中文
相关论文

相关论文: Scalable Evaluation for Audio Identification via S…

200 篇论文

Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real…

机器学习 · 计算机科学 2017-02-01 Moustafa Alzantot , Supriyo Chakraborty , Mani B. Srivastava

Human-centered data collection is typically costly and implicates issues of privacy. Various solutions have been proposed in the literature to reduce this cost, such as crowdsourced data collection, or the use of semi-supervised algorithms.…

信号处理 · 电气工程与系统科学 2021-05-07 Mohammad Nabati , Hojjat Navidan , Reza Shahbazian , Seyed Ali Ghorashi , David Windridge

Human annotation for syntactic parsing is expensive, and large resources are available only for a fraction of languages. A question we ask is whether one can leverage abundant unlabeled texts to improve syntactic parsers, beyond just using…

计算与语言 · 计算机科学 2019-02-22 Caio Corro , Ivan Titov

Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this…

计算机视觉与模式识别 · 计算机科学 2024-01-25 Dongmyoung Lee , Wei Chen , Nicolas Rojas

Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the underlying properties of these embeddings remain underexplored.…

Privacy-preserving synthetic data offers a promising solution to harness segregated data in high-stakes domains where information is compartmentalized for regulatory, privacy, or institutional reasons. This survey provides a comprehensive…

密码学与安全 · 计算机科学 2025-03-28 Viktor Schlegel , Anil A Bharath , Zilong Zhao , Kevin Yee

Synthetic data generation offers promise for addressing data scarcity and privacy concerns in educational technology, yet practitioners lack empirical guidance for selecting between traditional resampling techniques and modern deep learning…

机器学习 · 计算机科学 2026-04-24 Tapiwa Amion Chinodakufa , Ashfaq Ali Shafin , Khandaker Mamun Ahmed

There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the research community is actively working on developing…

计算与语言 · 计算机科学 2021-06-04 Nirav Diwan , Tanmoy Chakravorty , Zubair Shafiq

Diffusion models have demonstrated remarkable success in generative tasks, including audio super-resolution (SR). In many applications like movie post-production and album mastering, substantial computational budgets are available for…

声音 · 计算机科学 2025-08-05 Yizhu Jin , Zhen Ye , Zeyue Tian , Haohe Liu , Qiuqiang Kong , Yike Guo , Wei Xue

Diffusion-based speech generators are ubiquitous. These methods can generate very high quality synthetic speech and several recent incidents report their malicious use. To counter such misuse, synthetic speech detectors have been developed.…

音频与语音处理 · 电气工程与系统科学 2024-10-03 Kratika Bhagtani , Amit Kumar Singh Yadav , Paolo Bestagini , Edward J. Delp

Generative adversarial networks (GANs) and diffusion models have recently achieved state-of-the-art performance in audio super-resolution (ADSR), producing perceptually convincing wideband audio from narrowband inputs. However, existing…

音频与语音处理 · 电气工程与系统科学 2026-01-08 Mikhail Silaev , Konstantinos Drossos , Tuomas Virtanen

The scarcity of large-scale classroom speech data has hindered the development of AI-driven speech models for education. Public classroom datasets remain limited, and the lack of a dedicated classroom noise corpus prevents the use of…

声音 · 计算机科学 2025-06-12 Ahmed Adel Attia , Jing Liu , Carl Espy-Wilson

Recent advances in audio declipping have substantially improved the state of the art.% in certain saturation regimes. Yet, practitioners need guidelines to choose a method, and while existing benchmarks have been instrumental in advancing…

声音 · 计算机科学 2020-12-01 Clément Gaultier , Srđan Kitić , Rémi Gribonval , Nancy Bertin

This research paper presents a novel audio fingerprinting system for Automatic Content Recognition (ACR). By using signal processing techniques and statistical transformations, our proposed method generates compact fingerprints of audio…

声音 · 计算机科学 2023-05-18 Anoubhav Agarwaal , Prabhat Kanaujia , Sartaki Sinha Roy , Susmita Ghose

Ensuring the reliability of autonomous driving perception systems requires extensive environment-based testing, yet real-world execution is often impractical. Synthetic datasets have therefore emerged as a promising alternative, offering…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Dingyi Yao , Xinyao Han , Ruibo Ming , Zhihang Song , Lihui Peng , Jianming Hu , Danya Yao , Yi Zhang

In audio-related creative tasks, sound designers often seek to extend and morph different sounds from their libraries. Generative audio models, capable of creating audio using examples as references, offer promising solutions. By masking…

声音 · 计算机科学 2026-02-20 Prem Seetharaman , Oriol Nieto , Justin Salamon

The recent integration of generative neural strategies and audio processing techniques have fostered the widespread of synthetic speech synthesis or transformation algorithms. This capability proves to be harmful in many legal and…

声音 · 计算机科学 2022-10-07 Daniele Mari , Federica Latora , Simone Milani

The increasing realism of synthetic speech generated by advanced text-to-speech (TTS) models, coupled with post-processing and laundering techniques, presents a significant challenge for audio forensic detection. In this paper, we introduce…

We investigate the feasibility of a singing voice synthesis (SVS) system by using a decomposed framework to improve flexibility in generating singing voices. Due to data-driven approaches, SVS performs a music score-to-waveform mapping;…

声音 · 计算机科学 2024-07-15 Lester Phillip Violeta , Taketo Akama

We propose a methodology for training foundation models that enhances their in-context learning capabilities within the domain of bioacoustic signal processing. We use synthetically generated training data, introducing a…