False fame prevented: Avoiding fluency effects without judgmental correction.

Three studies show a way to prevent fluency effects independently of judgmental correction strategies by identifying and procedurally blocking the sources of fluency variations, which are assumed to be embodied in nature. For verbal stimuli, covert pronunciations are assumed to be the crucial source of fluency gains. As a consequence, blocking such pronunciation simulations through a secondary oral motor task decreased the false-fame effect for repeatedly presented names of actors (Experiment 1) as well as prevented increases in trust due to repetition for brand names and names of shares in the stock market (Experiment 2). Extending this evidence beyond repeated exposure, we demonstrated that blocking oral motor simulations also prevented fluency effects of word pronunciation on judgments of hazardousness (Experiment 3). Concerning the realm of judgment correction, this procedural blocking of (biasing) associative processes is a decontamination method not considered before in the literature, because it is independent of exposure control, mood, motivation, and post hoc correction strategies. The present results also have implications for applied issues, such as advertising and investment decisions. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Proper Name Pronunciations for Speech Technology Applications

This paper describes a 15-year research effort to improve the automatic pronunciation of proper names and details the issues involved in applying those pronunciations to speech synthesis and speech recognition. Our approach consists primarily of a large hand-tuned rule component, supplemented by a comparatively small pronunciation dictionary, both guided by extensive survey and polling data. Compared to other state-of-the-art programs, we use language-class identification to smaller degree. We utilize alternate pronunciations, obtained from the polling data, for both synthesis and recognition purposes. While our approach yields comparatively high accuracies, a comprehensive database of names and their pronunciations verified and authenticated through customer interactions (such as auto-attendants and automated directory assistance) will likely be the best future resource defining the ultimate in accuracy.     

解决多音字字-音转换的一种统计学习方法

字-音转换是语音合成系统中的一个重要模块,其中多音词和以单字词形式存在的多音字读音的确定一直是个没有很好解决的问题。本文通过对大量标注有正确拼音的语料的统计,指出着重解决41个重点多音字和22个重点多音词就可基本解决字-音转换的问题。本文采用基于扩展的随机复杂度的随机决策列表方法自动提取多音字(词)的读音规则,将字-音转换的错误率由8.8‰降低到4.4‰。规则的训练和测试的材料的标注是一个耗费人力和时间的工作,而训练材料的数量和质量又直接影响最终的结果。本文提出一种半自动的语料标注流程,可以节省将近一半的人工和时间。     

汝州方言的文白异读

汝州方言属于中原官话郑曹片,分别从声母的文白异读、韵母的文白异读、声调的文白异读、声韵调某两方面的文白异读、声韵调均异读等五方面的举例探讨了汝州方言的文白异读现象。