Related papers: Using Cyclic Noise as the Source Signal for Neural…

For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall…

We present a method to separate speech signals from noisy environments in the embedding space of a neural audio codec. We introduce a new training procedure that allows our model to produce structured encodings of audio waveforms given by…

The advancements of AI-synthesized human voices have introduced a growing threat of impersonation and disinformation. It is therefore of practical importance to developdetection methods for synthetic human voices. This work proposes a new…

This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently, DDPM-based neural vocoders have gained prominence as…

We investigate a method to incorporate signal models that allow an additional frequency harmonic in searches for gravitational waves from spinning neutron stars. We assume emission is given by the general triaxial non-aligned model of…

Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical…

In this work, we incorporated acoustically derived source features, aperiodicity, periodicity and pitch as additional targets to an acoustic-to-articulatory speech inversion (SI) system. We also propose a Temporal Convolution based SI…

The spectrum of a CW field whose phase experiences a periodic sawtooth modulation is analyzed. Two types of the sawtooth phase modulation are considered. One is created by combining many harmonics of the fundamental frequency. The second is…

Disorders of voice production have severe effects on the quality of life of the affected individuals. A simulation approach is used to investigate the cause-effect chain in voice production showing typical characteristics of voice such as…

In this paper, we introduce a spectral-domain inverse filtering approach for single-channel speech de-reverberation using deep convolutional neural network (CNN). The main goal is to better handle realistic reverberant conditions where the…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

Statistical signal processing based speech enhancement methods adopt expert knowledge to design the statistical models and linear filters, which is complementary to the deep neural network (DNN) based methods which are data-driven. In this…

A novel nonlinear model predictive control approach for state signal shaping is proposed. The control strategy introduces a residual shape cost kernel based on the dynamics of circular limit cycles from a supercritical Neimark-Sacker…

Generating synthetic financial time series data that accurately reflects real-world market dynamics holds tremendous potential for various applications, including portfolio optimization, risk management, and large scale machine learning. We…

We present a neural analysis and synthesis (NANSY) framework that can manipulate voice, pitch, and speed of an arbitrary speech signal. Most of the previous works have focused on using information bottleneck to disentangle analysis features…

Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative…

This study investigates the behavior of Causal Convolutional Neural Networks (CNNs) with quasi-linear activation functions when applied to time-series data characterized by multimodal frequency content. We demonstrate that, once trained,…

Controllable Singing Voice Synthesis (SVS) aims to generate expressive singing voices reflecting user intent. While recent SVS systems achieve high audio quality, most rely on probabilistic modeling, limiting precise control over attributes…

This method solves the dual problem of blind deconvolution and estimation of the time waveform of noisy second-order cyclo-stationary (CS2) signals that traverse a Transfer Function (TF) en route to a sensor. We have proven that the…

A vocoder is a conditional audio generation model that converts acoustic features such as mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal Processing (DDSP), we propose a new vocoder named SawSing for…