Making large-scale support vector machine learning practical
Advances in kernel methods
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Optimizing search engines using clickthrough data
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Ultraconservative online algorithms for multiclass problems
The Journal of Machine Learning Research
Stress assignment in letter to sound rules for speech synthesis
ACL '85 Proceedings of the 23rd annual meeting on Association for Computational Linguistics
Integer linear programming inference for conditional random fields
ICML '05 Proceedings of the 22nd international conference on Machine learning
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Discriminative Reranking for Natural Language Parsing
Computational Linguistics
Can syllabification improve pronunciation by analogy of English?
Natural Language Engineering
Reducing the annotation effort for letter-to-phoneme conversion
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
EACL 2012 Proceedings of the EACL 2012 Joint Workshop of LINGVIS & UNCLH
Hi-index | 0.01 |
Correct stress placement is important in text-to-speech systems, in terms of both the overall accuracy and the naturalness of pronunciation. In this paper, we formulate stress assignment as a sequence prediction problem. We represent words as sequences of substrings, and use the substrings as features in a Support Vector Machine (SVM) ranker, which is trained to rank possible stress patterns. The ranking approach facilitates inclusion of arbitrary features over both the input sequence and output stress pattern. Our system advances the current state-of-the-art, predicting primary stress in English, German, and Dutch with up to 98% word accuracy on phonemes, and 96% on letters. The system is also highly accurate in predicting secondary stress. Finally, when applied in tandem with an L2P system, it substantially reduces the word error rate when predicting both phonemes and stress.