Brendan Baker

Pennsylvania State University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Sridha Sridharan

Queensland University of Technology

Mitchell McLaren

Speech Pathology Australia

Robbie Vogt

Queensland University of Technology

Robert Vogt

Queensland University of Technology

Subramanian Sridharan

Queensland University of Technology

Michael Mason

Perth Children's Hospital

E.M.C. Wong

Goldsmiths University of London

Roger E. Beaty

Pennsylvania State University

Roy Wallace

Queensland University of Technology

T. Z. Martin

Harvard University

Cooperative Institutions

Queensland University of Technology

University of Nebraska–Lincoln

University of Kentucky

University of Kansas

California State University, Fullerton

American College of Surgeons

Speech Pathology Australia

California State University, San Bernardino

Oklahoma State University

Pennsylvania State University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

A study of phonetic feature representations for SVM-based speaker verification

Erik E. Merkley Brendan Baker Robert Vogt Sridha Sridharan

We investigate an alternative formulation of phonetic feature representations for SVM-based speaker verification. The new features are based on conditional likelihood representations rather than the joint-likelihood or bag-of-ngram calculations traditionally used. Conditional likelihoods are shown to be a more natural method of modelling phonetic information, and improve upon conventional joint likelihoods in a number of cases. The problem of feature normalisation is also examined, with a previously proposed non-parametric method based on rank shown to be particularly useful. Combinations of feature representations are examined and the potential for complementary information between joint and conditional likelihoods considered. Additionally, feature compensation is applied to conditional likelihoods with considerable improvement in performance.

Feature (linguistics)

Rank (graph theory)

Conditional probability distribution

10.1109/icspcs.2008.4813708

Cite

Citations (0)

Discriminative Optimization of the Figure of Merit for Phonetic Spoken Term Detection

IEEE Transactions on Audio Speech and Language Processing (2010)

Roy Wallace Brendan Baker Robbie Vogt Sridha Sridharan

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.

Discriminative model

Figure of Merit

Transformation matrix

Feature (linguistics)

10.1109/tasl.2010.2096215

Cite

Citations (10)

On the Use of Factor Analysis with Restricted Target Data in Speaker Verification

Odyssey (2010)

Javier Gónzalez-Domínguez Brendan Baker Robbie Vogt Joaquín González-Rodríguez Sridha Sridharan

Factor Analysis (FA) based techniques have become the state of the art in automatic speaker verification thanks to their great ability to model session variability. This ability, in turn, relies on accurately estimating a session variability subspace for the operating conditions of interest. In cases such as forensic speaker recognition, however, this requirement cannot always be satisfied due to the very limited quantity of appropriate development data. As a first step toward understanding the application of FA in these restricted data scenarios, this work analyzes the performance of FA with very limited development data and then explores several FA estimation methods that augment the target domain data with examples from a data-rich domain. Experiments on NIST SRE 2006 microphone data conditions demonstrate that telephone data can be effectively exploited to improve performance over a baseline system. Index Terms: Session Variability, Factor Analysis, Forensic Speaker Recognition.

NIST

Speaker Verification

Factor (programming language)

Baseline (sea)

Source

Cite

Citations (7)

A comparison of session variability compensation approaches for speaker verification

Mitchell McLaren Robert Vogt Brendan Baker Sridha Sridharan

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.

Discriminative model

NIST

Variation (astronomy)

Source

Cite

Citations (0)

Exploiting multiple feature sets in data-driven impostor dataset selection for speaker verification

Mitchell McLaren Brendan Baker Robert Vogt Sridha Sridharan

This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration demonstrate the versatility of background dataset refinement. This work also extends on the originally proposed technique to exploit support vector coefficients as an impostor suitability metric in the data-driven selection process. Using support vector coefficients improved the performance of the refined datasets in the evaluation of unseen data. Further, attempts are made to exploit the differences in impostor example suitability measures from varying features spaces to provide added robustness.

Robustness

Speaker Verification

Feature (linguistics)

Feature vector

Source

Cite

Citations (0)

A Presynaptic K+ Channel-Independent Neurotransmitter Release Mechanism Caused by Serotonin May Exist in Crayfish

