This paper introduces the Unbeatable Team’s submission to the ICASSP 2023 Deep Noise Suppression (DNS) Challenge. We expand our previous work, TEA-PSE, to its upgraded version – TEA-PSE 3.0. Specifically, TEA-PSE 3.0 incorporates a residual LSTM after squeezed temporal convolution network (S-TCN) to enhance sequence modeling capabilities. Additionally, the local-global representation (LGR) structure is introduced to boost speaker information extraction, and multi-STFT resolution loss is used to effectively capture the time-frequency characteristics of the speech signals. Moreover, retraining methods are employed based on the freeze training strategy to fine-tune the system. According to the official results, TEA-PSE 3.0 ranks 1st in both ICASSP 2023 DNS-Challenge track 1 and track 2.

The ICASSP 2023 Speech Signal Improvement (SSI) Challenge concentrates on improving the speech signal quality of real-time communication (RTC) systems. In this paper, we introduce the speech signal improvement network (SSI-Net) submitted to the ICASSP 2023 SSI Challenge, which satisfies the real-time condition. The proposed SSI-Net has a multi-stage architecture. We present the time-domain restoration generative adversarial network (TRGAN) in the first restoration stage for speech restoration. Regarding the second enhancement stage, we employ a lightweight multi-scale temporal frequency convolutional network with axial self-attention (MTFAA-Net) called MTFAA-Lite to enhance the fullband speech. In the subjective test on the SSI Challenge blind test set, our proposed SSI-Net yields a P.835 overall mean opinion score (MOS) of 3.190 and a P.804 overall MOS of 3.178, which eventually takes the 3rd place in tracks 1&2.

Recently, multi-channel speech enhancement has drawn much interest due to the use of spatial information to distinguish target speech from interfering signal. To make full use of spatial information and neural network based masking estimation, we propose a multi-channel denoising neural network - Spatial DCCRN. Firstly, we extend S-DCCRN to multi -channel scenario, aiming at performing cascaded sub-channel and full-channel processing strategy, which can model different channels separately. Moreover, instead of only adopting multi-channel spectrum or concatenating first-channel's magnitude and IPD as the model's inputs, we apply an angle feature extraction module (AFE) to extract frame-level angle feature embeddings, which can help the model to apparently perceive spatial information. Finally, since the phenomenon of residual noise will be more serious when the noise and speech exist in the same time frequency (TF) bin, we particularly design a masking and mapping filtering method to substitute the traditional filter-and-sum operation, with the purpose of cascading coarsely denoising, dereverberation and residual noise suppression. The proposed model, Spatial-DCCRN, has surpassed EaBNet, FasNet as well as several competitive models on the L3DAS22 Challenge dataset. Not only the 3D scenario, Spatial-DCCRN outperforms state-of-the-art (SOTA) model MIMO-UNet by a large margin in multiple evaluation metrics on the multi-channel ConferencingSpeech2021 Challenge dataset. Ablation studies also demonstrate the effectiveness of different contributions.

Multispectral images contain many clues of surface characteristics of the objects, thus can be used in many computer vision tasks, e.g., recolorization and segmentation. However, due to the complex geometry structure of natural scenes, the spectra curves of the same surface can look very different under different illuminations and from different angles. In this paper, a new Multispectral Image Intrinsic Decomposition model (MIID) is presented to decompose the shading and reflectance from a single multispectral image. We extend the Retinex model, which is proposed for RGB image intrinsic decomposition, for multispectral domain. Based on this, a subspace constraint is introduced to both the shading and reflectance spectral space to reduce the ill-posedness of the problem and make the problem solvable. A dataset of 22 scenes is given with the ground truth of shadings and reflectance to facilitate objective evaluations. The experiments demonstrate the effectiveness of the proposed method.

Speaker diarization in noisy conditions is addressed in this paper. The regression-based DNN is first adopted to map the noisy acoustic features to the clean features, and then consensus clustering of the original and mapped features is used to fuse the diarization results. The experiments are conducted on the IFLY-DIAR-II database, which is a Chinese talk show database with various noise types, such as music, applause and laughter. Compared to the baseline system using PLP features, a 21.26% relative DER improvement can be achieved using the proposed algorithm.