Most automatic speaker verification (ASV) systems are vulnerable to various spoofing attacks. In recent years, there have been many methods were proposed for detecting spoofing attacks in ASV, and significant progress has been made. However, current methods have shown little improvements in replay spoof attack detection as they lack a more suitable model for replay detection. To address this issue, in this paper, we propose a novel model based on attention-enhanced DenseNet-BiLSTM network and segment-based linear filter bank features. First, silent segments are selected from each speech signal by using a short-term zero-crossing rate and energy. If the total duration of silent segments only contains a very limited amount of data, the decaying tails will be selected instead. Second, the linear filter bank features are extracted from the selected segments in the relatively high-frequency domain. Finally, an attention-enhanced DenseNet-BiLSTM architecture which can avoid the problems of overfitting is built. To validate this model, we used two datasets, including BTAS2016 and ASVspoof2017. Experiments show that using the attention-enhanced DenseNet-BiLSTM model with the segment-based linear filter bank feature achieves the best performance. Compared with the baseline system based on constant Q cepstral coefficient and Gaussian mixture model (GMM), the proposed model can produce a relative improvement of 91.68% and 74.04% on the two data sets respectively.

Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker verification system is still vulnerable to spoofing attacks such as replay or Deep-Fake audio. Deep-Fake audio means that the spoofed utterances are generated using text-to-speech (TTS) and voice conversion (VC) algorithms. Here, we propose a novel framework based on hybrid features with the self-attention mechanism. It is expected that hybrid features can be used to get more discrimination capacity. Firstly, instead of only one type of conventional feature, deep learning features and Mel-spectrogram features will be extracted by two parallel paths: convolution neural networks and a short-time Fourier transform (STFT) followed by Mel-frequency. Secondly, features will be concatenated by a max-pooling layer. Thirdly, there is a Self-attention mechanism for focusing on essential elements. Finally, ResNet and a linear layer are built to get the results. Experimental results reveal that the hybrid features, compared with conventional features, can cover more details of an utterance. We achieve the best Equal Error Rate (EER) of 9.67\% in the physical access (PA) scenario and 8.94\% in the Deep fake task on the ASVspoof 2021 dataset. Compared with the best baseline system, the proposed approach improves by 74.60\% and 60.05\%, respectively.

The study of music-generated dance is a novel and challenging Image generation task. It aims to input a piece of music and seed motions, then generate natural dance movements for the subsequent music. Transformer-based methods face challenges in time series prediction tasks related to human movements and music due to their struggle in capturing the nonlinear relationship and temporal aspects. This can lead to issues like joint deformation, role deviation, floating, and inconsistencies in dance movements generated in response to the music. In this paper, we propose a Quaternion-Enhanced Attention Network (QEAN) for visual dance synthesis from a quaternion perspective, which consists of a Spin Position Embedding (SPE) module and a Quaternion Rotary Attention (QRA) module. First, SPE embeds position information into self-attention in a rotational manner, leading to better learning of features of movement sequences and audio sequences, and improved understanding of the connection between music and dance. Second, QRA represents and fuses 3D motion features and audio features in the form of a series of quaternions, enabling the model to better learn the temporal coordination of music and dance under the complex temporal cycle conditions of dance generation. Finally, we conducted experiments on the dataset AIST++, and the results show that our approach achieves better and more robust performance in generating accurate, high-quality dance movements. Our source code and dataset can be available from https://github.com/MarasyZZ/QEAN and https://google.github.io/aistplusplus_dataset respectively.