While automatic speech recognition of either Cantonese or English alone has achieved a great degree of success, recognition of Canton-English code-mixing speech is not as trivial. This paper attempts to analyze the effect of language mixing on recognition performance of code-mixing utterances. By examining the recognition results of Canton-English code-mixing speech, where Canton is the matrix ...

Code-mixing is a common phenomenon in bilingual societies. It refers to the intra-sentential switching of two different languages in a spoken utterance. This paper presents the first study on automatic recognition of Cantonese-English code-mixing speech, which is common in Hong Kong. This study starts with the design and compilation of code-mixing speech and text corpora. The problems of acoust...

This paper investigates incremental part of speech tagging for speech transcripts that contain multilingual intrasentential code-mixing, and compares the accuracy of a monolithic tagging model trained on a heterogeneous-language dataset to a model that switches between two homogeneous-language tagging models dynamically using word-by-word language identification. We find that the dynamic model,...

Code-Mixing (CM) is a very commonly observed mode of communication in a multilingual configuration. The trends of using this newly emerging language has its effect as a culling option especially in platforms like social media. This becomes particularly important in the context of technology and health, where expressing the upcoming advancements is difficult in native language. Despite the chang...

Applying large scale pre-trained image-language model to video-language tasks has recently become a trend, which brings two challenges. One is how effectively transfer knowledge from static images dynamic videos, and the other deal with prohibitive cost of fully fine-tuning due growing size. Existing works that attempt realize parameter-efficient learning can be categorized into types: 1) appen...

We study personalized price competition with costly advertising among n quality-cost differentiated firms. Strategies involve mixing over both prices and whether to advertise. In equilibrium, only the top two firms advertise, earning “Bertrand-like” profits. Social efficiency is U-shaped in the ad cost, with losses due to excessive advertising and sales by the “wrong” firm. Quality or cost impr...

We describe a Unified Modelling Language (UML) diagramming tool that uses an E-whiteboard, pen-based sketching interface to support collaborative design. Our tool allows designers to sketch UML visual modelling language constructs, mixing different UML diagram components, free-hand annotations and hand-written text. A key novelty of our approach is the preservation of handdrawn diagrams and sup...

According to a recent survey, it is common for students to study two topics at the same time using flashcards, and students who do so virtually always keep the topics separate instead of mixing flashcards together (Wissman, Rawson, & Pyc, 2012). We predicted that mixing might be a relatively easy way to increase learning efficiency because mixing increases the spacing between repetitions of a g...