The prevailing approach to speech recognition is Hidden Markov Modelling, which yields good performance. However, it ignores phonetics, which has the potential for going beyond the acoustic variance to provide a more abstract underlying representation.ududThe novel approach pursued in this thesis is motivated by phonetic and phonological considerations. It is based on the notion of pseudo-articulatory representations, which are abstract and idealized accounts of articulatory activity. The original work presented here demonstrates the recovery of syllable structure information from pseudo-articulatory representations directly without resorting to statistical models of phone sequences. The work is also original in its use of syllable structures to recover phonemes. This thesis presents the three-stage syllable based, pseudo-articulatory approach in detail. Though it still has problems, this research leads to a more plausible style of automatic speech recognition and will contribute to modelling and understanding speech behaviour. Additionally, it also permits a 'multithreaded' approach combining information from different processes.ud
展开▼
机译:语音识别的主要方法是Hidden Markov Modelling,它具有良好的性能。但是,它忽略了语音学,语音学有可能超越声学方差来提供更抽象的基础表示。 ud ud本论文中追求的新颖方法是受语音和语音学考虑的推动。它基于伪发音表示的概念,它是对发音活动的抽象和理想化描述。此处介绍的原始工作演示了直接从伪发音表示中恢复音节结构信息的方法,而无需借助电话序列的统计模型。该作品在使用音节结构恢复音素方面也是原创的。本文详细介绍了基于三段音节的伪发音方法。尽管它仍然存在问题,但这项研究导致了一种更加合理的自动语音识别样式,并将有助于建模和理解语音行为。此外,它还允许“多线程”方法结合来自不同进程的信息。
展开▼