Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier
Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which results in a limited ability of extracting the speech signal from noisy speech compared to supervised approaches. In this paper, we propose to guide the variational autoencoder with a supervised classifier separately trained on noisy speech. The estimated label is a high-level categorical variable describing the speech signal (e.g. speech activity) allowing for a more informed latent distribution compared to the standard variational autoencoder. We evaluate our method with different types of labels on real recordings of different noisy environments. Provided that the label better informs the latent distribution and that the classifier achieves good performance, the proposed approach outperforms the standard variational autoencoder and a conventional neural network-based supervised approach.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech EnhancementMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders
Dynamical variational autoencoders (DVAEs) are a class of deep generative models with latent variables, dedicated to model time series of high-dimensional data. DVAEs can be considered as extensions of the variational au…
Representation LearningSpeech EnhancementTime SeriesTime Series AnalysisPosterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder
In this paper, we address the unsupervised speech enhancement problem based on recurrent variational autoencoder (RVAE). This approach offers promising generalization performance over the supervised counterpart. Neverthe…
Computational EfficiencySpeech EnhancementVariational InferenceRobust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders
Recently, an audio-visual speech generative model based on variational autoencoder (VAE) has been proposed, which is combined with a nonnegative matrix factorization (NMF) model for noise variance to perform unsupervised…
Speech EnhancementIncorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better r…
Speech EnhancementTripletSemi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization
In this paper we address speaker-independent multichannel speech enhancement in unknown noisy environments. Our work is based on a well-established multichannel local Gaussian modeling framework. We propose to use a neur…
Speech Enhancement