STIMULATE: Modeling Structure in Speech above the Segment for Spontaneous Speech Recognition

电流 讲话 识别技术， 而 有用 在有限的领域与合作的发言者，仍然导致不可接受的 高 错误率（30-50%） 对 不受约束的对话或广播讲话。 这些任务和高准确度条件之间的一个重要区别是说话风格的变化更大，即使在来自单个说话者的数据中也是如此。 现有的声学模型没有考虑系统的 因素 在这种变化的背后 所以 必须 “更广泛”，导致单词之间更容易混淆，因此错误率更高。 这项工作提出了改进声学模型表示源的变化在三个时间尺度：音节，短区域内的话语，和扬声器。 在音节级别，自动聚类将捕获音节位置和语音缩减效果。 在区域级别，缓慢变化的隐藏说话模式将指示与减少的语音与清晰的语音相关联的发音的系统差异。在说话人层面，语音之间的相关性的层次模型将改善声学模型从少量数据的适应。 实验将涉及大词汇量的会话语音识别，使用多遍搜索策略来处理这里提出的高阶模型的成本。通过表示系统的可变性，所提出的工作应显着推进无约束语音识别和人机语音通信的目标任务更普遍。

Current speech recognition technology, while useful in constrained domains with cooperative speakers, still leads to unacceptably high error rates (30-50%) on unconstrained conversational or broadcast speech. An important difference between these tasks and high accuracy conditions is the larger variability in speaking style, even within data from a single speaker. Existing acoustic models do not account for the systematic factors behind this variability so must be ``broader,'' leading to more confusability among words and hence high error rates. This work proposes to improve acoustic models by representing sources of variability at three time scales: the syllable, short regions within an utterance, and the speaker. At the syllable level, automatic clustering will capture syllable position and phonetic reduction effects. At the region level, a slowly varying hidden speaking mode will indicate systematic differences in pronunciations associated with reduced vs. clearly articulated speech. At the speaker level, hierarchical models of the correlation among speech sounds will improve adaptation of acoustic models from small amounts of data. Experiments will involve large vocabulary recognition of conversational speech using a multi-pass search strategy to handle the cost of the higher-order models proposed here. By representing systematic variability, the proposed work should significantly advance both the target task of unconstrained speech recognition and human- computer speech communication more generally.