2023
Speech Audio Synthesis from Tagged MRI and Non-negative Matrix Factorization via Plastic Transformer
Liu X, Xing F, Stone M, Zhuo J, Fels S, Prince J, El Fakhri G, Woo J. Speech Audio Synthesis from Tagged MRI and Non-negative Matrix Factorization via Plastic Transformer. Lecture Notes In Computer Science 2023, 14226: 435-445. PMID: 38651032, PMCID: PMC11034915, DOI: 10.1007/978-3-031-43990-2_41.Peer-Reviewed Original ResearchWeight mapAudio waveformEnd-to-end deep learning frameworkMatrix factorization-based approachesFactorization-based approachDeep learning frameworkNon-negative matrix factorizationEnd-to-endAdversarial trainingProcess of speech productionTwo-dimensional spectrogramConventional convolutionLearning frameworkMotion featuresTraining samplesAudio synthesisDimension expansionMatrix inputMatrix factorizationTagged MRISpeech productionTransformation modelExperimental resultsSpectrogramPlastic transformation
2022
Tagged-MRI Sequence to Audio Synthesis via Self Residual Attention Guided Heterogeneous Translator
Liu X, Xing F, Prince J, Zhuo J, Stone M, El Fakhri G, Woo J. Tagged-MRI Sequence to Audio Synthesis via Self Residual Attention Guided Heterogeneous Translator. Lecture Notes In Computer Science 2022, 13436: 376-386. PMID: 36820764, PMCID: PMC9942274, DOI: 10.1007/978-3-031-16446-0_36.Peer-Reviewed Original ResearchAudio waveformEnd-to-end deep learning frameworkAdversarial training approachDeep learning frameworkEnd-to-endTwo-dimensional spectrogramAdversarial networkIntermediate representationLearning frameworkResidual attentionDisentanglement strategyAudio synthesisDataset sizeImprove realismHeterogeneous representationsHeterogeneous translationAttentional strategiesTraining approachExperimental resultsMuscle deformationIntelligible speechMotor control theoriesTagged-MRIRelated-disordersSpeech acousticsTagged-MRI to audio synthesis with a pairwise heterogeneous deep translator
Liu X, Xing F, Stone M, Prince J, Kim J, Fakhri G, Woo J. Tagged-MRI to audio synthesis with a pairwise heterogeneous deep translator. The Journal Of The Acoustical Society Of America 2022, 151: a133-a133. DOI: 10.1121/10.0010891.Peer-Reviewed Original ResearchLatent space featuresEncoder-decoder structureCNN-based encoderSpace featuresDeep learning frameworkTagged MRI sequencesKullback-Leibler divergenceMel-spectrogramSpeech-related disordersLearning frameworkAudio synthesisAudio waveformSpeech productionKullback-LeiblerHeterogeneous representationsEvaluation strategiesIntelligible speechFrameworkTagged-MRISpeechDecodingAudioVisual movementEncodingUtterances
2021
A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech
Woo J, Xing F, Prince J, Stone M, Gomez A, Reese T, Wedeen V, El Fakhri G. A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech. Medical Image Analysis 2021, 72: 102131. PMID: 34174748, PMCID: PMC8316408, DOI: 10.1016/j.media.2021.102131.Peer-Reviewed Original ResearchConceptsNon-negative matrix factorizationSparse Non-negative Matrix FactorizationIterative shrinkage-thresholding algorithmNon-negative matrix factorization frameworkDeep neural networksMatrix factorization frameworkDeep learning frameworkTongue motionIdentified functional unitsGraph regularizationClustering performanceWeight mapLearning frameworkSpectral clusteringNeural networkMatrix factorizationModular architectureIncreased interpretabilityMotion dataFactorization frameworkConvoluted natureComparison methodTagged magnetic resonance imagingMuscle coordination patternsSpeech