Related papers: Maximum Voiced Frequency Estimation: Exploiting Am…
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…
Sound field reproduction methods based on numerical optimization, which aim to minimize the error between synthesized and desired sound fields, are useful in many practical scenarios because of their flexibility in the array geometry of…
This paper introduces a general and flexible framework for F0 and aperiodicity (additive non periodic component) analysis, specifically intended for high-quality speech synthesis and modification applications. The proposed framework…
In clinical voice signal analysis, mishandling of subharmonic voicing may cause an acoustic parameter to signal false negatives. As such, the ability of a fundamental frequency estimator to identify speaking fundamental frequency is…
Most of the deep learning based speech enhancement (SE) methods rely on estimating the magnitude spectrum of the clean speech signal from the observed noisy speech signal, either by magnitude spectral masking or regression. These methods…
We study the computational phase transition in a multi-frequency group synchronization problem, where pairwise relative measurements of group elements are observed across multiple frequency channels and corrupted by Gaussian noise. Using…
This article focuses on the research tool for investigating the fundamental frequencies of voiced sounds. We introduce an objective and informative measurement method of pitch extractors' response to frequency-modulated tones. The method…
Decomposition of an audio mixture into harmonic and percussive components, namely harmonic/percussive source separation (HPSS), is a useful pre-processing tool for many audio applications. Popular approaches to HPSS exploit the distinctive…
Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end…
Recent advances in emotional voice conversion (EVC) have enabled the generation of expressive synthetic speech, raising new concerns in audio deepfake detection. Existing approaches treat speech as a homogeneous signal and largely overlook…
Most speech enhancement algorithms make use of the short-time Fourier transform (STFT), which is a simple and flexible time-frequency decomposition that estimates the short-time spectrum of a signal. However, the duration of short STFT…
A deep neural network solution for time-scale modification (TSM) focused on large stretching factors is proposed, targeting environmental sounds. Traditional TSM artifacts such as transient smearing, loss of presence, and phasiness are…
A two-step enhancement method based on spectral subtraction and phase spectrum compensation is presented in this paper for noisy speeches in adverse environments involving non-stationary noise and medium to low levels of SNR. The magnitude…
Many multi-microphone speech enhancement algorithms require the relative transfer function (RTF) vector of the desired speech source, relating the acoustic transfer functions of all array microphones to a reference microphone. In this…
Deep learning based speech enhancement and source separation systems have recently reached unprecedented levels of quality, to the point that performance is reaching a new ceiling. Most systems rely on estimating the magnitude of a target…
In our previous work, we proposed a neural vocoder called APNet, which directly predicts speech amplitude and phase spectra with a 5 ms frame shift in parallel from the input acoustic features, and then reconstructs the 16 kHz speech…
Time-frequency (T-F) domain-based neural vocoders have shown promising results in synthesizing high-fidelity audio. Nevertheless, it remains unclear on the mechanism of effectively predicting magnitude and phase targets jointly. In this…
Bayesian estimation of short-time spectral amplitude is one of the most predominant approaches for the enhancement of the noise corrupted speech. The performance of these estimators are usually significantly improved when any perceptually…
The research presents a voice conversion model using coefficient mapping and neural network. Most previous works on parametric speech synthesis did not account for losses in spectral details causing over smoothing and invariably, an…
Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…