Abstract
Using TTS systems helps to reduce the cost of audio-book generation. This paper investigates the idea of mixing synthetic and recorded natural speech signals to control the trade-off between the overall quality of audio book and its production cost. Firstly, fully synthetic signals and mixed synthetic and natural signals are compared perceptually using different levels of synthetic quality. The listeners’ perception shows that mixed signals are preferred. Next, the order and configuration of mixed signals are studied. The perceptual test does not show any significant difference between the different configurations. Finally, the synthetic quality and the bias of a starting and ending part of mixed signals in perceptual test are investigated.
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
References
Boeffard, O., Charonnat, L., Le Maguer, S., Lolive, D., Vidal, G.: Towards fully automatic annotation of audio books for TTS. In: Eighth International Conference on Language Resources and Evaluation (LREC), Istanbul, Turkey, pp. 975–980 (2012)
Chiaráin, N.N., Chasaide, A.N.: Effects of educational context on learners’ ratings of a synthetic voice. In: Seventh ISCA Workshop on Speech and Language Technology in Education, Stockholm, Sweden, pp. 47–52 (2017)
Clark, R., Silen, H., Kenter, T., Leith, R.: Evaluating long-form text-to-speech: Comparing the ratings of sentences and paragraphs. In: Tenth ISCA Workshop on Speech Synthesis (SSW10), Vienna, Austria (2019)
Gong, L., Lai, J.: To mix or not to mix synthetic speech and human speech? Contrasting impact on judge-rated task performance versus self-rated performance and attitudinal responses. Int. J. Speech Technol. 6(2), 123–131 (2003)
Hinterleitner, F., Neitzel, G., Möller, S., Norrenbrock, C.: An evaluation protocol for the subjective assessment of text-to-speech in audiobook reading tasks. In: Blizzard Challenge Workshop. International Speech Communication Association (ISCA), Florence, Italy (2011)
Latorre, J., Yanagisawa, K., Wan, V., Kolluru, B., Gales, M.J.: Speech intonation for tts: Study on evaluation methodology. In: Fifteenth Annual Conference of the International Speech Communication Association (INTERSPEECH), Singapore, pp. 2957–2961 (2014)
Lewis, J.R., Commarford, P.M., Kotan, C.: Web-based comparison of two styles of auditory presentation: All TTS versus rapidly mixed TTS and recordings. In: Human Factors and Ergonomics Society Annual Meeting, San Francisco, vol. 50, pp. 723–727 (2006)
P.800.2, I.T.R.: Mean opinion score interpretation and reporting. International Telecommunication Union (2013)
Shamsi, M.: TTS voice corpus reduction for audio-book generation. Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues [Young Researchers Meeting in Computer Science for Automatic Language Processing], RÉCITAL, Nancy, France, 22 edn., vol. 3, pp. 193–204 (2020)
Shamsi, M., Chevelu, J., Lolive, D., Barbot, N.: Corpus design for expressive speech: Impact of the utterance length. In: Tenth International Conference of Speech Prosody, pp. 955–959 (2020)
Shamsi, M., Lolive, D., Barbot, N., Chevelu, J.: Corpus design using convolutional auto-encoder embeddings for audio-book synthesis. In: Twentieth Annual Conference of the International Speech Communication Association (INTERSPEECH), Graz, Austria, pp. 1531–1535 (2019)
Shamsi, M., Lolive, D., Barbot, N., Chevelu, J.: Investigating the relation between voice corpus design and hybrid synthesis under reduction constraint. In: MartĂn-Vide, C., Purver, M., Pollak, S. (eds.) SLSP 2019. LNCS (LNAI), vol. 11816, pp. 162–173. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-31372-2_14
Wester, M., Watts, O., Henter, G.E.: Evaluating comprehension of natural and synthetic conversational speech. In: Eighth International Conference of Speech Prosody, Boston, USA, pp. 736–740 (2016)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Shamsi, M., Barbot, N., Lolive, D., Chevelu, J. (2020). Mixing Synthetic and Recorded Signals for Audio-Book Generation. In: Karpov, A., Potapova, R. (eds) Speech and Computer. SPECOM 2020. Lecture Notes in Computer Science(), vol 12335. Springer, Cham. https://doi.org/10.1007/978-3-030-60276-5_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-60276-5_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60275-8
Online ISBN: 978-3-030-60276-5
eBook Packages: Computer ScienceComputer Science (R0)