Related papers: Unsupervised Discrete Sentence Representation Lear…
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this…
In this paper, we are interested in unsupervised (unknown noise) audio-visual speech enhancement based on variational autoencoders (VAEs), where the probability distribution of clean speech spectra is simulated using an encoder-decoder…
Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This remains a challenging problem, as existing approaches based on…
Density estimation, compression and data generation are crucial tasks in artificial intelligence. Variational Auto-Encoders (VAEs) constitute a single framework to achieve these goals. Here, we present a novel class of generative models,…
Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular…
Continuous speech representations based on Variational Autoencoders (VAEs) have emerged as a promising alternative to traditional spectrogram or discrete token based features for speech generation and reconstruction. Recent research has…
Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning.…
Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…
New system for i-vector speaker recognition based on variational autoencoder (VAE) is investigated. VAE is a promising approach for developing accurate deep nonlinear generative models of complex data. Experiments show that VAE provides…
In previous work, we proposed a variational autoencoder-based (VAE) Bayesian permutation training speech enhancement (SE) method (PVAE) which indicated that the SE performance of the traditional deep neural network-based (DNN) method could…
This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level…
This paper presents a novel framework for automatic speech-driven gesture generation, applicable to human-agent interaction including both virtual agents and robots. Specifically, we extend recent deep-learning-based, data-driven methods…
Text style transfer aims to change the style of sentences while preserving the semantic meanings. Due to the lack of parallel data, the Denoising Auto-Encoder (DAE) is widely used in this task to model distributions of different sentence…
We present a Split Vector Quantized Variational Autoencoder (SVQ-VAE) architecture using a split vector quantizer for NTTS, as an enhancement to the well-known Variational Autoencoder (VAE) and Vector Quantized Variational Autoencoder…
We would like to learn a representation of the data which decomposes an observation into factors of variation which we can independently control. Specifically, we want to use minimal supervision to learn a latent representation that…
With the rapid development of artificial intelligence, conversational bots have became prevalent in mainstream E-commerce platforms, which can provide convenient customer service timely. To satisfy the user, the conversational bots need to…
Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic…
Deep generative models aim to learn underlying distributions that generate the observed data. Given the fact that the generative distribution may be complex and intractable, deep latent variable models use probabilistic frameworks to learn…
Current variational dialog models have employed pre-trained language models (PLMs) to parameterize the likelihood and posterior distributions. However, the Gaussian assumption made on the prior distribution is incompatible with these…
Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature…