English
Related papers

Related papers: Masked Audio Generation using a Single Non-Autoreg…

200 papers

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Heming Wang , Meng Yu , Hao Zhang , Chunlei Zhang , Zhongweiyang Xu , Muqiao Yang , Yixuan Zhang , Dong Yu

Generating audio from a video's visual context has multiple practical applications in improving how we interact with audio-visual media - for example, enhancing CCTV footage analysis, restoring historical videos (e.g., silent movies), and…

Sound · Computer Science 2024-04-30 Hugo Garrido-Lestache Belinchon , Helina Mulugeta , Adam Haile

Due to the unprecedented breakthroughs brought about by deep learning, speech enhancement (SE) techniques have been developed rapidly and play an important role prior to acoustic modeling to mitigate noise effects on speech. To increase the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-15 Fu-An Chao , Shao-Wei Fan Jiang , Bi-Cheng Yan , Jeih-weih Hung , Berlin Chen

This work seeks the possibility of generating the human face from voice solely based on the audio-visual data without any human-labeled annotations. To this end, we propose a multi-modal learning framework that links the inference stage and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-14 Hyeong-Seok Choi , Changdae Park , Kyogu Lee

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Sound · Computer Science 2023-12-06 Pavel Andreev , Nicholas Babaev , Azat Saginbaev , Ivan Shchekotov , Aibek Alanov

Audio-driven one-shot talking face generation methods are usually trained on video resources of various persons. However, their created videos often suffer unnatural mouth shapes and asynchronous lips because those methods struggle to learn…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Suzhen Wang , Lincheng Li , Yu Ding , Xin Yu

This paper introduces R-MelNet, a two-part autoregressive architecture with a frontend based on the first tier of MelNet and a backend WaveRNN-style audio decoder for neural text-to-speech synthesis. Taking as input a mixed sequence of…

Sound · Computer Science 2022-07-01 Kyle Kastner , Aaron Courville

Self-supervised pre-training, such as BERT, MASS and BART, has emerged as a powerful technique for natural language understanding and generation. Existing pre-training techniques employ autoencoding and/or autoregressive objectives to train…

Computation and Language · Computer Science 2020-09-22 Bin Bi , Chenliang Li , Chen Wu , Ming Yan , Wei Wang , Songfang Huang , Fei Huang , Luo Si

We propose a novel method for generating high-resolution videos of talking-heads from speech audio and a single 'identity' image. Our method is based on a convolutional neural network model that incorporates a pre-trained StyleGAN…

Computer Vision and Pattern Recognition · Computer Science 2022-09-12 Mohammed M. Alghamdi , He Wang , Andrew J. Bulpitt , David C. Hogg

The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often…

Sound · Computer Science 2022-03-23 Tao Wang , Jiangyan Yi , Ruibo Fu , Jianhua Tao , Zhengqi Wen

Transformer-based autoregressive (AR) methods have achieved appealing performance for varied sequence-to-sequence generation tasks, e.g., neural machine translation, summarization, and code generation, but suffer from low inference…

Computation and Language · Computer Science 2023-03-15 Yisheng Xiao , Ruiyang Xu , Lijun Wu , Juntao Li , Tao Qin , Yan-Tie Liu , Min Zhang

The ability to envisage the visual of a talking face based just on hearing a voice is a unique human capability. There have been a number of works that have solved for this ability recently. We differ from these approaches by enabling a…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Ravindra Yadav , Ashish Sardana , Vinay P Namboodiri , Rajesh M Hegde

Phase information has a significant impact on speech perceptual quality and intelligibility. However, existing speech enhancement methods encounter limitations in explicit phase estimation due to the non-structural nature and wrapping…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-02 Ye-Xin Lu , Yang Ai , Zhen-Hua Ling

We present AudioGen-Omni - a unified approach based on multimodal diffusion transformers (MMDit), capable of generating high-fidelity audio, speech, and song coherently synchronized with the input video. AudioGen-Omni introduces a novel…

Sound · Computer Science 2025-08-08 Le Wang , Jun Wang , Chunyu Qiang , Feng Deng , Chen Zhang , Di Zhang , Kun Gai

Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including…

Sound · Computer Science 2019-06-25 Adrien Bitton , Philippe Esling , Antoine Caillon , Martin Fouilleul

Multimodality-to-Multiaudio (MM2MA) generation faces significant challenges in synthesizing diverse and contextually aligned audio types (e.g., sound effects, speech, music, and songs) from multimodal inputs (e.g., video, text, images),…

Sound · Computer Science 2025-08-06 Yan Rong , Jinting Wang , Guangzhi Lei , Shan Yang , Li Liu

Autoregressive models are typically applied to sequences of discrete tokens, but recent research indicates that generating sequences of continuous embeddings in an autoregressive manner is also feasible. However, such Continuous…

Machine Learning · Computer Science 2024-11-28 Marco Pasini , Javier Nistal , Stefan Lattner , George Fazekas

A recurrent Neural Network (RNN) is trained to predict sound samples based on audio input augmented by control parameter information for pitch, volume, and instrument identification. During the generative phase following training, audio…

Sound · Computer Science 2019-03-27 Lonce Wyse , Muhammad Huzaifah

Speech generation models based on large language models (LLMs) typically operate on discrete acoustic codes, which differ fundamentally from text tokens due to their multicodebook structure. At each timestep, models must predict N codebook…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-26 Roy Fejgin , Paarth Neekhara , Xuesong Yang , Edresson Casanova , Ryan Langman , Jaehyeon Kim , Subhankar Ghosh , Shehzeen Hussain , Jason Li

Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences.…

Computation and Language · Computer Science 2018-10-30 Chunqi Wang , Ji Zhang , Haiqing Chen