相关论文: DDSP-QbE++: Improving Speech Quality for Speech An…

We explore two approaches to creatively altering vocal timbre using Differentiable Digital Signal Processing (DDSP). The first approach is inspired by classic cross-synthesis techniques. A pretrained DDSP decoder predicts a filter for a…

Speech anonymisation aims to protect speaker identity by changing personal identifiers in speech while retaining linguistic content. Current methods fail to retain prosody and unique speech patterns found in elderly and pathological speech…

In this paper, we propose a dual-stage architecture for bandwidth extension (BWE) increasing the effective sampling rate of speech signals from 8 kHz to 48 kHz. Unlike existing end-to-end deep learning models, our proposed method explicitly…

Controlling the variations of sound effects using neural audio synthesis models has been a difficult task. Differentiable digital signal processing (DDSP) provides a lightweight solution that achieves high-quality sound synthesis while…

Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is…

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…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter and have been used as natural, grounded features for speech synthesis. Differentiable digital signal…

A differentiable digital signal processing (DDSP) autoencoder is a musical sound synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis. It allows us to flexibly edit sounds by changing the fundamental…

Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech…

Tools to generate high quality synthetic speech signal that is perceptually indistinguishable from speech recorded from human speakers are easily available. Several approaches have been proposed for detecting synthetic speech. Many of these…

Recently, self-supervised learning (SSL) techniques have been introduced to solve the monaural speech enhancement problem. Due to the lack of using clean phase information, the enhancement performance is limited in most SSL methods.…

Generating sound effects with controllable variations is a challenging task, traditionally addressed using sophisticated physical models that require in-depth knowledge of signal processing parameters and algorithms. In the era of…

Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Quantum phase estimation (QPE) is a cornerstone algorithm for extracting Hamiltonian eigenvalues, but its standard, eigenstate-centric form relies on carefully prepared coherent inputs that are costly or impractical for many strongly…

Differentiable digital signal processing (DDSP) techniques, including methods for audio synthesis, have gained attention in recent years and lend themselves to interpretability in the parameter space. However, current differentiable…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Adaptive sampling results in dramatic improvements in the recovery of sparse signals in white Gaussian noise. A sequential adaptive sampling-and-refinement procedure called Distilled Sensing (DS) is proposed and analyzed. DS is a form of…

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…