Related papers: Continuous Autoregressive Modeling with Stochastic…

Modeling nonstationary processes is of paramount importance to many scientific disciplines including environmental science, ecology, and finance, among others. Consequently, flexible methodology that provides accurate estimation across a…

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we…

Stochastic embedding transitions introduce a probabilistic mechanism for adjusting token representations dynamically during inference, mitigating the constraints imposed through static or deterministic embeddings. A transition framework was…

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…

Traditional transformer-based semantic segmentation relies on quantized embeddings. However, our analysis reveals that autoencoder accuracy on segmentation mask using quantized embeddings (e.g. VQ-VAE) is 8% lower than continuous-valued…

Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in…

End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…

In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the speech and text…

Modelling longitudinal data is an important yet challenging task. These datasets can be high-dimensional, contain non-linear effects and time-varying covariates. Gaussian process (GP) prior-based variational autoencoders (VAEs) have emerged…

Recently, autoregressive (AR) language models have emerged as a dominant approach in speech synthesis, offering expressive generation and scalable training. However, conventional AR speech synthesis models relying on the next-token…

Aligning pretrained audio encoders and Large Language Models (LLMs) offers a promising, parameter-efficient path to building powerful multimodal agents. However, existing methods often require costly full-model finetuning or rely on static…

Any autoencoder network can be turned into a generative model by imposing an arbitrary prior distribution on its hidden code vector. Variational Autoencoder (VAE) [2] uses a KL divergence penalty to impose the prior, whereas Adversarial…

Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the learned representations are i.i.d. and fail to capture the…

We address speech enhancement based on variational autoencoders, which involves learning a speech prior distribution in the time-frequency (TF) domain. A zero-mean complex-valued Gaussian distribution is usually assumed for the generative…

The recent text-to-speech (TTS) has achieved quality comparable to that of humans; however, its application in spoken dialogue has not been widely studied. This study aims to realize a TTS that closely resembles human dialogue. First, we…

With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention. Recently, learned image compression methods had exceeded their classical counterparts in terms of…

Conditional Generative Models are now acknowledged an essential tool in Machine Learning. This paper focuses on their control. While many approaches aim at disentangling the data through the coordinate-wise control of their latent…

Conditional waveform synthesis models learn a distribution of audio waveforms given conditioning such as text, mel-spectrograms, or MIDI. These systems employ deep generative models that model the waveform via either sequential…

This paper proposes a new model, called condition-transforming variational autoencoder (CTVAE), to improve the performance of conversation response generation using conditional variational autoencoders (CVAEs). In conventional CVAEs , the…

End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the…