The role of prosody and voice quality in indirect storytelling speech: A cross-narrator perspective in four European languages

Montaño, Raúl; Álías, Francesc

doi:10.1016/j.specom.2017.01.007

Cited by 4 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further factors come into play in the context of story-telling where the speaker is either reading or narrating a well-rehearsed story. Montaño and Alías (2017) review approaches used to characterize story-telling speech.…”

Section: Content and Durationmentioning

confidence: 99%

Towards Understanding Text Factors in Oral Reading

Loukina

Liceralde

Klebanov

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

Using a case study, we show that variation in oral reading rate across passages for professional narrators is consistent across readers and much of it can be explained using features of the texts being read. While text complexity is a poor predictor of the reading rate, a substantial share of variability can be explained by timing and story-based factors with performance reaching r=0.75 for unseen passages and narrator.

show abstract

Section: Content and Durationmentioning

confidence: 99%

Towards Understanding Text Factors in Oral Reading

Loukina

Liceralde

Klebanov

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

show abstract

“…In Spanish, a lower pitch (F0 mean) and intensity have also been noticed in postcharacter sentences (Montaño et al 2013, Montaño andAlías 2016). A comparison of Spanish, German, French, and English has shown that post-character sentences show similar acoustic distributions across all languages: they tend to be spoken with a muffled voice that implies lower F0 and intensity values (Montaño and Alías 2017).…”

Section: Introductionmentioning

confidence: 93%

“…Professional audiobook voice artists can use different speaking styles depending on genre, personal preference, and the demands placed on them: they may choose to personify every character using their voice (especially for children's books) or only differentiate narrative parts from dialogue (see, e.g., Alain et al 2017, Mihkla et al 2018, Montaño et al 2013, and Zhao et al 2006. Montaño and Alías (2017) have shown that the content of a book determines the mode of reading aloud, regardless of language. Yet it is clear that there exist culturally different expectations for the paralinguistic aspects of an audiobook (see, e.g., Stolarski 2017aStolarski , 2017b.…”

Section: Introductionmentioning

confidence: 99%

Towards a vividness in synthesized speech for audiobooks

Pajupuu

Altrov

Pajupuu³

2019

ESUKA-JEFUL

View full text Add to dashboard Cite

The goal of this study was to determine which acoustic parameters are significant in differentiating the speaking styles of a narrator and that of male and female characters as voiced by a reader of audiobooks. The study was initiated by a need to improve the expressivity and differentiation of speaking styles in fiction books read out by synthesized voices. The corpus used as research material was created from an audio novel, as read by a professional male voice artist. To determine whether it is possible to identify these speaking styles from the voice of the reader, a web-based perception test consisting of 48 sentences was conducted. The results showed that the listeners identified all three styles. For acoustic analysis, the openSMILE toolkit was used and 88 eGeMAPS-defined parameters were extracted for every sentence in the corpus. All styles were differentiated by 38 statistically significant parameters. To improve vividness, synthesizers aimed at reading fiction books could be trained to perform all three styles. Kokkuvõte. Hille Pajupuu, Rene Altrov ja Jaan Pajupuu: Teel audioraamatute sünteeskõne elavdamisele. Uurimuse eesmärk oli teada saada, milli sed olulisemad akustilised parameetrid eristavad audioraamatu lugeja hääles jutustaja kõnet ning mees- ja naistegelaste otsekõnet. Uurimuse tingis vajadus parandada sünteeshäälega loetavate juturaamatute väljendus rikkust ja kõnestiilide eristatavust. Uurimismaterjalina kasutati professionaalse meeshäälega loetud audioromaani „Tõde ja õigus I“ põhjal loodud korpust. Et teada saada, kas audioraamatu lugeja hääle põhjal on kuulaja võimeline eristama eri kõnestiile (jutustaja kõnet, mees- ja naistegelaste otsekõnet), koostati 48 lausest koosnev tajutest. Testi tulemused näitasid, et kuulajad tundsid ära kõik kolm kõnestiili. Akustiliseks analüüsiks kasutati kogu korpuse materjali. openSMILE’i tööriistaga ekstraheeriti kõnest iga lause jaoks 88 eGeMAPSis defineeritud parameetrit. Statistiliselt oluliselt eristasid kõnestiile 38 parameetrit, millest 18 oli seotud hääle kvaliteedi ja tämbriga, 11 hääle valjusega, 8 hääle kõrgusega ja 1 tempoga. Kuna tajutest ja akustiliste parameetrite analüüs näitasid, et audioraamatus eristusid nii jutustaja kõne, naistegelaste otsekõne kui ka meestegelaste otsekõne, võib pidada otstarbekaks õpetada juturaamatuid ettelugevaid süntesaatoreid esitama kõiki kolme kõnestiili. Märksõnad: audioraamatud, kõnestiil, otsekõne, karakteri kõne, GeMAPS, kõneanalüüs, ekspressiivne kõnesüntees

show abstract

“…Audionarratology has been the topic of a recent conference and a related book, spanning arts at the interface of narrative and sound in a broad range of media, for example, song lyrics, radio drama, video games, and audio guides in art galleries (Mildorf & Kinzel, 2016; see also Rubery, 2011b). In addition, there is a large body of literature on expressive voice qualities and acoustic aspects of audiobooks (e.g., Drugman, Alku, Alwan, & Yegnanarayana, 2014; Montaño & Alías, 2017; Stolarski, 2015; Székely, Cabral, Abou-Zleikha, Cahill, & Carson-Berndsen, 2012; Székely, Csapó, Tóth, Mihajlik, & Carson-Berndsen, 2012), often focused on improving text-to-speech synthesis.…”

Section: Audiobook Absorptionmentioning

confidence: 99%

Narrative aesthetic absorption in audiobooks is predicted by blink rate and acoustic features.

Lange

Thiele

Kuijpers

2022

Psychology of Aesthetics, Creativity, and the Arts

View full text Add to dashboard Cite

Narrative aesthetic absorption describes a state in which we focus on the story world of a narrative while becoming less aware of our surroundings and ourselves. It is characterized by dimensions such as focused attention, vivid mental imagery, and emotional engagement. In our study, we investigate narrative aesthetic absorption in the context of listening to audiobooks. We asked participants to evaluate their absorption experience during listening to 56 excerpts of audiobooks, and we recorded their eyes to measure saccadic, pupil, and blinking activity. In addition, we analyzed the acoustic features of the audiobook excerpts. To understand the relationships between absorption in audiobooks, eye movement behavior, trait absorption, and acoustic signatures of audiobooks, we fitted linear mixed effect models predicting the subjective experience of absorption. Our results show that absorption was predicted by decreased blink rate, increased articulation rate of the narrator, and trait absorption. Blink rate and trait absorption also predicted valence and liking of the audiobooks. Articulation rate predicted liking and pitch predicted arousal. Being absorbed during audiobook listening shows high similarity with being absorbed during literary reading but less similarity with feeling absorbed while listening to music.

show abstract

The role of prosody and voice quality in indirect storytelling speech: A cross-narrator perspective in four European languages

Cited by 4 publications

References 48 publications

Towards Understanding Text Factors in Oral Reading

Towards Understanding Text Factors in Oral Reading

Towards a vividness in synthesized speech for audiobooks

Narrative aesthetic absorption in audiobooks is predicted by blink rate and acoustic features.

Contact Info

Product

Resources

About