相关论文: From Real to Cloned Singer Identification

Speech deepfake detection has achieved remarkable success in clean environments but faces significant challenges in complex, real-world scenarios where speech is often mixed with background music or noise. Current state-of-the-art methods…

The success of deep learning-based speaker verification systems is largely attributed to access to large-scale and diverse speaker identity data. However, collecting data from more identities is expensive, challenging, and often limited by…

Separating a singing voice from its music accompaniment remains an important challenge in the field of music information retrieval. We present a unique neural network approach inspired by a technique that has revolutionized the field of…

Recently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, the application of diffusion models for synthesizing time-varying audio faces…

Voice faking, driven primarily by recent advances in text-to-speech (TTS) synthesis technology, poses significant societal challenges. Currently, the prevailing assumption is that unaltered human speech can be considered genuine, while fake…

Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic content unchanged. Voice conversion involves multiple speech…

Music retrieval and recommendation applications often rely on content features encoded as embeddings, which provide vector representations of items in a music dataset. Numerous complementary embeddings can be derived from processing items…

A main challenge in applying deep learning to music processing is the availability of training data. One potential solution is Multi-task Learning, in which the model also learns to solve related auxiliary tasks on additional datasets to…

Various parametric representations have been proposed to model the speech signal. While the performance of such vocoders is well-known in the context of speech processing, their extrapolation to singing voice synthesis might not be…

Recent advancements in DeepFake generation, along with the proliferation of open-source tools, have significantly lowered the barrier for creating synthetic media. This trend poses a serious threat to the integrity and authenticity of…

Generative models achieve remarkable results in multiple data domains, including images and texts, among other examples. Unfortunately, malicious users exploit synthetic media for spreading misinformation and disseminating deepfakes.…

Cover song identification represents a challenging task in the field of Music Information Retrieval (MIR) due to complex musical variations between query tracks and cover versions. Previous works typically utilize hand-crafted features and…

This paper conducts a comprehensive layer-wise analysis of self-supervised learning (SSL) models for audio deepfake detection across diverse contexts, including multilingual datasets (English, Chinese, Spanish), partial, song, and…

The goal of this contribution is to use a parametric speech synthesis system for reducing background noise and other interferences from recorded speech signals. In a first step, Hidden Markov Models of the synthesis system are trained. Two…

Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same dataset. However, the problem remains challenging when one tries to generalize the detector to forgeries…

Synthetic data generation is gaining increasing popularity in different computer vision applications. Existing state-of-the-art face recognition models are trained using large-scale face datasets, which are crawled from the Internet and…

This paper addresses the challenges and advancements in speech recognition for singing, a domain distinctly different from standard speech recognition. Singing encompasses unique challenges, including extensive pitch variations, diverse…

Facing the diversity and growth of the musical field nowadays, the search for precise songs becomes more and more complex. The identity of the singer facilitates this search. In this project, we focus on the problem of identifying the…

Freely available and easy-to-use audio editing tools make it straightforward to perform audio splicing. Convincing forgeries can be created by combining various speech samples from the same person. Detection of such splices is important…

Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks. However,…