{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T23:16:13Z","timestamp":1784675773307,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T00:00:00Z","timestamp":1595376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,22]]},"DOI":"10.1145\/3405755.3406120","type":"proceedings-article","created":{"date-parts":[[2020,7,13]],"date-time":"2020-07-13T22:52:27Z","timestamp":1594680747000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Persuasive Synthetic Speech"],"prefix":"10.1145","author":[{"given":"Mateusz","family":"Dubiel","sequence":"first","affiliation":[{"name":"University of Strathclyde"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Halvey","sequence":"additional","affiliation":[{"name":"University of Strathclyde"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pilar Oplustil","family":"Gallegos","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,7,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Martin Klesen, and Stefan Baldes.","author":"Andr\u00e9 Elisabeth","year":"2000"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1736359"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0185651"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1958.10501456"},{"key":"e_1_3_2_1_5_1","volume-title":"Springer Handbook of Speech Processing","author":"Campbell Nick"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Tim Capes Paul Coles Alistair Conkie Ladan Golipour Abie Hadjitarkhani Qiong Hu Nancy Huddleston Melvyn Hunt Jiangchuan Li Matthias Neeracher etal 2017. Siri On-Device Deep Learning-Guided Unit Selection Text-to-Speech System.. In INTERSPEECH. 4011--4015.  Tim Capes Paul Coles Alistair Conkie Ladan Golipour Abie Hadjitarkhani Qiong Hu Nancy Huddleston Melvyn Hunt Jiangchuan Li Matthias Neeracher et al. 2017. Siri On-Device Deep Learning-Guided Unit Selection Text-to-Speech System.. In INTERSPEECH. 4011--4015.","DOI":"10.21437\/Interspeech.2017-1798"},{"key":"e_1_3_2_1_7_1","volume-title":"Claire G\u00e9linas-Chebat, and Robert Boivin.","author":"Chebat Jean-Charles","year":"2007"},{"key":"e_1_3_2_1_8_1","unstructured":"Robert AJ Clark Korin Richmond and Simon King. 2004. Festival 2-build your own general purpose unit selection speech synthesiser. (2004). https:\/\/tinyurl.com\/TTSfestival  Robert AJ Clark Korin Richmond and Simon King. 2004. Festival 2-build your own general purpose unit selection speech synthesiser. (2004). https:\/\/tinyurl.com\/TTSfestival"},{"key":"e_1_3_2_1_9_1","volume-title":"Stat. Power Anal. Behav. Sci 567","author":"Cohen J","year":"1988"},{"key":"e_1_3_2_1_10_1","volume-title":"Wizard of Oz studies - why and how. Knowledge-based systems 6, 4","author":"Dahlb\u00e4ck Nils","year":"1993"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3176349.3176360"},{"key":"e_1_3_2_1_12_1","volume-title":"The Second International Workshop on Conversational Approaches to Information Retrieval. https:\/\/tinyurl.com\/sigir-cair","author":"Dubiel Mateusz","year":"2018"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/beheco\/arr134"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1068\/p5514"},{"key":"e_1_3_2_1_15_1","volume-title":"Manipulations of fundamental and formant frequencies influence the attractiveness of human male voices. Animal behaviour 69, 3","author":"Feinberg David R","year":"2005"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the AISB 2004 Convention. The Society for the Study of Artificial Intelligence and the Simulation of Behaviour, 1--11","author":"Fischer Kerstin","year":"2004"},{"key":"e_1_3_2_1_17_1","volume-title":"9th Conference Speech and Computer.","author":"Gaudissart Vincent","year":"2004"},{"key":"e_1_3_2_1_18_1","unstructured":"Andrew Gibiansky Sercan Arik Gregory Diamos John Miller Kainan Peng Wei Ping Jonathan Raiman and Yanqi Zhou. 2017. Deep voice 2: Multi-speaker neural text-to-speech. In Advances in neural information processing systems. 2962--2970.  Andrew Gibiansky Sercan Arik Gregory Diamos John Miller Kainan Peng Wei Ping Jonathan Raiman and Yanqi Zhou. 2017. Deep voice 2: Multi-speaker neural text-to-speech. In Advances in neural information processing systems. 2962--2970."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2699509.2699577"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1080\/00223891.2015.1132426"},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. Blizzard Challenge Workshop","author":"Karaiskos Vasilis","year":"2008"},{"key":"e_1_3_2_1_22_1","unstructured":"Kayak. 2020. (Amazon Echo application software). https:\/\/www.amazon.co.uk\/KAYAK\/dp\/B01EILLOXI  Kayak. 2020. (Amazon Echo application software). https:\/\/www.amazon.co.uk\/KAYAK\/dp\/B01EILLOXI"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/dir.4000040304"},{"key":"e_1_3_2_1_24_1","volume-title":"Google's new voice is as good as your own. New scientist 3159","author":"Kobie Nicole","year":"2018"},{"key":"e_1_3_2_1_25_1","volume-title":"Bala Krishna Kolluru, and Mark J.F. Gales","author":"Latorre Javier","year":"2014"},{"key":"e_1_3_2_1_26_1","unstructured":"Kevin Lenzo. [n. d.]