English
Related papers

Related papers: Continuous Autoregressive Modeling with Stochastic…

200 papers

Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS). However, as they lack the ability to model global characteristics of speech (such as speaker individualities or speaking styles),…

Computation and Language · Computer Science 2019-02-12 Kei Akuzawa , Yusuke Iwasawa , Yutaka Matsuo

We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for…

Computation and Language · Computer Science 2025-05-28 Lingwei Meng , Long Zhou , Shujie Liu , Sanyuan Chen , Bing Han , Shujie Hu , Yanqing Liu , Jinyu Li , Sheng Zhao , Xixin Wu , Helen Meng , Furu Wei

We investigate a fully Latent AutoRegressive scheme based on a Gaussian Process (GP) integrated into a Variational Autoencoder (VAE). In this setting, sequential dynamics are transferred from the observation space to a continuous latent…

Machine Learning · Computer Science 2025-12-16 Yves Ruffenach

This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix…

Machine Learning · Computer Science 2020-02-11 Simon Leglaive , Xavier Alameda-Pineda , Laurent Girin , Radu Horaud

Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-grained variational autoencoder (VAE) structure, extracting…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-11 Guangzhi Sun , Yu Zhang , Ron J. Weiss , Yuan Cao , Heiga Zen , Andrew Rosenberg , Bhuvana Ramabhadran , Yonghui Wu

Attention-based models such as Transformers and recurrent models like state space models (SSMs) have emerged as successful methods for autoregressive sequence modeling. Although both enable parallel training, none enable parallel generation…

Machine Learning · Computer Science 2024-07-12 Gaspard Lambrechts , Yann Claes , Pierre Geurts , Damien Ernst

This work focuses on full-body co-speech gesture generation. Existing methods typically employ an autoregressive model accompanied by vector-quantized tokens for gesture generation, which results in information loss and compromises the…

Graphics · Computer Science 2025-03-19 Binjie Liu , Lina Liu , Sanyi Zhang , Songen Gu , Yihao Zhi , Tianyi Zhu , Lei Yang , Long Ye

With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling based decoding strategies bring…

Computation and Language · Computer Science 2024-06-13 Bing Han , Long Zhou , Shujie Liu , Sanyuan Chen , Lingwei Meng , Yanming Qian , Yanqing Liu , Sheng Zhao , Jinyu Li , Furu Wei

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…

Sound · Computer Science 2026-05-26 Changhao Cheng , Wei Wang , Wangyou Zhang , Dongya Jia , Jian Wu , Zhuo Chen , Yanmin Qian

We introduce KALL-E, a novel autoregressive (AR) language model for text-to-speech (TTS) synthesis that operates by predicting the next distribution of continuous speech frames. Unlike existing methods, KALL-E directly models the continuous…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-18 Kangxiang Xia , Xinfa Zhu , Jixun Yao , Wenjie Tian , Wenhao Li , Lei Xie

As an extension of variational autoencoder (VAE), complex VAE uses complex Gaussian distributions to model latent variables and data. This work proposes a complex recurrent VAE framework, specifically in which complex-valued recurrent…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-28 Yuying Xie , Thomas Arildsen , Zheng-Hua Tan

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good…

Computation and Language · Computer Science 2019-02-15 Ya-Jie Zhang , Shifeng Pan , Lei He , Zhen-Hua Ling

We present a controllable neural audio synthesizer based on Gaussian Mixture Variational Autoencoders (GM-VAE), which can generate realistic piano performances in the audio domain that closely follows temporal conditions of two essential…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-14 Hao Hao Tan , Yin-Jyun Luo , Dorien Herremans

Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…

Computation and Language · Computer Science 2024-12-12 Yutao Sun , Hangbo Bao , Wenhui Wang , Zhiliang Peng , Li Dong , Shaohan Huang , Jianyong Wang , Furu Wei

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Sound · Computer Science 2020-12-18 Mostafa Sadeghi , Simon Leglaive , Xavier Alameda-PIneda , Laurent Girin , Radu Horaud

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…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-02 Zhikang Niu , Shujie Hu , Jeongsoo Choi , Yushen Chen , Peining Chen , Pengcheng Zhu , Yunting Yang , Bowen Zhang , Jian Zhao , Chunhui Wang , Xie Chen

We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our model specifies the…

Computation and Language · Computer Science 2019-03-19 Wenlin Wang , Zhe Gan , Hongteng Xu , Ruiyi Zhang , Guoyin Wang , Dinghan Shen , Changyou Chen , Lawrence Carin

In this paper, we address the unsupervised speech enhancement problem based on recurrent variational autoencoder (RVAE). This approach offers promising generalization performance over the supervised counterpart. Nevertheless, the involved…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Mostafa Sadeghi , Romain Serizel

In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-05 Gautam Krishna , Co Tran , Mason Carnahan , Ahmed Tewfik

This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network…

‹ Prev 1 2 3 10 Next ›