English
Related papers

Related papers: Improved Prosody from Learned F0 Codebook Represen…

200 papers

VQ-VAE, as a mainstream approach of speech tokenizer, has been troubled by ``index collapse'', where only a small number of codewords are activated in large codebooks. This work proposes product-quantized (PQ) VAE with more codebooks but…

Sound · Computer Science 2024-06-06 Haohan Guo , Fenglong Xie , Dongchao Yang , Hui Lu , Xixin Wu , Helen Meng

Learning interpretable representations of data remains a central challenge in deep learning. When training a deep generative model, the observed data are often associated with certain categorical labels, and, in parallel with learning to…

Machine Learning · Computer Science 2019-10-01 Yifan Xue , Michael Ding , Xinghua Lu

Although substantial efforts have been made to learn disentangled representations under the variational autoencoder (VAE) framework, the fundamental properties to the dynamics of learning of most VAE models still remain unknown and…

Machine Learning · Computer Science 2020-07-14 Yanjun Li , Shujian Yu , Jose C. Principe , Xiaolin Li , Dapeng Wu

Disentangled representation learning aims to learn low-dimensional representations where each dimension corresponds to an underlying generative factor. While the Variational Auto-Encoder (VAE) is widely used for this purpose, most existing…

Machine Learning · Computer Science 2024-12-31 Di Fan , Yannian Kou , Chuanhou Gao

We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-07 Puyuan Peng , Herman Kamper , Karen Livescu

This paper presents the description of our submitted system for Voice Conversion Challenge (VCC) 2020 with vector-quantization variational autoencoder (VQ-VAE) with WaveNet as the decoder, i.e., VQ-VAE-WaveNet. VQ-VAE-WaveNet is a…

Sound · Computer Science 2020-10-16 Haitong Zhang

In this paper, we propose an online speaker adaptation method for WaveNet-based neural vocoders in order to improve their performance on speaker-independent waveform generation. In this method, a speaker encoder is first constructed using a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-17 Qiuchen Huang , Yang Ai , Zhenhua Ling

Interpretable machine learning is rapidly becoming a crucial tool for scientific discovery. Among existing approaches, variational autoencoders (VAEs) have shown promise in extracting the hidden physical features of some input data, with no…

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…

Computation and Language · Computer Science 2024-01-23 YoungJoon Yoo , Jongwon Choi

Given the complex geometry of white matter streamlines, Autoencoders have been proposed as a dimension-reduction tool to simplify the analysis streamlines in a low-dimensional latent spaces. However, despite these recent successes, the…

Machine Learning · Statistics 2023-11-21 Andrew Lizarraga , Brandon Taraku , Edouardo Honig , Ying Nian Wu , Shantanu H. Joshi

With the continued proliferation of Large Language Model (LLM) based chatbots, there is a growing demand for generating responses that are not only linguistically fluent but also consistently aligned with persona-specific traits in…

Computation and Language · Computer Science 2025-12-12 Qi Lin , Weikai Xu , Lisi Chen , Bin Dai

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…

Computation and Language · Computer Science 2020-06-26 Yushi Hu , Shane Settle , Karen Livescu

Learning latent representations that are simultaneously expressive, geometrically well-structured, and reliably calibrated remains a central challenge for Variational Autoencoders (VAEs). Standard VAEs typically assume a diagonal Gaussian…

Machine Learning · Computer Science 2025-12-02 Mehmet Can Yavuz

Cross-modal retrieval is to utilize one modality as a query to retrieve data from another modality, which has become a popular topic in information retrieval, machine learning, and database. How to effectively measure the similarity between…

Information Retrieval · Computer Science 2021-12-07 Jiwei Zhang , Yi Yu , Suhua Tang , Jianming Wu , Wei Li

Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images into discrete tokens. However, they are difficult to train due to discretization. In this paper, we propose a simple yet effective technique…

Machine Learning · Computer Science 2026-05-27 Tongda Xu , Wendi Zheng , Jiajun He , Jose Miguel Hernandez-Lobato , Yan Wang , Ya-Qin Zhang , Jie Tang

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,…

Computation and Language · Computer Science 2021-11-25 Seongmin Park , Jihwa Lee

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Many style-transfer-inspired methods such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-17 Kaizhi Qian , Zeyu Jin , Mark Hasegawa-Johnson , Gautham J. Mysore

Objective speech disorder classification for speakers with communication difficulty is desirable for diagnosis and administering therapy. With the current state of speech technology, it is evident to propose neural networks for this…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-15 Jinzi Qi , Hugo Van hamme

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and…

Computation and Language · Computer Science 2018-02-07 Xiaoyu Shen , Hui Su , Shuzi Niu , Vera Demberg

Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explained and improved upon.…

Computation and Language · Computer Science 2024-02-02 Yingji Zhang , Danilo S. Carvalho , Marco Valentino , Ian Pratt-Hartmann , Andre Freitas