. The Carnegie Mellon University pronouncing dictionary.  Kevin Lenzo. [n. d.]. The Carnegie Mellon University pronouncing dictionary."},{"key":"e_1_3_2_1_27_1","volume-title":"On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics","author":"Mann Henry B","year":"1947"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0090779"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Joseph Mendelson and Matthew P Aylett. 2017. Beyond the Listening Test: An Interactive Approach to TTS Evaluation.. In INTERSPEECH. 249--253.  Joseph Mendelson and Matthew P Aylett. 2017. Beyond the Listening Test: An Interactive Approach to TTS Evaluation.. In INTERSPEECH. 249--253.","DOI":"10.21437\/Interspeech.2017-1438"},{"key":"e_1_3_2_1_30_1","volume-title":"A Recorded Debating Dataset. arXiv preprint arXiv:1709.06438","author":"Mirkin Shachar","year":"2017"},{"key":"e_1_3_2_1_31_1","unstructured":"Michel Nienhuis. 2009. Prosodic Correlates of Rhetorical Appeal. (2009). https:\/\/tinyurl.com\/RethoricalAppeal  Michel Nienhuis. 2009. Prosodic Correlates of Rhetorical Appeal. (2009). https:\/\/tinyurl.com\/RethoricalAppeal"},{"key":"e_1_3_2_1_32_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300344"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1006\/jesp.1995.1008"},{"key":"e_1_3_2_1_35_1","volume-title":"Vocal expression of emotion. Handbook of affective sciences","author":"Scherer Klaus R","year":"2003"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0210555"},{"key":"e_1_3_2_1_37_1","volume-title":"Affective information processing","author":"Schr\u00f6der Marc"},{"key":"e_1_3_2_1_38_1","unstructured":"Skyscanner Flight Search. 2018. (Amazon Echo application software). https:\/\/www.skyscanner.com\/tips-and-inspiration\/features\/amazon-echo-and-skyscanner-a-match-made-in-travel-heaven  Skyscanner Flight Search. 2018. (Amazon Echo application software). https:\/\/www.skyscanner.com\/tips-and-inspiration\/features\/amazon-echo-and-skyscanner-a-match-made-in-travel-heaven"},{"key":"e_1_3_2_1_39_1","volume-title":"Sex differences in persuadability of human and computer-synthesized speech: meta-analysis of seven studies. Psychological reports 94, 3_suppl","author":"Stern Steven E","year":"2004"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1518\/001872099779656680"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2005.07.002"},{"key":"e_1_3_2_1_42_1","unstructured":"Eva Strangert and Joakim Gustafson. 2008. Improving speaker skill in a resynthesis experiment. (2008). http:\/\/www.diva-portal.org\/smash\/get\/diva2:149676\/FULLTEXT01.pdf  Eva Strangert and Joakim Gustafson. 2008. Improving speaker skill in a resynthesis experiment. (2008). http:\/\/www.diva-portal.org\/smash\/get\/diva2:149676\/FULLTEXT01.pdf"},{"key":"e_1_3_2_1_43_1","volume-title":"Ninth Annual Conference of the International Speech Communication Association.","author":"Strangert Eva","year":"2008"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1970.10481069"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","volume-title":"Text-to-speech synthesis","author":"Taylor Paul","DOI":"10.1017\/CBO9780511816338"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173782"},{"key":"e_1_3_2_1_48_1","volume-title":"Are we using enough listeners? No! An empirically-supported critique of interspeech 2014 TTS evaluations","author":"Wester Mirjam"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1297231.1297260"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.33.1"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/1454077.1454079"},{"key":"e_1_3_2_1_52_1","volume-title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech. arXiv preprint arXiv:1904.02882","author":"Zen Heiga","year":"2019"},{"key":"e_1_3_2_1_53_1","volume-title":"Statistical parametric speech synthesis. speech communication 51, 11","author":"Zen Heiga","year":"2009"}],"event":{"name":"CUI '20: 2nd Conference on Conversational User Interfaces","location":"Bilbao Spain","acronym":"CUI '20"},"container-title":["Proceedings of the 2nd Conference on Conversational User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3405755.3406120","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3405755.3406120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:09Z","timestamp":1750195929000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3405755.3406120"}},"subtitle":["Voice Perception and User Behaviour"],"short-title":[],"issued":{"date-parts":[[2020,7,22]]},"references-count":53,"alternative-id":["10.1145\/3405755.3406120","10.1145\/3405755"],"URL":"https:\/\/doi.org\/10.1145\/3405755.3406120","relation":{},"subject":[],"published":{"date-parts":[[2020,7,22]]},"assertion":[{"value":"2020-07-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}