Advanced text to speech (TTS) models such as FastSpeech [20] can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-tomany mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacherstudent distillation pipeline is complicated, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs during training and use predicted values during inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of full end-to-end training and even faster inference than FastSpeech. Experimental results show that 1) FastSpeech 2 and 2s outperform FastSpeech in voice quality with much simplified training pipeline and reduced training time; 2) FastSpeech 2 and 2s can match the voice quality of autoregressive models while enjoying much faster inference speed. Audio samples are available at https://speechresearch. github.io/fastspeech2/.

No abstract

Existing autonomous driving pipelines separate the perception module from the prediction module. The two modules communicate via hand-picked features such as agent boxes and trajectories as interfaces. Due to this separation, the prediction module only receives partial information from the perception module. Even worse, errors from the perception modules can propagate and accumulate, adversely affecting the prediction results. In this work, we propose ViP3D, a visual trajectory prediction pipeline that leverages the rich information from raw videos to predict future trajectories of agents in a scene. ViP3D employs sparse agent queries throughout the pipeline, making it fully differentiable and interpretable. Furthermore, we propose an evaluation metric for this novel end-to-end visual trajectory prediction task. Extensive experimental results on the nuScenes dataset show the strong performance of ViP3D over traditional pipelines and previous end-to-end models. 1

Service industries contribute significantly to the economic, social, and even life aspect of the world. However, service innovation has been rarely discussed in healthcare context, especially in the digital healthcare context Service innovation needs to be organized in the premise of mutual trust to be efficient, thereby improving service performance. The trust and efficiency here demands a good online platform service to both virtualize the interaction processes and maintain trust and agency. This research uses social network theory and agency theory to emphasize the importance of trust in cooperation in hospitals, and the relationship between organizational trust and organizational performance. Furthermore, we analyzed the role of agents in enhancing the relationship between service innovation and trust. Based on the analyses, five propositions and future research directions are proposed.

No abstract