Scalable Factorized Hierarchical Variational Autoencoder Training
Deep generative models have achieved great success in unsupervised learning with the ability to capture complex nonlinear relationships between latent generating factors and observations. Among them, a factorized hierarchical variational autoencoder (FHVAE) is a variational inference-based model that formulates a hierarchical generative process for sequential data. Specifically, an FHVAE model can learn disentangled and interpretable representations, which have been proven useful for numerous speech applications, such as speaker verification, robust speech recognition, and voice conversion. However, as we will elaborate in this paper, the training algorithm proposed in the original paper is not scalable to datasets of thousands of hours, which makes this model less applicable on a larger scale. After identifying limitations in terms of runtime, memory, and hyperparameter optimization, we propose a hierarchical sampling training algorithm to address all three issues. Our proposed method is evaluated comprehensively on a wide variety of datasets, ranging from 3 to 1,000 hours and involving different types of generating factors, such as recording conditions and noise types. In addition, we also present a new visualization method for qualitatively evaluating the performance with respect to the interpretability and disentanglement. Models trained with our proposed algorithm demonstrate the desired characteristics on all the datasets.
Code (2)
Tasks
DisentanglementHyperparameter OptimizationRobust Speech RecognitionSpeaker Verificationspeech-recognitionSpeech RecognitionVariational InferenceVoice ConversionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Scalable Gaussian Process Variational Autoencoders
Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP-VAEs has led to significant improvements in t…
Factorized Gaussian Process Variational Autoencoders
Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency across latent variables. Gaussian proce…
Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective
Disentangled representation learning aims to extract explanatory features or factors and retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents a way to disentangle a speech signal i…
DisentanglementRepresentation LearningSpeaker Recognitionspeech-recognition+3Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision. Specifically, we exploit the multi-scale nature of infor…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speaker Verificationspeech-recognition+1Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
The electroencephalogram (EEG) is a powerful method to understand how the brain processes speech. Linear models have recently been replaced for this purpose with deep neural networks and yield promising results. In relat…
ClassificationEEGElectroencephalogram (EEG)