Automatic Feature Template Generation for Prosodic Phrasing

Prosodic phrase prediction is important for both the naturalness and intelligibility of Text-to-Speech (TTS) systems. To automatically generate feature templates of prosodic phrasing models, this paper proposes a hybrid approach which converts the rules generated by classification and regression tree (CART) into templates of transformation-based learning (TBL), and designs a hierarchical clustering based feature combination algorithm for maximum entropy (ME) model. While minimizing human supervision, TBL templates automatically generated by CART can provide good alternatives or beneficial supplement to manually summarized templates, and ME templates automatically generated by the proposed feature combination algorithm not only make an improvement of 3.1% on F-measure over manual templates, but also reduce the size of ME model by up to 79.0%.

[1]  Mitchell P. Marcus,et al.  Maximum entropy models for natural language ambiguity resolution , 1998 .

[2]  Mari Ostendorf,et al.  Automatic labeling of prosodic patterns , 1994, IEEE Trans. Speech Audio Process..

[3]  Eric Brill,et al.  Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging , 1995, CL.

[4]  Hwee Tou Ng,et al.  A Maximum Entropy Approach to Chinese Word Segmentation , 2005, SIGHAN@IJCNLP 2005.

[5]  Martha Palmer,et al.  Simple Features for Chinese Word Sense Disambiguation , 2002, COLING.

[6]  Wang Ren-hua.  Prosody Phrase Break Prediction Based on Maximum Entropy Model , 2004 .

[7]  Yiming Yang,et al.  A Comparative Study on Feature Selection in Text Categorization , 1997, ICML.

[8]  Dunja Mladenic,et al.  Feature Selection for Unbalanced Class Distribution and Naive Bayes , 1999, ICML.

[9]  Adwait Ratnaparkhi,et al.  A Maximum Entropy Model for Part-Of-Speech Tagging , 1996, EMNLP.

[10]  Mitchell P. Marcus,et al.  Text Chunking using Transformation-Based Learning , 1995, VLC@ACL.

[11]  Eric Brill,et al.  Learning to Parse with Transformations , 1996 .

[12]  Zhao Sheng.  Rule-learning Based Prosodic Structure Prediction , 2002 .

[13]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[14]  David Yarowsky,et al.  Hierarchical Decision Lists for Word Sense Disambiguation , 2000, Comput. Humanit..

[15]  Paul Taylor,et al.  Assigning phrase breaks from part-of-speech sequences , 1997, Comput. Speech Lang..