Related papers: Revisiting Representation Learning for Singing Voi…

Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment. In this study, we propose the integration of two…

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…

Music source separation has been a popular topic in signal processing for decades, not only because of its technical difficulty, but also due to its importance to many commercial applications, such as automatic karoake and remixing. In this…

Singing voice synthesis (SVS) has seen remarkable advancements in recent years. However, compared to speech and general audio data, publicly available singing datasets remain limited. In practice, this data scarcity often leads to…

Conventional approaches to sound localization and separation are based on microphone arrays in artificial systems. Inspired by the selective perception of human auditory system, we design a multi-source listening system which can separate…

We present a physics-informed voiced backend renderer for singing-voice synthesis. Given synthetic single-channel audio and a fund-amental--frequency trajectory, we train a time-domain Webster model as a physics-informed neural network to…

The detection of anomalous sounds in machinery operation presents a significant challenge due to the difficulty in generalizing anomalous acoustic patterns. This task is typically approached as an unsupervised learning or novelty detection…

Self-supervised audio-visual source separation leverages natural correlations between audio and vision modalities to separate mixed audio signals. In this work, we first systematically analyse the performance of existing multimodal fusion…

The single-speaker singing voice synthesis (SVS) usually underperforms at pitch values that are out of the singer's vocal range or associated with limited training samples. Based on our previous work, this work proposes a…

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein distance is replaced by…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

Speech separation has recently made significant progress thanks to the fine-grained vision used in time-domain methods. However, several studies have shown that adopting Short-Time Fourier Transform (STFT) for feature extraction could be…

Supervised multi-channel audio source separation requires extracting useful spectral, temporal, and spatial features from the mixed signals. The success of many existing systems is therefore largely dependent on the choice of features used…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

We propose a novel unsupervised singing voice detection method which use single-channel Blind Audio Source Separation (BASS) algorithm as a preliminary step. To reach this goal, we investigate three promising BASS approaches which operate…

Monaural source separation is important for many real world applications. It is challenging because, with only a single channel of information available, without any constraints, an infinite number of solutions are possible. In this paper,…

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Deep learning based models have significantly improved the performance of speech separation with input mixtures like the cocktail party. Prominent methods (e.g., frequency-domain and time-domain speech separation) usually build regression…

Neural speech separation has made remarkable progress and its integration with automatic speech recognition (ASR) is an important direction towards realizing multi-speaker ASR. This work provides an insightful investigation of speech…

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…