提出了用于音素識別的K子空間和時延自相關器神經網絡結構，用將時延設計加入線性自相關器，以擴展音素濾波神經網絡的方法，產生p維子空間，并采用迭代過程修改劃分，以便捕獲語音信號中的時間序列信息。這種帶不分類訓練過程的體系結構提供了一種高識別性能的方法，沒有大多數常規語音識別神經網絡所常有的網絡輸出值不表示候選者似然性的缺陷。通過英語音素和漢語音素的初步試驗，識別正確率為84.38%，比音素濾波神經網絡方法好。

A neural network architecture, K-subspaces and time-delay auto-associators, is proposed for phoneme recognition. It extends the phoneme filter neural networks approach by adding linear auto-associators to create p-dimension subspace, and an iteration is employed to improve the decision. It is good to capture the time-sequence information in speech signal. The architecture proposed could provide a high recognition performance without traditional neural network’s shortcoming. Some recognition simulations for both English and Chinese phonemes are conducted, and the recognition rate is 84.38% which is better than phoneme filter neural networks approach.