相关论文: DDSP-QbE++: Improving Speech Quality for Speech An…
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…
We study mechanical amplification and noise squeezing in a nonlinear nanomechanical resonator driven by an intense pump near its dynamical bifurcation point, namely, the onset of Duffing bistability. Phase sensitive amplification is…
Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…
Quantum error correction protocols require rapid and repeated qubit measurements. While multiplexed readout in superconducting quantum systems improves efficiency, fast probe pulses introduce spectral broadening, leading to signal leakage…
We present QSilk, a lightweight, always-on stabilization layer for latent diffusion that improves high-frequency fidelity while suppressing rare activation spikes. QSilk combines (i) a per-sample micro clamp that gently limits extreme…
We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only…
Digital pulse width modulation has been considered for high-fidelity and high-efficiency audio amplifiers for several years. It has been shown that the distortion can be reduced and the implementation of the system can be simplified if the…
In this paper, we propose an audio declipping method that takes advantages of both sparse optimization and deep learning. Since sparsity-based audio declipping methods have been developed upon constrained optimization, they are adjustable…
This paper targets a new scenario that integrates speech separation with speech compression, aiming to disentangle multiple speakers while producing discrete representations for efficient transmission or storage, with applications in online…
Speech signals in real-world environments are frequently affected by various distortions such as additive noise, reverberation, and bandwidth limitation, which may appear individually or in combination. Traditional speech enhancement…
In this paper, a two-stage dual tree complex wavelet packet transform (DTCWPT) based speech enhancement algorithm has been proposed, in which a speech presence probability (SPP) estimator and a generalized minimum mean squared error (MMSE)…
In this paper, a speech enhancement method based on noise compensation performed on short time magnitude as well phase spectra is presented. Unlike the conventional geometric approach (GA) to spectral subtraction (SS), here the noise…
As a neurophysiological response to threat or adverse conditions, stress can affect cognition, emotion and behaviour with potentially detrimental effects on health in the case of sustained exposure. Since the affective content of speech is…
With just a few speech samples, it is possible to perfectly replicate a speaker's voice in recent years, while malicious voice exploitation (e.g., telecom fraud for illegal financial gain) has brought huge hazards in our daily lives.…
Starting from the Quantum-Phase-Estimate (QPE) algorithm, a method is proposed to construct entangled states that describe correlated many-body systems on quantum computers. Using operators for which the discrete set of eigenvalues is…
This paper proposes an expressive singing voice synthesis system by introducing explicit vibrato modeling and latent energy representation. Vibrato is essential to the naturalness of synthesized sound, due to the inherent characteristics of…
As deepfake audio becomes more realistic and diverse, developing generalizable countermeasure systems has become crucial. Existing detection methods primarily depend on XLS-R front-end features to improve generalization. Nonetheless, their…
Auditory Attention Detection (AAD) aims to detect target speaker from brain signals in a multi-speaker environment. Although EEG-based AAD methods have shown promising results in recent years, current approaches primarily rely on…
Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples…
Amplitude amplification provides a quadratic speed-up for an array of quantum algorithms when run on a quantum machine perfectly isolated from its environment. However, the advantage is substantially diminished as the NISQ-era quantum…