Long Yan

Zhifang Guo, Jianguo Mao, Rui Tao et al.

Text-based audio generation models have limitations as they cannot encompass all the information in audio, leading to restricted controllability when relying solely on text. To address this issue, we propose a novel model that enhances the controllability of existing pre-trained text-to-audio models by incorporating additional conditions including content (timestamp) and style (pitch contour and energy contour) as supplements to the text. This approach achieves fine-grained control over the temporal order, pitch, and energy of generated audio. To preserve the diversity of generation, we employ a trainable control condition encoder that is enhanced by a large language model and a trainable Fusion-Net to encode and fuse the additional conditions while keeping the weights of the pre-trained text-to-audio model frozen. Due to the lack of suitable datasets and evaluation metrics, we consolidate existing datasets into a new dataset comprising the audio and corresponding conditions and use a series of evaluation metrics to evaluate the controllability performance. Experimental results demonstrate that our model successfully achieves fine-grained control to accomplish controllable audio generation. Audio samples and our dataset are publicly available at https://conditionaudiogen.github.io/conditionaudiogen/

Zhirong Ye, Xiangdong Wang, Hong Liu et al.

Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level prediction, converting it into a sequence multi-label classification problem. A critical issue with the frame-based model is that it pursues the best frame-level prediction rather than the best event-level prediction. Besides, it needs post-processing and cannot be trained in an end-to-end way. This paper firstly presents the one-dimensional Detection Transformer (1D-DETR), inspired by Detection Transformer for image object detection. Furthermore, given the characteristics of SED, the audio query branch and a one-to-many matching strategy for fine-tuning the model are added to 1D-DETR to form Sound Event Detection Transformer (SEDT). To our knowledge, SEDT is the first event-based and end-to-end SED model. Experiments are conducted on the URBAN-SED dataset and the DCASE2019 Task4 dataset, and both show that SEDT can achieve competitive performance.

Ke Wang, Gang Li, Junlan Chen et al.

China is the world's largest automotive market and is ambitious for autonomous vehicles (AVs) development. As one of the key goals of AVs, pedestrian safety is an important issue in China. Despite the rapid development of driverless technologies in recent years, there is a lack of researches on the adaptability of AVs to pedestrians. To fill the gap, this study would discuss the adaptability of current driverless technologies to China urban pedestrians by reviewing the latest researches. The paper firstly analyzed typical Chinese pedestrian behaviors and summarized the safety demands of pedestrians for AVs through articles and open database data, which are worked as the evaluation criteria. Then, corresponding driverless technologies are carefully reviewed. Finally, the adaptability would be given combining the above analyses. Our review found that autonomous vehicles have trouble in the occluded pedestrian environment and Chinese pedestrians do not accept AVs well. And more explorations should be conducted on standard human-machine interaction, interaction information overload avoidance, occluded pedestrians detection and nation-based receptivity research. The conclusions are very useful for motor corporations and driverless car researchers to place more attention on the complexity of the Chinese pedestrian environment, for transportation experts to protect pedestrian safety in the context of AVs, and for governors to think about making new pedestrians policies to welcome the upcoming driverless cars.