Structured Adaptive Regularization of Weight Vectors for a Robust Grapheme-to-Phoneme Conversion Model

• KUBO Keigo

  Graduate School of Information Science, Nara Institute of Science and Technology

• SAKTI Sakriani

  Graduate School of Information Science, Nara Institute of Science and Technology

• NEUBIG Graham

  Graduate School of Information Science, Nara Institute of Science and Technology

• TODA Tomoki

  Graduate School of Information Science, Nara Institute of Science and Technology

• NAKAMURA Satoshi

  Graduate School of Information Science, Nara Institute of Science and Technology

Abstract

Grapheme-to-phoneme (g2p) conversion, used to estimate the pronunciations of out-of-vocabulary (OOV) words, is a highly important part of recognition systems, as well as text-to-speech systems. The current state-of-the-art approach in g2p conversion is structured learning based on the Margin Infused Relaxed Algorithm (MIRA), which is an online discriminative training method for multiclass classification. However, it is known that the aggressive weight update method of MIRA is prone to overfitting, even if the current example is an outlier or noisy. Adaptive Regularization of Weight Vectors (AROW) has been proposed to resolve this problem for binary classification. In addition, AROW's update rule is simpler and more efficient than that of MIRA, allowing for more efficient training. Although AROW has these advantages, it has not been applied to g2p conversion yet. In this paper, we first apply AROW on g2p conversion task which is structured learning problem. In an evaluation that employed a dataset generated from the collective knowledge on the Web, our proposed approach achieves a 6.8% error reduction rate compared to MIRA in terms of phoneme error rate. Also the learning time of our proposed approach was shorter than that of MIRA in almost datasets.

Journal

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E97.D (6), 1468-1476, 2014

  The Institute of Electronics, Information and Communication Engineers

Keywords

• g2p conversion
• out-of-vocabulary word
• online discriminative training
• structured learning
• AROW

Details

• CRID: 1390001204378019584
• NII Article ID: 130004841779
• DOI: 10.1587/transinf.e97.d.1468
• ISSN: 17451361
• ISSN: 09168532
• Web Site: https://www.jstage.jst.go.jp/article/transinf/E97.D/6/E97.D_1468/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed