) accuracy by optimizing the figure of merit (FOM). In this paper, the index takes the form of a phonetic posterior-feature matrix. Accuracy is improved by formulating STD as a discriminative training problem and directly optimizing the FOM, through its use as an objective function to train a transformation of the index. The outcome of indexing is then a matrix of enhanced posterior-features that are directly tailored for the STD task. The technique is shown to improve the FOM by up to 13% on held-out data. Additional analysis explores the effect of the technique on phone recognition accuracy, examines the actual values of the learned transform, and demonstrates that using an extended training data set results in further improvement in the FOM.
- 3 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 19 (6) , 1677-1687
Discriminative Optimization of the Figure of Merit for Phonetic Spoken Term Detection
This paper proposes to improve spoken term detection (STD) accuracy by optimizing the figure of merit (FOM). In this paper, the index takes the form of a phonetic posterior-feature matrix. Accuracy is improved by formulating STD as a discriminative training problem and directly optimizing the FOM, through its use as an objective function to train a transformation of the index. The outcome of indexing is then a matrix of enhanced posterior-features that are directly tailored for the STD task. The technique is shown to improve the FOM by up to 13% on held-out data. Additional analysis explores the effect of the technique on phone recognition accuracy, examines the actual values of the learned transform, and demonstrates that using an extended training data set results in further improvement in the FOM.
- 19 August 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 5 (4) , 802-809
A Comparison of Session Variability Compensation Approaches for Speaker Verification
This paper compares two of the leading techniques for session variability compensation in the context of support vector machine (SVM) speaker verification using Gaussian mixture model (GMM) mean supervectors: joint factor analysis (JFA) modeling and nuisance attribute projection (NAP). Motivation for this comparison comes from the distinctly different domains in which these techniques are employed-the probabilistic GMM domain versus the discriminative SVM kernel. A theoretical analysis is given comparing the JFA and NAP approaches to variability compensation. The role of speaker factors in the factor analysis model is also contrasted against the scatter difference NAP objective of retaining speaker information in the SVM kernel space. These methods for retaining speaker variation are found to provide improved verification performance over the removal of channel effects alone. Overall, experimental results on the NIST 2006 and 2008 SRE corpora demonstrate the effectiveness of both JFA and NAP techniques for reducing the effects of variability. However, the overheads associated with the implementation of JFA may make NAP a more attractive technique due to its simple yet effective approach to variability compensation.
- 19 August 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 5 (4) , 802-809
A Comparison of Session Variability Compensation Approaches for Speaker Verification
This paper compares two of the leading techniques for session variability compensation in the context of support vector machine (SVM) speaker verification using Gaussian mixture model (GMM) mean supervectors: joint factor analysis (JFA) modeling and nuisance attribute projection (NAP). Motivation for this comparison comes from the distinctly different domains in which these techniques are employed-the probabilistic GMM domain versus the discriminative SVM kernel. A theoretical analysis is given comparing the JFA and NAP approaches to variability compensation. The role of speaker factors in the factor analysis model is also contrasted against the scatter difference NAP objective of retaining speaker information in the SVM kernel space. These methods for retaining speaker variation are found to provide improved verification performance over the removal of channel effects alone. Overall, experimental results on the NIST 2006 and 2008 SRE corpora demonstrate the effectiveness of both JFA and NAP techniques for reducing the effects of variability. However, the overheads associated with the implementation of JFA may make NAP a more attractive technique due to its simple yet effective approach to variability compensation.
- 3 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 18 (6) , 1496-1506
Data-Driven Background Dataset Selection for SVM-Based Speaker Verification
The recently proposed data-driven background dataset refinement technique provides a means of selecting an informative background for support vector machine (SVM)-based speaker verification systems. This paper investigates the characteristics of the impostor examples in such highly informative background datasets. Data-driven dataset refinement individually evaluates the suitability of candidate impostor examples for the SVM background prior to selecting the highest-ranking examples as a refined background dataset. Further, the characteristics of the refined dataset were analyzed to investigate the desired traits of an informative SVM background. The most informative examples of the refined dataset were found to consist of large amounts of active speech and distinctive language characteristics. The data-driven refinement technique was shown to filter the set of candidate impostor examples to produce a more disperse representation of the impostor population in the SVM kernel space, thereby reducing the number of redundant and less-informative examples in the background dataset. Furthermore, data-driven refinement was shown to provide performance gains when applied to the difficult task of refining a small candidate dataset that was mismatched to the evaluation conditions.
- 3 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 18 (6) , 1496-1506
Data-Driven Background Dataset Selection for SVM-Based Speaker Verification
The recently proposed data-driven background dataset refinement technique provides a means of selecting an informative background for support vector machine (SVM)-based speaker verification systems. This paper investigates the characteristics of the impostor examples in such highly informative background datasets. Data-driven dataset refinement individually evaluates the suitability of candidate impostor examples for the SVM background prior to selecting the highest-ranking examples as a refined background dataset. Further, the characteristics of the refined dataset were analyzed to investigate the desired traits of an informative SVM background. The most informative examples of the refined dataset were found to consist of large amounts of active speech and distinctive language characteristics. The data-driven refinement technique was shown to filter the set of candidate impostor examples to produce a more disperse representation of the impostor population in the SVM kernel space, thereby reducing the number of redundant and less-informative examples in the background dataset. Furthermore, data-driven refinement was shown to provide performance gains when applied to the difficult task of refining a small candidate dataset that was mismatched to the evaluation conditions.
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Speaker Verification using Hidden Markov Models in a Multilingual Text-constrained Framework
This paper expands upon previous work, making use of a multilingual framework for text-constrained speaker verification. The framework attempts to overcome some of the restrictions found with previously developed monolingual text-constrained techniques. Pseudo-syllabic segmentation is used in order to extract regions for the constrained recognition. In this study, a comparison between Gaussian mixture models and hidden Markov models is presented for modelling these syllabic events. Results are presented for the NIST 2004 speaker recognition evaluation corpus. The results suggest that temporal patterns within the frame sequences are present and able to be exploited through use of Markovian modelling. The HMM based system is also compared against a traditional global acoustic GMM-UBM speaker verification system, with encouraging results presented
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Speaker Verification using Hidden Markov Models in a Multilingual Text-constrained Framework
This paper expands upon previous work, making use of a multilingual framework for text-constrained speaker verification. The framework attempts to overcome some of the restrictions found with previously developed monolingual text-constrained techniques. Pseudo-syllabic segmentation is used in order to extract regions for the constrained recognition. In this study, a comparison between Gaussian mixture models and hidden Markov models is presented for modelling these syllabic events. Results are presented for the NIST 2004 speaker recognition evaluation corpus. The results suggest that temporal patterns within the frame sequences are present and able to be exploited through use of Markovian modelling. The HMM based system is also compared against a traditional global acoustic GMM-UBM speaker verification system, with encouraging results presented
- 31 August 2005
- Published by Elsevier in Computer Speech & Language
- Vol. 20 (2-3) , 276-302
A syllable-scale framework for language identification
- 31 August 2005
- Published by Elsevier in Computer Speech & Language
- Vol. 20 (2-3) , 276-302
A syllable-scale framework for language identification