Abstract
Emotional Voice Conversion (EVC) is a method to convert the emotional state of an utterance to another without changing the linguistic information and speaker’s identity. Its application is enormous in human-machine interaction, development of emotional Text-To-Speech (TTS), etc. This study focuses on analyzing the characteristics of Mandarin and English language for EVC between these languages. Prosodic features, such as energy, fundamental or pitch frequency (\(F_{0}\)), duration, pauses/silences, and loudness are compared using several techniques, such as narrowband spectrograms, Root Mean Square Energy (RMSE), and Zero-Crossing Rate (ZCR). Teager Energy Operator (TEO) based features are studied to analyze the energy profile of emotions. The Emotional Speech Dataset (ESD) is used in this work. Experiments were performed on 5 emotions, namely, anger, happiness, neutral, sad, and surprise. Results showed that tonal language (i.e., Mandarin) has steep and multiple fluctuations in \(F_{0}\) contour as it is pitch-dependent, as compared to the stress-time language (English), which had less \(F_{0}\) fluctuations, and is stable for the most duration of the sentence. Loudness and silences are also different in the two languages. These findings may serve as important cues for EVC task.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
An introduction to Tonal languages. https://ceas.sas.upenn.edu/sites/default/files/. Accessed 9 Sep 2022
Alex, S.B., Mary, L., Babu, B.P.: Attention and feature selection for automatic speech emotion recognition using utterance and syllable-level prosodic features. Circuits Syst. Signal Process. 39(11), 5681–5709 (2020)
Bachu, R., Kopparthi, S., Adapa, B., Barkana, B.: Separation of voiced and unvoiced using zero crossing rate and energy of the speech signal. In: American Society for Engineering Education (ASEE) Zone Conference Proceedings, pp. 1–7. American Society for Engineering Education (2008)
Brata, I., Darmawan, I.: Comparative study of pitch detection algorithm to detect traditional balinese music tones with various raw materials. J. Phys.: Conf. Ser. 1722, 012071 (2021)
Kawanami, H., Iwami, Y., Toda, T., Saruwatari, H., Shikano, K.: GMM-based voice conversion applied to emotional speech synthesis. In: 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 - INTERSPEECH 2003, Geneva, Switzerland (2003)
Licklider, J.C.R., Pollack, I.: Effects of differentiation, integration, and infinite peak clipping upon the intelligibility of speech. J. Acoust. Soc. Am. 20(1), 42–51 (1948)
Mohammadi, S.H., Kain, A.: An overview of voice conversion systems. Speech Commun. 88, 65–82 (2017)
Patil, H.A., Parhi, K.K.: Development of TEO phase for speaker recognition. In: 2010 International Conference on Signal Processing and Communications (SPCOM), pp. 1–5. IISc Bangalore, India (2010)
Pittermann, J., Pittermann, A., Minker, W.: Handling Emotions in Human-computer Dialogues. Springer (2010). https://doi.org/10.1007/978-90-481-3129-7
Swain, M., Routray, A., Kabisatpathy, P.: Databases, features and classifiers for speech emotion recognition: a review. Int. J. Speech Technol. 21(1), 93–120 (2018). https://doi.org/10.1007/s10772-018-9491-z
Wang, L., Wu, E.X., Chen, F.: Contribution of RMS-level-based speech segments to target speech decoding under noisy conditions. In: INTERSPEECH, pp. 121–124, Shangai China (2020)
Zhou, K., Sisman, B., Li, H.: Transforming spectrum and prosody for emotional voice conversion with non-parallel training data. arXiv preprint arXiv:2002.00198 (2020)
Zhou, K., Sisman, B., Liu, R., Li, H.: Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, pp. 920–924 (2021)
Zhou, K., Sisman, B., Liu, R., Li, H.: Emotional voice conversion: theory, databases and ESD. Speech Commun. 137, 1–18 (2022)
Acknowledgements
The authors are thankful to the Ministry of Electronics and Information Technology (MeitY), New Delhi, Government of India, for sponsoring the project, ”National Language Translation Mission (NLTM): BHASHINI with the objective of Building Assistive Speech Technologies for the Challenged (Grant ID: 11(1)2022-HCC (TDIL)).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Uthiraa, S., Patil, H.A. (2023). Analysis of Mandarin vs English Language for Emotional Voice Conversion. In: Karpov, A., Samudravijaya, K., Deepak, K.T., Hegde, R.M., Agrawal, S.S., Prasanna, S.R.M. (eds) Speech and Computer. SPECOM 2023. Lecture Notes in Computer Science(), vol 14339. Springer, Cham. https://doi.org/10.1007/978-3-031-48312-7_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-48312-7_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48311-0
Online ISBN: 978-3-031-48312-7
eBook Packages: Computer ScienceComputer Science (R0)