Related papers: Conditional Generative Adversarial Networks for Sp…

Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data. In this paper, we propose using a…

This paper proposes an approach for applying GANs to NMT. We build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generator and a discriminator. The generator aims to generate sentences…

With recent advances of diffusion model, generative speech enhancement (SE) has attracted a surge of research interest due to its great potential for unseen testing noises. However, existing efforts mainly focus on inherent properties of…

Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process.…

Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory quality of speech, but the enhanced feature distribution is…

In recent years, Generative Adversarial Networks (GANs) have seen significant advancements, leading to their widespread adoption across various fields. The original GAN architecture enables the generation of images without any specific…

Spatial target speaker extraction isolates a desired speaker's voice in multi-speaker environments using spatial information, such as the direction of arrival (DoA). Although recent deep neural network (DNN)-based discriminative methods…

The Transformer architecture has demonstrated a superior ability compared to recurrent neural networks in many different natural language processing applications. Therefore, our study applies a modified Transformer in a speech enhancement…

Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as part of model training…

Conventional predictive Artificial Neural Networks (ANNs) commonly employ deterministic weight matrices; therefore, their prediction is a point estimate. Such a deterministic nature in ANNs causes the limitations of using ANNs for medical…

One of the most significant challenges in statistical signal processing and machine learning is how to obtain a generative model that can produce samples of large-scale data distribution, such as images and speeches. Generative Adversarial…

Background noise reduces speech intelligibility and quality, making speaker verification (SV) in noisy environments a challenging task. To improve the noise robustness of SV systems, additive noise data augmentation method has been commonly…

Automatic syllable stress detection is a crucial component in Computer-Assisted Language Learning (CALL) systems for language learners. Current stress detection models are typically trained on clean speech, which may not be robust in…

Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…

Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to…

Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…

Conventional deep neural network (DNN)-based speech enhancement (SE) approaches aim to minimize the mean square error (MSE) between enhanced speech and clean reference. The MSE-optimized model may not directly improve the performance of an…

The prevailing method for neural speech enhancement predominantly utilizes fully-supervised deep learning with simulated pairs of far-field noisy-reverberant speech and clean speech. Nonetheless, these models frequently demonstrate…

Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the…

Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress…