Related papers: SingFake: Singing Voice Deepfake Detection

Audio deepfakes represent a growing threat to digital security and trust, leveraging advanced generative models to produce synthetic speech that closely mimics real human voices. Detecting such manipulations is especially challenging under…

Speech deepfake detection is a well-established research field with different models, datasets, and training strategies. However, the lack of standardized implementations and evaluation protocols limits reproducibility, benchmarking, and…

Existing singing voice synthesis (SVS) models largely rely on fine-grained, phoneme-level durations, which limits their practical application. These methods overlook the complementary role of visual information in duration prediction.To…

Audio deepfake detection aims to detect real human voices from those generated by Artificial Intelligence (AI) and has emerged as a significant problem in the field of voice biometrics systems. With the ever-improving quality of synthetic…

Methods that can generate synthetic speech which is perceptually indistinguishable from speech recorded by a human speaker, are easily available. Several incidents report misuse of synthetic speech generated from these methods to commit…

This paper proposes an expressive singing voice synthesis system by introducing explicit vibrato modeling and latent energy representation. Vibrato is essential to the naturalness of synthesized sound, due to the inherent characteristics of…

This paper presents a novel method for extracting the vocal track from a musical mixture. The musical mixture consists of a singing voice and a backing track which may comprise of various instruments. We use a convolutional network with…

In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment…

Extensive works have tackled Language Identification (LID) in the speech domain, however their application to the singing voice trails and performances on Singing Language Identification (SLID) can be improved leveraging recent progresses…

Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion.…

The problem of pitch tracking has been extensively studied in the speech research community. The goal of this paper is to investigate how these techniques should be adapted to singing voice analysis, and to provide a comparative evaluation…

In the face of a new era of generative models, the detection of artificially generated content has become a matter of utmost importance. In particular, the ability to create credible minute-long synthetic music in a few seconds on…

Recent advancements in generative models have significantly enhanced talking face video generation, yet singing video generation remains underexplored. The differences between human talking and singing limit the performance of existing…

Singing voices contain much richer information than common voices, including varied vocal and acoustic properties. However, current open-source audio-text datasets for singing voices capture only a narrow range of attributes and lack…

Generalization is a main issue for current audio deepfake detectors, which struggle to provide reliable results on out-of-distribution data. Given the speed at which more and more accurate synthesis methods are developed, it is very…

This paper presents XiaoiceSing, a high-quality singing voice synthesis system which employs an integrated network for spectrum, F0 and duration modeling. We follow the main architecture of FastSpeech while proposing some singing-specific…

We introduce a post-training approach that adapts self-supervised learning (SSL) models for deepfake speech detection by bridging the gap between general pre-training and domain-specific fine-tuning. We present AntiDeepfake models, a series…

Automatic speaker recognition algorithms typically characterize speech audio using short-term spectral features that encode the physiological and anatomical aspects of speech production. Such algorithms do not fully capitalize on…

Recent advances in audio generation led to an increasing number of deepfakes, making the general public more vulnerable to financial scams, identity theft, and misinformation. Audio deepfake detectors promise to alleviate this issue, with…

The rapid development of generative audio raises ethical and security concerns stemming from forged data, making deepfake sound detection an important safeguard against the malicious use of such technologies. Although prior studies have…