More Accurate and Efficient Analysis for Automatic Speech Recognition

更准确、更高效的自动语音识别分析

• 批准号: 914-2013
• 负责人: OShaughnessy, Douglas
• 金额: $ 2.11万
• 依托单位: Institut national de la recherche scientifique
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2013
• 资助国家: 加拿大
• 起止时间: 2013-01-01 至 2014-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=520319
• 关键词: More; Accurate; Efficient; Analysis; Automatic

Efficient communicating with machines via voice will facilitate interactions that so far have been hindered by awkward interfaces such as keyboards and telephone keypads. People nowadays have increasing need to interact with computers, yet this is still done mostly by typing. Even attempts to seek information by telephone often require many cycles of listening to long messages and then pushing a button, because our capability to do reliable automatic speech recognition (ASR) is quite limited. For some time now, refinements to basic ASR methods established years ago have improved performance, without radical changes to the basic approaches. The recent vast increase in computational power and memory size has led researchers to attack increasingly difficult tasks such as continuously-spoken, very-large-vocabulary, speaker-independent, noisy speech over the telephone. For some limited tasks, e.g., recognizing credit card numbers, or words drawn from medium-sized vocabularies and spoken with frequent pauses, recognition accuracy rises above 99%, and hence practical commercial products are available. However, progress has been slow for the more difficult tasks of recognizing conversational speech or noisy speech. Furthermore, recognition error rates remain high when generalized speaker-independent models are used to decode speakers not used in the training phase.

通过语音与机器进行高效通信将促进迄今为止因键盘和电话小键盘等笨拙界面所阻碍的交互。 如今，人们越来越需要与计算机交互，但这仍然主要通过打字来完成。 即使尝试通过电话查找信息，通常也需要多次收听长消息，然后按下按钮，因为我们进行可靠的自动语音识别 (ASR) 的能力非常有限。 一段时间以来，对多年前建立的基本 ASR 方法的改进提高了性能，而无需对基本方法进行根本性改变。 最近计算能力和内存大小的大幅增长导致研究人员致力于解决日益困难的任务，例如通过电话连续说话、词汇量非常大、与说话者无关、有噪音的语音。 对于一些有限的任务，例如识别信用卡号码，或识别中等词汇量且经常停顿的单词，识别准确率可达99％以上，因此可以提供实用的商业产品。 然而，对于识别会话语音或噪声语音等更困难的任务来说，进展缓慢。 此外，当使用广义的说话人无关模型来解码训练阶段未使用的说话人时，识别错误率仍然很高。