中文
相关论文

相关论文: VCNAC: A Variable-Channel Neural Audio Codec for M…

200 篇论文

As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two…

音频与语音处理 · 电气工程与系统科学 2025-06-03 Songjun Cao , Qinghua Wu , Jie Chen , Jin Li , Long Ma

Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to…

机器学习 · 计算机科学 2017-05-31 Emre Çakır , Giambattista Parascandolo , Toni Heittola , Heikki Huttunen , Tuomas Virtanen

Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content. Although recent systems have improved conversion quality, building zero-shot VC systems…

音频与语音处理 · 电气工程与系统科学 2026-04-23 Qixi Zheng , Yuxiang Zhao , Tianrui Wang , Wenxi Chen , Kele Xu , Yikang Li , Qinyuan Chen , Xipeng Qiu , Kai Yu , Xie Chen

Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for…

声音 · 计算机科学 2024-12-30 Junzuo Zhou , Jiangyan Yi , Yong Ren , Jianhua Tao , Tao Wang , Chu Yuan Zhang

In the development of spatial audio technologies, reliable and shared methods for evaluating audio quality are essential. Listening tests are currently the standard but remain costly in terms of time and resources. Several models predicting…

音频与语音处理 · 电气工程与系统科学 2026-01-21 Adrien Llave , Emma Granier , Grégory Pallone

Since Text-to-Speech systems typically don't produce waveforms directly, recent spoof detection studies use resynthesized waveforms from vocoders and neural audio codecs to simulate an attacker. Unlike vocoders, which are specifically…

声音 · 计算机科学 2026-02-19 Yixuan Xiao , Florian Lux , Alejandro Pérez-González-de-Martos , Ngoc Thang Vu

Audio captioning aims to generate text descriptions of audio clips. In the real world, many objects produce similar sounds. How to accurately recognize ambiguous sounds is a major challenge for audio captioning. In this work, inspired by…

音频与语音处理 · 电气工程与系统科学 2023-05-30 Xubo Liu , Qiushi Huang , Xinhao Mei , Haohe Liu , Qiuqiang Kong , Jianyuan Sun , Shengchen Li , Tom Ko , Yu Zhang , Lilian H. Tang , Mark D. Plumbley , Volkan Kılıç , Wenwu Wang

This paper presents a refinement framework of WaveNet vocoders for variational autoencoder (VAE) based voice conversion (VC), which reduces the quality distortion caused by the mismatch between the training data and testing data.…

音频与语音处理 · 电气工程与系统科学 2020-04-09 Wen-Chin Huang , Yi-Chiao Wu , Hsin-Te Hwang , Patrick Lumban Tobing , Tomoki Hayashi , Kazuhiro Kobayashi , Tomoki Toda , Yu Tsao , Hsin-Min Wang

Convolutional Neural Networks (CNNs) rely on fixed-size kernels scanning local patches, which limits their ability to capture global context or long-range dependencies without very deep architectures. Vision Transformers (ViTs), in turn,…

计算机视觉与模式识别 · 计算机科学 2026-01-28 Gijs Joppe Moens , Regina Beets-Tan , Eduardo H. P. Pooch

Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader…

音频与语音处理 · 电气工程与系统科学 2025-11-21 Wei-Cheng Tseng , David Harwath

Audio coding is an essential module in the real-time communication system. Neural audio codecs can compress audio samples with a low bitrate due to the strong modeling and generative capabilities of deep neural networks. To address the poor…

声音 · 计算机科学 2023-10-18 Wenzhe Liu , Wei Xiao , Meng Wang , Shan Yang , Yupeng Shi , Yuyong Kang , Dan Su , Shidong Shang , Dong Yu

Neural audio codecs are a fundamental component of modern generative audio pipelines. Although recent codecs achieve strong low-bitrate reconstruction and provide powerful representations for downstream tasks, most are non-streamable,…

声音 · 计算机科学 2025-09-22 Luca Della Libera , Cem Subakan , Mirco Ravanelli

The framework of visually-guided sound source separation generally consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. An ongoing trend in this field has been to tailor involved visual…

声音 · 计算机科学 2023-06-21 Zengjie Song , Zhaoxiang Zhang

Automatic detection of synthetic speech is becoming increasingly important as current synthesis methods are both near indistinguishable from human speech and widely accessible to the public. Audio watermarking and other active disclosure…

声音 · 计算机科学 2024-09-23 Lauri Juvela , Xin Wang

This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin…

机器学习 · 计算机科学 2025-10-14 Naman Agrawal

From the perspective of joint source-channel coding (JSCC), there has been significant research on utilizing semantic communication, which inherently possesses analog characteristics, within digital device environments. However, a…

信号处理 · 电气工程与系统科学 2025-02-04 Yoon Huh , Hyowoon Seo , Wan Choi

The recent progress in artificial intelligence has led to an ever-increasing usage of images and videos by machine analysis algorithms, mainly neural networks. Nonetheless, compression, storage and transmission of media have traditionally…

图像与视频处理 · 电气工程与系统科学 2024-01-22 Jukka I. Ahonen , Nam Le , Honglei Zhang , Antti Hallapuro , Francesco Cricri , Hamed Rezazadegan Tavakoli , Miska M. Hannuksela , Esa Rahtu

Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice…

计算与语言 · 计算机科学 2018-10-15 Sercan O. Arik , Jitong Chen , Kainan Peng , Wei Ping , Yanqi Zhou

Voice conversion is becoming increasingly popular, and a growing number of application scenarios require models with streaming inference capabilities. The recently proposed DualVC attempts to achieve this objective through streaming model…

音频与语音处理 · 电气工程与系统科学 2024-01-19 Ziqian Ning , Yuepeng Jiang , Pengcheng Zhu , Shuai Wang , Jixun Yao , Lei Xie , Mengxiao Bi

Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete tokens that can be processed by LLMs. However, existing codecs typically operate at fixed frame rates,…

机器学习 · 计算机科学 2026-02-05 Luca Della Libera , Cem Subakan , Mirco Ravanelli