RI:Small Time-Based Language Modeling

RI:基于时间的小型语言建模

• 批准号: 0914868
• 负责人: Nigel Ward
• 金额: $ 45万
• 依托单位: University of Texas at El Paso
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-10-01 至 2014-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0914868&HistoricalAwards=false
• 关键词: RI; Small; Time; Based; Language

Speech recognizers all include a component for predicting, based on the past context, what words are likely to appear next. Today these components, known as language models, operate at the symbol level, abstracted away from the details of how and when the words are spoken. Spoken language, however, is not just a symbolic or mathematical object, but is produced and understood by human brains, with specific processing constraints, and these can directly affect what happens when in dialog.This project is developing language models and ``dialog models'' that explicitly use the information in the timings of words. Inspired by psychological research suggesting that dialog and language behaviors are the result of multiple simultaneously active cognitive processes, the working assumption is that the words likely to be spoken at a given time depend, probabilistically, on the elapsed time since various reference points: for example since the speaker began talking, since the speaker's last disfluency, since the listener's last back-channel, etc. Statistical analyses of large corpora of human-human spoken dialogs, with machine learning methods, are revealing patterns and regularities which are being used to build language models with improved predictive power.These language models implicitly represent some aspects of dialog dynamics, with the potential to lead to an integrated understanding of the nature of dialog as a human ability. These improved language models are also likely to improve speech recognition accuracy, enabling the development of spoken language systems that are more accurate, more efficient, and more useful.

语音识别器都包括一个组件，用于根据过去的上下文预测接下来可能出现的单词。 今天，这些被称为语言模型的组件在符号级别上运行，从单词如何以及何时被说出的细节中抽象出来。 然而，口语不仅仅是一个符号或数学对象，而是由人类大脑产生和理解的，具有特定的处理限制，这些可以直接影响对话时发生的事情。该项目正在开发语言模型和"对话模型“，这些模型明确使用单词计时中的信息。受心理学研究的启发，对话和语言行为是多个同时活跃的认知过程的结果，工作假设是，在给定时间可能说出的单词取决于从各种参考点开始的时间：例如，从说话者开始说话起，从说话者的最后一次不流利起，从听者的最后一次反向通道起，等。使用机器学习方法对人-人口语对话的大型语料库进行的统计分析揭示了用于构建具有改进的预测能力的语言模型的模式和语义。这些语言模型隐含地表示对话动态的某些方面，有可能导致对对话作为人类能力的本质的综合理解。 这些改进的语言模型也有可能提高语音识别的准确性，从而能够开发更准确、更有效和更有用的口语系统。