Using the LARA Little Prince to compare human and TTS audio quality

Conférence Chapitre d'actes Using the LARA Little Prince to compare human and TTS audio quality eng 2022 author Akhlaghi Elham author Auðunardóttir Ingibjörg author Bączkowska Anna author Bédi Branislav author Beedar Hakeem author Berthelsen Harald author Chua Cathy author Cucchiarini Catia author Habibi Hanieh 911216 author Horváthová Ivana author Ikeda Junta author Maizonniaux Christèle author Chiaráin Neasa Ní author Raheb Chadi author Rayner Emmanuel 135728 author Sloan John 984002 author Tsourakis Nikolaos 653574 author Yao Chunlin 2967-2975 9791095546726 http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.318.pdf A popular idea in Computer Assisted Language Learning (CALL) is to use multimodal annotated texts, with annotations typically including embedded audio and translations, to support L2 learning through reading. An important question is how to create good quality audio, which can be done either through human recording or by a Text-To-Speech (TTS) engine. We may reasonably expect TTS to be quicker and easier, but human to be of higher quality. Here, we report a study using the open source LARA platform and ten languages. Samples of audio totalling about five minutes, representing the same four passages taken from LARA versions of Saint-Exupèry’s “Le petit prince”, were provided for each language in both human and TTS form; the passages were chosen to instantiate the 2x2 cross product of the conditions dialogue, not-dialogue and humour, not-humour. 251 subjects used a web form to compare human and TTS versions of each item and rate the voices as a whole. For the three languages where TTS did best, English, French and Irish, the evidence from this study and the previous one it extended suggest that TTS audio is now pedagogically adequate and roughly comparable with a non-professional human voice in terms of exemplifying correct pronunciation and prosody. It was however still judged substantially less natural and less pleasant to listen to. No clear evidence was found to support the hypothesis that dialogue and humour pose special problems for TTS. All data and software will be made freely available. TTS Evaluation Multimodality Reading Emotion Dewey 410.2 Marseille, France European Language Resources Association (ELRA) 112 Département de traitement informatique multilingue 92 false 696 TIM/ISSCO Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022) Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis 20-25 juin 2022 Marseille 48669fc0-ed99-4643-bb33-ab3cba5b7b90 Proceedings chapter (Published version) Public 2022.lrec-1.318.pdf 1670512 application/pdf CC BY-NC-4.0 openAccess Faculté de traduction et d'interprétation / Département de traitement informatique multilingue

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Using the LARA Little Prince to compare human and TTS audio quality	Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022)			2022	177	205

Archive ouverte UNIGE

Sloan, John