Related papers: SingMOS: An extensive Open-Source Singing Voice Da…
We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding…
Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry. In automatic song writing, lyric-to-melody generation and melody-to-lyric generation are two…
Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS…
Singing Voice Synthesis (SVS) has witnessed significant advancements with the advent of deep learning techniques. However, a significant challenge in SVS is the scarcity of labeled singing voice data, which limits the effectiveness of…
Note-level automatic music transcription is one of the most representative music information retrieval (MIR) tasks and has been studied for various instruments to understand music. However, due to the lack of high-quality labeled data,…
We present a database of parallel recordings of speech and singing, collected and released by the Human Language Technology (HLT) laboratory at the National University of Singapore (NUS), that is called NUS-HLT Speak-Sing (NHSS) database.…
Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professional granularity to capture multi-dimensional aesthetic nuances. In this paper, we propose…
We propose an algorithm that is capable of synthesizing high quality target speaker's singing voice given only their normal speech samples. The proposed algorithm first integrate speech and singing synthesis into a unified framework, and…
We introduce SHEET, a multi-purpose open-source toolkit designed to accelerate subjective speech quality assessment (SSQA) research. SHEET stands for the Speech Human Evaluation Estimation Toolkit, which focuses on data-driven deep neural…
The advancement of machine learning in audio analysis has opened new possibilities for technology-enhanced music education. This paper introduces a framework for automatic singing mistake detection in the context of music pedagogy,…
Reviews of songs play an important role in online music service platforms. Prior research shows that users can make quicker and more informed decisions when presented with meaningful song reviews. However, reviews of music songs are…
Singing voice synthesis (SVS) aims to generate expressive and high-quality vocals from musical scores, requiring precise modeling of pitch, duration, and articulation. While diffusion-based models have achieved remarkable success in image…
Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, personalities, and emotions. Such controllable voice creation…
Automatic Speech Recognition and Text-to-Speech systems are primarily trained in a supervised fashion and require high-quality, accurately labeled speech datasets. In this work, we examine common problems with speech data and introduce a…
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…
Our quality audit for three widely used public multilingual speech datasets - Mozilla Common Voice 17.0, FLEURS, and Vox Populi - shows that in some languages, these datasets suffer from significant quality issues, which may obfuscate…
In this study, we present SingVisio, an interactive visual analysis system that aims to explain the diffusion model used in singing voice conversion. SingVisio provides a visual display of the generation process in diffusion models,…
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…
Human annotations of mood in music are essential for music generation and recommender systems. However, existing datasets predominantly focus on Western songs with terms derived from English, which may limit generalizability across diverse…
Increasing amount of research has shed light on machine perception of audio events, most of which concerns detection and classification tasks. However, human-like perception of audio scenes involves not only detecting and classifying audio…