English
Related papers

Related papers: A Generative Model for Raw Audio Using Transformer…

200 papers

State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw…

Computation and Language · Computer Science 2018-06-22 Neil Zeghidour , Nicolas Usunier , Gabriel Synnaeve , Ronan Collobert , Emmanuel Dupoux

Deep generative modeling has led to new and state of the art approaches for enforcing structural priors in a variety of inverse problems. In contrast to priors given by sparsity, deep models can provide direct low-dimensional…

Optimization and Control · Mathematics 2018-12-12 Wen Huang , Paul Hand , Reinhard Heckel , Vladislav Voroninski

We demonstrate how conditional generation from diffusion models can be used to tackle a variety of realistic tasks in the production of music in 44.1kHz stereo audio with sampling-time guidance. The scenarios we consider include…

Sound · Computer Science 2023-12-06 Mark Levy , Bruno Di Giorgi , Floris Weers , Angelos Katharopoulos , Tom Nickson

Deep learning has revolutionised synthetic speech quality. However, it has thus far delivered little value to the speech science community. The new methods do not meet the controllability demands that practitioners in this area require…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-03 Gustavo Teodoro Döhler Beck , Ulme Wennberg , Zofia Malisz , Gustav Eje Henter

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however…

In recent years, text-to-audio models have revolutionized the field of automatic audio generation. This paper investigates their application in generating synthetic datasets for training data-driven models. Specifically, this study analyzes…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-09 Francesca Ronchini , Luca Comanducci , Fabio Antonacci

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…

Machine Learning · Computer Science 2024-08-20 Giovanni Bindi , Philippe Esling

This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator's…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-27 Ryuichi Yamamoto , Eunwoo Song , Min-Jae Hwang , Jae-Min Kim

Models for audio generation are typically trained on hours of recordings. Here, we illustrate that capturing the essence of an audio source is typically possible from as little as a few tens of seconds from a single training signal.…

Sound · Computer Science 2021-10-27 Gal Greshler , Tamar Rott Shaham , Tomer Michaeli

In recent years, the burgeoning interest in diffusion models has led to significant advances in image and speech generation. Nevertheless, the direct synthesis of music waveforms from unrestricted textual prompts remains a relatively…

Sound · Computer Science 2023-09-22 Pengfei Zhu , Chao Pang , Yekun Chai , Lei Li , Shuohuan Wang , Yu Sun , Hao Tian , Hua Wu

In this paper, we propose a novel score-base generative model for unconditional raw audio synthesis. Our proposal builds upon the latest developments on diffusion process modeling with stochastic differential equations, which already…

Sound · Computer Science 2021-06-15 Simon Rouard , Gaëtan Hadjeres

Audio signals are sampled at high temporal resolutions, and learning to synthesize audio requires capturing structure across a range of timescales. Generative adversarial networks (GANs) have seen wide success at generating images that are…

Sound · Computer Science 2019-02-12 Chris Donahue , Julian McAuley , Miller Puckette

The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process --- creating audio samples from a score and instrument information --- is modeled using…

Sound · Computer Science 2018-11-02 Jong Wook Kim , Rachel Bittner , Aparna Kumar , Juan Pablo Bello

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…

Sound · Computer Science 2025-11-26 Genís Plaja-Roglans , Yun-Ning Hung , Xavier Serra , Igor Pereira

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Sound · Computer Science 2022-07-05 Kun Wei , Pengcheng Guo , Ning Jiang

The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale datasets are capable of capturing a diverse set of features, and…

Pre-trained transformer language models on large unlabeled corpus have produced state-of-the-art results in natural language processing, organic molecule design, and protein sequence generation. However, no such models have been applied to…

In this paper, we propose a novel conditional convolution network, named location-variable convolution, to model the dependencies of the waveform sequence. Different from the use of unified convolution kernels in WaveNet to capture the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-23 Zhen Zeng , Jianzong Wang , Ning Cheng , Jing Xiao

Many security and network applications require having large datasets to train the machine learning models. Limited data access is a well-known problem in the security domain. Recent studies have shown the potential of Transformer models to…

Machine Learning · Computer Science 2025-06-10 Yusuf Elnady

Deep neural networks have shown promise for music audio signal processing applications, often surpassing prior approaches, particularly as end-to-end models in the waveform domain. Yet results to date have tended to be constrained by low…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-11 William Mitchell , Scott H. Hawley
‹ Prev 1 4 5 6 7 8 10 Next ›