Improving basic methods of automatic speech recognition

自动语音识别(ASR)最大的问题是健壮性--确保ASR模型足够通用。一个健壮的ASR系统应该能够在任何合理的环境中解码任何说话人的语音。在实践中，除训练ASR模型的人外，说话人会导致ASR准确性显著下降。此外，环境噪声(例如，天气、其他说话者、汽车)和通信失真(例如，使用移动电话)通常会严重降低ASR性能。即使是简单的麦克风替换也会降低准确度。相比之下，人类听众往往能迅速适应所有这些困难，这有力地表明，当前的ASR方案存在重大缺陷。虽然在设计ASR系统时没有必要直接模仿人类的感知，但我们关于人类语音产生和感知的大部分知识还没有整合到实际的ASR中。通过更好地将结构信息与当前的随机方法相结合，ASR可以得到极大的改善。

The biggest problem in automatic speech recognition (ASR) is robustness - making sure that ASR models are general enough. A robust ASR system should be able to decode speech from any speaker, in any reasonable environment. In practice, speakers other than those that trained the ASR models lead to a significant decrease in ASR accuracy. As well, environmental noise (e.g., weather, other talkers, cars) and communication distortions (e.g., with mobile phones) degrade ASR performance, often severely. Even simple microphone substitution reduces accuracy. Human listeners, in contrast, often can adapt rapidly to all these difficulties, which strongly suggests that major flaws exist in current ASR schemes. While it is not necessary to directly mimic human perception when designing ASR systems, much of what we know about human speech production and perception has yet to be integrated into practical ASR. ASR can be greatly improved by better integration of structural information with the current stochastic methodology.