Related papers: Singer Identity Representation Learning using Self…

We conduct an investigation on various hyper-parameters regarding neural networks used to generate spectral envelopes for singing synthesis. Two perceptive tests, where the first compares two models directly and the other ranks models with…

There are individual differences in expressive behaviors driven by cultural norms and personality. This between-person variation can result in reduced emotion recognition performance. Therefore, personalization is an important step in…

Conventional singing voice conversion (SVC) methods often suffer from operating in high-resolution audio owing to a high dimensionality of data. In this paper, we propose a hierarchical representation learning that enables the learning of…

Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embeddings, designed for discrimination rather than characterizing…

Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its…

A text-independent speaker recognition system relies on successfully encoding speech factors such as vocal pitch, intensity, and timbre to achieve good performance. A majority of such systems are trained and evaluated using spoken voice or…

Deep learning based singing voice synthesis (SVS) systems have been demonstrated to flexibly generate singing with better qualities, compared to conventional statistical parametric based methods. However, neural systems are generally…

In this paper, we propose MakeSinger, a semi-supervised training method for singing voice synthesis (SVS) via classifier-free diffusion guidance. The challenge in SVS lies in the costly process of gathering aligned sets of text, pitch, and…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

The deepfake generation of singing vocals is a concerning issue for artists in the music industry. In this work, we propose a singing voice deepfake detection (SVDD) system, which uses noise-variant encodings of open-AI's Whisper model. As…

Self-supervised models, namely, wav2vec and its variants, have shown promising results in various downstream tasks in the speech domain. However, their inner workings are poorly understood, calling for in-depth analyses on what the model…

We study the problem of semi-supervised singing voice separation, in which the training data contains a set of samples of mixed music (singing and instrumental) and an unmatched set of instrumental music. Our solution employs a single…

Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings. In this work, we propose a novel self-supervised approach…

Singing voice synthesis has made remarkable progress in generating natural and high-quality voices. However, existing methods rarely provide precise control over vocal techniques such as intensity, mixed voice, falsetto, bubble, and breathy…

This paper presents our systems (denoted as T13) for the singing voice conversion challenge (SVCC) 2023. For both in-domain and cross-domain English singing voice conversion (SVC) tasks (Task 1 and Task 2), we adopt a recognition-synthesis…

Most singer identification methods are processed in the frequency domain, which potentially leads to information loss during the spectral transformation. In this paper, instead of the frequency domain, we propose an end-to-end architecture…

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the…