为了探索情感语音相对于中性语音的变化规律,该文对实验室采集的中文情感语音库M A SC@CCNT进行初步实验分析。首先对语音库进行听辨分析,甄选感情明显的语料,再针对含有兴高采烈、愤怒、惊慌、悲伤等4种情感的语音信号,分析它们的时间构造、能量构造、基频构造和共振峰构造的特征,并通过和不带感情的平静语音信号特征进行比较,得出了不同情感信号特征的分布变化规律。结果表明:时间构造、频谱、能量、基音频率和元音共振峰这5种特征在分辨情感语音上有着明显的作用,而悲伤情感最易分辨;情感语音的变化没有统一的规律,因说话人的性别而异,甚至因人而异。
In hard real-time systems, schedulability analysis is not only one of the important means of guaranteeing the timelines of embedded software but also one of the fundamental theories of applying other new techniques, such as energy savings and fault tolerance. However, most of the existing schedulability analysis methods assume that schedulers use preemptive scheduling or non-preemptive scheduling. In this paper, we present a schedulability analysis method, i.e., the worst-case hybrid scheduling (WCHS) algorithm, which considers the influence of release jitters of transactions and extends schedulability analysis theory to timing analysis of linear transactions under fixed priority hybrid scheduling. To the best of our knowledge, this method is the first one on timing analysis of linear transactions under hybrid scheduling. An example is employed to demonstrate the use of this method. Experiments show that this method has lower computational complexity while keeping correctness, and that hybrid scheduling has little influence on the average worst-case response time (WCRT), but a negative impact on the schedulability of systems.
Smart cars are promising application domain for ubiquitous computing. Context-awareness is the key feature of a smart car for safer and easier driving. Despite many industrial innovations and academic progresses have been made, we find a lack of fully context-aware smart cars. This study presents a general architecture of smart cars from the viewpoint of context- awareness. A hierarchical context model is proposed for description of the complex driving environment. A smart car prototype including software platform and hardware infrastructures is built to provide the running environment for the context model and applications. Two performance metrics were evaluated: accuracy of the context situation recognition and efficiency of the smart car. The whole response time of context situation recognition is nearly 1.4 s for one person, which is acceptable for non-time critical applications in a smart car.
