Related papers: Convolutional Variational Autoencoders for Spectro…

The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models. However, the main drawback of this approach is the blurriness of the generated…

Variational autoencoders (VAEs) are a popular class of deep generative models with many variants and a wide range of applications. Improvements upon the standard VAE mostly focus on the modelling of the posterior distribution over the…

Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Audio classification and restoration are among major downstream tasks in audio signal processing. However, restoration derives less of a benefit from pretrained models compared to the overwhelming success of pretrained models in…

Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to mitigate this is to train or fine-tune models with more…

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a…

This study investigates the use of non-linear unsupervised dimensionality reduction techniques to compress a music dataset into a low-dimensional representation which can be used in turn for the synthesis of new sounds. We systematically…

Deep speaker embedding has achieved state-of-the-art performance in speaker recognition. A potential problem of these embedded vectors (called `x-vectors') are not Gaussian, causing performance degradation with the famous PLDA back-end…

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 into sequential-level…

Variational autoencoders (VAEs) are a popular generative model used to approximate distributions. The encoder part of the VAE is used in amortized learning of latent variables, producing a latent representation for data samples. Recently,…

In this article we introduce the notion of Split Variational Autoencoder (SVAE), whose output $\hat{x}$ is obtained as a weighted sum $\sigma \odot \hat{x_1} + (1-\sigma) \odot \hat{x_2}$ of two generated images $\hat{x_1},\hat{x_2}$, and…

We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the…

Deep generative models have emerged as influential instruments for data generation and manipulation. Enhancing the controllability of these models by selectively modifying data attributes has been a recent focus. Variational Autoencoders…

Variational autoencoders were proven successful in domains such as computer vision and speech processing. Their adoption for modeling user preferences is still unexplored, although recently it is starting to gain attention in the current…

People can easily imagine the potential sound while seeing an event. This natural synchronization between audio and visual signals reveals their intrinsic correlations. To this end, we propose to learn the audio-visual correlations from the…

While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the…