Speech enhancement has benefited from the success of deep learning in terms of
intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods …

Self-supervised learning (SSL) representation for speech has achieved state-of-the-art
(SOTA) performance on several downstream tasks. However, there remains room for …

Under our previous work on frequency bin-wise independent processing, a dramatic
reduction of the computational complexity for recurrent neural networks (RNN) is achieved …

This paper describes a method based on deep metric learning for content-based cross-
modal retrieval of a piece of music and its representative image (ie, a music audio signal …

This paper presents a denoising and dereverberation hierarchical neural vocoder (DNR-
HiNet) to convert noisy and reverberant acoustic features into clean speech waveforms. The …

Airborne speech enhancement is always a major challenge for the security of airborne
systems. Recently, multi-objective learning technology has become one of the mainstream …

Single-channel speech enhancement approaches do not always improve automatic
recognition rates in the presence of noise, because they can introduce distortions unhelpful …

Many state-of-the-art speech enhancement (SE) systems have recently used convolutional
neural networks (CNNs) to extract multi-scale feature maps. However, CNN relies more on …

This paper presents a denoising and dereverberation hierarchical neural vocoder (DNR-
HiNet) to convert noisy and reverberant acoustic features into a clean speech waveform. We …

In real time, the speech signal received contains noise produced in the background and
reverberations. These disturbances reduce the quality of speech; therefore, it is important to …