Brendan Baker Brian Marion

Recent studies on the sea-slug Aplysia have shown that the neurotransmitter serotonin (5-HT) may trigger an additional ion-channel-independent mechanism that contributes to the presynaptic release of neurotransmitter thereby enhancing excitatory post-synaptic potential (EPSP) sizes and facilitation in chemical synapses beyond what is already known to be caused by 5-HT’s inhibition of K+ channels. Though numerous studies of this mechanism have been performed on Aplysia , few or none have been done on crayfish. In order to test the universality of this additional K+ channel-independent mechanism in other organisms, we devised a system of experiments attempting to isolate the mechanism in the neuromuscular junction (NMJ) of the superficial crayfish extensor muscle. By blocking presynaptic K+ channels through application of the drug 3-4 diaminopyridine (3-4 DAP), we tried to account for how much the K+ channels contributed to overall EPSP enhancement and facilitation when exposed to 5-HT. Our results, however, contradicted our predictions; 3-4 DAP decreased both EPSP amplitude and facilitation in both test conditions. This, along with some apparently inconsistent behavior between experimentation days, prevents us from being able to support the mechanism’s existence. Nevertheless, the broadened shapes of the experimental EPSPs hint towards presynaptic action potential lengthening under our test conditions, a sign that this K+ channel-independent process may in fact exist in crayfish.

Facilitation

Aplysia

Neural facilitation

Source

Cite

Citations (0)

Divergent Semantic Integration (DSI): Extracting Creativity from Narratives with Distributional Semantic Modeling

Dan R. Johnson James C. Kaufman Brendan Baker John Patterson Baptiste Barbot

We developed a novel conceptualization of one component of creativity in narratives by integrating creativity theory and distributional semantics theory. We termed the new construct, divergent semantic integration (DSI), defined as the extent to which a narrative connects divergent ideas. Across nine studies, 27 different narrative prompts and over 3,500 short narratives, we compared six models of DSI that varied in their computational architecture. The best performing model employed Bidirectional Encoder Representations Transformer (BERT), which generates context-dependent numerical representations of words (i.e., embeddings). BERT DSI scores demonstrated impressive predictive power, explaining up to 72% of the variance in human creativity ratings, even approaching human inter-rater reliability for some tasks. BERT DSI scores showed equivalently high predictive power for expert and non-expert human ratings of creativity in narratives. Critically, DSI scores generalized across Ethnicity and English language proficiency, including individuals identifying as Hispanic and L2 English speakers. The integration of creativity and distributional semantics theory has substantial potential to generate novel hypotheses about creativity and novel operationalizations of its underlying processes and components. To facilitate new discoveries across diverse disciplines, we provide a tutorial with code (osf.io/ath2s) on how to compute DSI and a web app (semdis.wlu.psu.edu) to freely retrieve DSI scores.

Computational Creativity

10.31234/osf.io/fmwgy

Cite

Citations (6)

Noise robust voice activity detection using features extracted from the time-domain autocorrelation function

Interspeech 2022 (2010)

Houman Ghaemmaghami Brendan Baker Robert Vogt Sridha Sridharan

This paper presents a method of voice activity detection (VAD) for high noise scenarios, using a noise robust voiced speech detection feature. The developed method is based on the fusion of two systems. The first system utilises the maximum peak of the normalised time-domain autocorrelation function (MaxPeak). The second zone system uses a novel combination of cross-correlation and zero-crossing rate of the normalised autocorrelation to approximate a measure of signal pitch and periodicity (CrossCorr) that is hypothesised to be noise robust. The score outputs by the two systems are then merged using weighted sum fusion to create the proposed autocorrelation zero-crossing rate (AZR) VAD. Accuracy of AZR was compared to state of the art and standardised VAD methods and was shown to outperform the best performing system with an average relative improvement of 24.8% in half-total error rate (HTER) on the QUT-NOISE-TIMIT database created using real recordings from high-noise environments.

Autocorrelation technique

Pitch detection algorithm

10.21437/interspeech.2010-776

Cite

Citations (44)

Data-Driven Impostor Selection for T-Norm Score Normalisation and the Background Dataset in SVM-Based Speaker Verification

Lecture notes in computer science (2009)

Mitchell McLaren Robbie Vogt Brendan Baker Sridha Sridharan

NIST

Speaker Verification

Training set

Data set

Relevance

10.1007/978-3-642-01793-3_49

Cite

Citations (7)

Pitch and Energy Trajectory Modelling in a Syllable Length Temporal Framework for Language Identification

T. Z. Martin E.M.C. Wong Brendan Baker Michael Mason Subramanian Sridharan

Recent studies have indicated that language identity is encapsulated in a more complicated manner to that represented by short term acoustic features. In particular, trajectory information over syllable-like durations have shown significant promise. This study introduces a novel three-tiered language identification approach which incorporates this information as well as acoustic context in the form of broad syllabic events. Experimental results using the CallFriend database demonstrate the effectiveness of these systems at providing complementary information to a GMM based system.

Syllabic verse

Identification

Source

Cite

Citations (6)