相关论文: Addressing Index Collapse of Large-Codebook Speech…

State-of-the-art high-spectral-efficiency communication systems employ high-order modulation formats coupled with high symbol rates to accommodate the ever-growing demand for data rate-hungry applications. However, such systems are more…

Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (or KL loss vanishing), where the posterior collapses to the…

The expressive quality of synthesized speech for audiobooks is limited by generalized model architecture and unbalanced style distribution in the training data. To address these issues, in this paper, we propose a self-supervised style…

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…

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…

Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and…

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling,…

This paper presents an analysis of speech synthesis quality achieved by simultaneously performing voice conversion and language code-switching using multilingual VQ-VAE speech synthesis in German, French, English and Italian. In this paper,…

Recent progress in scaling up large language models has shown impressive capabilities in performing few-shot learning across a wide range of text-based tasks. However, a key limitation is that these language models fundamentally lack visual…

Text variational autoencoders (VAEs) are notorious for posterior collapse, a phenomenon where the model's decoder learns to ignore signals from the encoder. Because posterior collapse is known to be exacerbated by expressive decoders,…

Built upon vector quantization (VQ), discrete audio codec models have achieved great success in audio compression and auto-regressive audio generation. However, existing models face substantial challenges in perceptual quality and signal…

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…

Variational autoencoders (VAEs) combine latent variables with amortized variational inference, whose optimization usually converges into a trivial local optimum termed posterior collapse, especially in text modeling. By tracking the…

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and…

Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning. However, the existing VAE models have some…

This paper introduces a novel approach for topic modeling utilizing latent codebooks from Vector-Quantized Variational Auto-Encoder~(VQ-VAE), discretely encapsulating the rich information of the pre-trained embeddings such as the…

Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the seminal Vector Quantized Variational Auto-Encoder (VQ-VAE),…

With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade. Meanwhile, the self-supervised pre-trained model and vector quantization (VQ) have achieved excellent performance on many…

A major challenge in quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional…

Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called…