Abstract
Prosodic breaks prediction from text is a fundamental task to obtain naturalness in text to speech applications. In this work we build a data-driven break predictor out of linguistic features like the Part of Speech (POS) tags and forward-backward word distance to punctuation marks, and to do so we use a basic Recurrent Neural Network (RNN) model to exploit the sequence dependency in decisions. In the experiments we evaluate the performance of a logistic regression model and the recurrent one. The results show that the logistic regression outperforms the baseline (CART) by a \(9.5\,\%\) in the F-score, and the addition of the recurrent layer in the model further improves the predictions of the baseline by an \(11\,\%\).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Taylor, P.: Text-to-Speech Synthesis. Cambridge University Press, Cambridge (2009)
Taylor, P., Black, A.W.: Assigning phrase breaks from part-of-speech sequences. Comput. Speech Lang. 12, 99–117 (1998)
Bonafonte, A., Agüero, P.D.: Phrase break prediction using a finite state transducer. In: Proceedings of Advanced Speech Technologies (2004)
Agüero, P.D., et al.: Síntesis de voz aplicada a la traducción voz a voz. Ph.D. dissertation, Tesis Doctoral. Universidad Politécnica de Cataluña (2012). http://hdl.handle.net/10803/97035
Hirschberg, J., Prieto, P.: Training intonational phrasing rules automatically for English and Spanish text-to-speech. Speech Commun. 18(3), 281–290 (1996)
Li, J., Hu, G., Wang, R.: Prosody phrase break prediction based on maximum entropy model. J. Chin. Inf. Process. 18, 56–63 (2004)
Watts, O., Gangireddy, S., Yamagishi, J., King, S., Renals, S., Stan, A., Giurgiu, M.: Neural net word representations for phrase-break prediction without a part of speech tagger. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2599–2603. IEEE (2014)
Mishra, T., Kim, Y.-J., Bangalore, S.: Intonational phrase break prediction for text-to-speech synthesis using dependency relations. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4919–4923. IEEE (2015)
Watts, O., Yamagishi, J., King, S.: Unsupervised continuous-valued word features for phrase-break prediction without a part-of-speech tagger. In: INTERSPEECH, pp. 2157–2160 (2011)
Sun, X., Applebaum, T.H.: Intonational phrase break prediction using decision tree and n-gram model. In: INTERSPEECH, pp. 537–540 (2001)
Deng, L., Yu, D.: Deep learning: methods and applications. Found. Trends Sig. Process. 7(3–4), 197–387 (2014)
Kim, Y., Jernite, Y., Sontag, D., Rush, A.M.: Character-aware neural language models, arXiv preprint arXiv:1508.06615 (2015)
Sutskever, I., Martens, J., Hinton, G.E.: Generating text with recurrent neural networks. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 1017–1024 (2011)
Mikolov, T., Deoras, A., Kombrink, S., Burget, L., Cernockỳ, J.: Empirical evaluation and combination of advanced language modeling techniques. In: INTERSPEECH, pp. 605–608 (2011)
Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation, arXiv preprint arXiv:1406.1078 (2014)
Zen, H., Sak, H.: Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4470–4474 (2015)
Fan, Y., Qian, Y., Xie, F.-L., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: INTERSPEECH, pp. 1964–1968 (2014)
Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertainty Fuzziness Knowl.-Based Syst. 6(02), 107–116 (1998)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Chollet, F.: Keras (2015). https://github.com/fchollet/keras
Bonafonte, A., Höge, H., Kiss, I., Moreno, A., Ziegenhain, U., van den Heuvel, H., Hain, H.-U., Wang, X.S., Garcia, M.-N.: TC-STAR: specifications of language resources and evaluation for speech synthesis. In: Proceedings of LREC Conference, pp. 311–314 (2006)
Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), pp. 1139–1147 (2013)
Forney Jr., J.D.: The viterbi algorithm. Proc. IEEE 61(3), 268–278 (1973)
Acknowledgments
This work was supported by the Spanish Ministerio de Economía y Competitividad and European Regional Development Fund, contract TEC2015-69266-P (MINECO/FEDER, UE).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Pascual, S., Bonafonte, A. (2016). Prosodic Break Prediction with RNNs. In: Abad, A., et al. Advances in Speech and Language Technologies for Iberian Languages. IberSPEECH 2016. Lecture Notes in Computer Science(), vol 10077. Springer, Cham. https://doi.org/10.1007/978-3-319-49169-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-49169-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49168-4
Online ISBN: 978-3-319-49169-1
eBook Packages: Computer ScienceComputer Science (R0)