Phoneme boundary estimation using bidirectional recurrent neural networks and its applications

✍ Scribed by Toshiaki Fukada; Mike Schuster; Yoshinori Sagisaka

• Publisher: John Wiley and Sons
• Year: 1999
• Tongue: English
• Weight: 180 KB
• Volume: 30
• Category: Article
• ISSN: 0882-1666
• DOI: 10.1002/(sici)1520-684x(199904)30:4<20::aid-scj3>3.0.co;2-e

✦ Synopsis

This paper describes a phoneme boundary estimation method based on bidirectional recurrent neural networks (BRNNs). Experimental results showed that the proposed method could estimate segment boundaries significantly better than an HMM or a multilayer perceptron-based method. Furthermore, we incorporated the BRNN-based segment boundary estimator into the HMM-based and segment model-based recognition systems. As a result, we confirmed that (1) BRNN outputs were effective for improving the recognition rate and reducing computational time in an HMM-based recognition system and (2) segment lattices obtained by the proposed methods dramatically reduce the computational complexity of segment modelbased recognition.