Xinwei Cao

Xinwei Cao, Mengxuan Lu, Torbjørn Svendsen et al.

We address the problem of out-of-distribution (OOD) detection for target observations embedded in a subspace of the high dimensional data space. Using continuous normalizing flows (CNFs), we propose a Lagrangian sub-flow (LSF) framework designed to isolate and estimate the density for the relevant components in the representation and using the remaining components as context. Through experimentation with models for speech synthesis, we show that CNFs, similarly to other deep generative models (DGMs), are susceptible to the "likelihood paradox", where high likelihood is erroneously assigned to OOD samples. This is attributed to the inductive bias of DGMs that prioritize low-level structural details over high-level semantic coherence. To mitigate this phenomenon, we propose a number of geometric diagnostic signals based on the velocity field over the sub-flow trajectory. Based on these signals, we design metrics for the challenging task of zero-shot phoneme-level mispronunciation detection. Finally, we demonstrate the superiority of these metrics compared to likelihood-based methods on a real-world mispronunciation detection benchmark.

Xinwei Cao, Zijian Fan, Torbjørn Svendsen et al.

Mispronunciation detection and diagnosis (MDD) is a significant part in modern computer aided language learning (CALL) systems. Within MDD, phoneme-level pronunciation assessment is key to helping L2 learners improve their pronunciation. However, most systems are based on a form of goodness of pronunciation (GOP) which requires pre-segmentation of speech into phonetic units. This limits the accuracy of these methods and the possibility to use modern CTC-based acoustic models for their evaluation. In this study, we first propose self-alignment GOP (GOP-SA) that enables the use of CTC-trained ASR models for MDD. Next, we define a more general alignment-free method that takes all possible alignments of the target phoneme into account (GOP-AF). We give a theoretical account of our definition of GOP-AF, an implementation that solves potential numerical issues as well as a proper normalization which makes the method applicable with acoustic models with different peakiness over time. We provide extensive experimental results on the CMU Kids and Speechocean762 datasets comparing the different definitions of our methods, estimating the dependency of GOP-AF on the peakiness of the acoustic models and on the amount of context around the target phoneme. Finally, we compare our methods with recent studies over the Speechocean762 data showing that the feature vectors derived from the proposed method achieve state-of-the-art results on phoneme-level pronunciation assessment.

Ameer Tamoor Khan, Xinwei Cao, Shuai Li

As a disruptive technology, blockchain, particularly its original form of bitcoin as a type of digital currency, has attracted great attentions. The innovative distributed decision making and security mechanism lay the technical foundation for its success, making us consider to penetrate the power of blockchain technology to distributed control and cooperative robotics, in which the distributed and secure mechanism is also highly demanded. Actually, security and distributed communication have long been unsolved problems in the field of distributed control and cooperative robotics. It has been reported on the network failure and intruder attacks of distributed control and multi-robotic systems. Blockchain technology provides promise to remedy this situation thoroughly. This work is intended to create a global picture of blockchain technology on its working principle and key elements in the language of control and robotics, to provide a shortcut for beginners to step into this research field.