Related papers: Metric-oriented Speech Enhancement using Diffusion…

Single-channel speech enhancement models face significant performance degradation in extremely noisy environments. While prior work has shown that complementary bone-conducted speech can guide enhancement, effective integration of this…

This paper presents a speech enhancement method, where an adaptive threshold is statistically determined based on Gaussian modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of noisy speech. In order to…

Remote sensing image change description represents an innovative multimodal task within the realm of remote sensing processing.This task not only facilitates the detection of alterations in surface conditions, but also provides…

Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is…

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing…

Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge…

Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the…

Diffusion model, as a new generative model which is very popular in image generation and audio synthesis, is rarely used in speech enhancement. In this paper, we use the diffusion model as a module for stochastic refinement. We propose…

Creating synthetic voices with found data is challenging, as real-world recordings often contain various types of audio degradation. One way to address this problem is to pre-enhance the speech with an enhancement model and then use the…

We propose a training method for deep neural network (DNN)-based source enhancement to increase objective sound quality assessment (OSQA) scores such as the perceptual evaluation of speech quality (PESQ). In many conventional studies, DNNs…

Mixture-of-Experts (MoE) is a promising way to scale up the learning capacity of large language models. It increases the number of parameters while keeping FLOPs nearly constant during inference through sparse activation. Yet, it still…

In this paper, we propose a novel deep inductive transfer learning framework, named feature distribution adaptation network, to tackle the challenging multi-modal speech emotion recognition problem. Our method aims to use deep transfer…

The Mean Opinion Score (MOS) is fundamental to speech quality assessment. However, its acquisition requires significant human annotation. Although deep neural network approaches, such as DNSMOS and UTMOS, have been developed to predict MOS…

Speech signal analysis poses significant challenges, particularly in tasks such as speech quality evaluation and profiling, where the goal is to predict multiple perceptual and objective metrics. For instance, metrics like PESQ (Perceptual…

Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by limited training data or information loss during knowledge…

Speech-to-speech translation is a typical sequence-to-sequence learning task that naturally has two directions. How to effectively leverage bidirectional supervision signals to produce high-fidelity audio for both directions? Existing…

Enhancing noisy speech is an important task to restore its quality and to improve its intelligibility. In traditional non-machine-learning (ML) based approaches the parameters required for noise reduction are estimated blindly from the…

Singing voice conversion (SVC) is one promising technique which can enrich the way of human-computer interaction by endowing a computer the ability to produce high-fidelity and expressive singing voice. In this paper, we propose DiffSVC, an…

Recent studies show that using diffusion models for time series signal reconstruction holds great promise. However, such approaches remain largely unexplored in the domain of medical time series. The unique characteristics of the…

Hard-parameter sharing is a common strategy to train a single model jointly across diverse tasks. However, this often leads to task interference, impeding overall model performance. To address the issue, we propose a simple yet effective…