The spectator as co-mixer

Artificial Intelligence, intelligibility, and the customization of cinematic listening

Authors

DOI:

https://doi.org/10.33871/19805071.2026.34.1.11624

Keywords:

Artificial Intelligence, Sound Design, Speech Intelligibility, Listening Customization, Spectral Analysis

Abstract

This article analyzes the impact of artificial intelligence on the reconfiguration of the cinematic sound chain, from production to reception. Drawing from cinema’s verbocentric tradition (Chion, 2008), it discusses the current crisis of vocal intelligibility, intensified by aesthetic choices and audio compression on streaming platforms. It argues that the industry responds to this scenario through machine learning algorithms that deepen the existing trend of customized listening, transferring part of the mixing control to the viewer. As a case study, Amazon Prime Video’s Dialogue Boost tool is examined. Based on spectrographic analyses of the series The Marvelous Mrs. Maisel and Fallout, the study demonstrates that the feature operates through the selective attenuation of non-vocal sounds. The results indicate the reinforcement of a "telephonic mode" of vocal representation, prioritizing semantic clarity over acoustic fidelity, and straining the ethics of audiovisual work preservation.

Downloads

Download data is not yet available.

Author Biographies

Rodrigo Octavio D'Azevedo Carreiro, Universidade Federal de Pernambuco

Professor titular da Universidade Federal de Pernambuco (UFPE), onde atua no Programa de Pós-Graduação em Comunicação e no Bacharelado em Cinema e Audiovisual. Cursou Mestrado e Doutorado em Comunicação na própria UFPE, com pós-doutorado na Universidade Federal Fluminense (UFF). É bolsista de Produtividade em Pesquisa do CNPq desde 2020. Pesquisa sound design, escuta, processos criativos cinematográficos e gêneros fílmicos populares, especialmente horror e thriller. Autor dos livros A Linguagem do Cinema (Editora da UFPE, 2021), O som no cinema de horror (Editora da UFPR, 2023) e Cinema de Horror: Uma Introdução (2025, com Laura Cánepa), entre outros. Lidera o LAPIS (Laboratório de Pesquisa de Imagem e Som), grupo certificado pelo CNPq. E-mail: rcarreiro@gmail.com. Orcid: https://orcid.org/0000-0003-3087-9557. Currículo Lattes: http://lattes.cnpq.br/0263456536361820.

Débora Regina Opolski, Universidade Estadual do Paraná

Professora do Instituto Federal do Paraná (IFPR) e do Mestrado em Cinema e Artes do Vídeo da UNESPAR. Doutora em comunicação e Linguagens (Cinema e Audiovisual) pela Universidade Tuiuti do Paraná (UTP). Bolsista Capes/Fulbright para estágio de doutorado na University of Southern California (USC), School of cinematic Arts (2015- 2016). Mestre em Música (Teoria e Criação) pela Universidade Federal do Paraná (UFPR). Graduação em Música (Produção Sonora) também pela UFPR. Autora dos livros Introdução ao Desenho de Som (Editora da UFPB, 2013) e Edição de Diálogos no Cinema (Editora da UFPR, 2021). Integrante dos grupos de pesquisa Cinecriare Cinema: Criação e Reflexão, da UNESPAR e LAPIS, da UFPE. E-mail: deboraopolski@gmail.com. ORCID: https://orcid.org/0000-0002-7784-3626. Currículo Lattes: http://lattes.cnpq.br/5694754137339356.

References

AMAZON Original Spec and Delivery. Gearspace, 31 mar. 2016. Disponível em: https://gearspace.com/board/post-production-forum/1077559-amazon-original-spec-delivery.html. Acesso em: 25 nov. 2025.

AMAZON STAFF. Prime Video launches a new accessibility feature that makes it easier to hear dialogue in your favorite movies and series. About Amazon, 18 abr. 2023. Disponível em: https://www.aboutamazon.com/news/entertainment/prime-video-dialogue-boost. Acesso em: 24 nov. 2025.

BBC RESEARCH & DEVELOPMENT. Object-based media. BBC, 2023. Disponível em: https://www.bbc.co.uk/rd/object-based-media#work. Acesso em: 24 nov. 2025.

BORDWELL, David. The introduction of sound. In: BORDWELL, David; THOMPSON, Kristin; STEIGER, Janet (org.). The classical Hollywood cinema: film style & mode of production to 1960. New York: Columbia University Press, 1985. p. 298-308.

BRITO, Carlo. ‘O mecanismo’ volta e Selton Mello explica sussurros: ‘Eu não falo baixo, as pessoas falam alto’. G1, 10 maio 2019. Disponível em: https://g1.globo.com/pop-arte/noticia/2019/05/10/o-mecanismo-volta-e-selton-mello-explica-sussurros-eu-nao-falo-baixo-as-pessoas-falam-alto.ghtml. Acesso em: 24 nov. 2025.

CARREIRO, Rodrigo. A história do som dos filmes. In: CARREIRO, Rodrigo (org.). O som do filme: uma introdução. Curitiba: Editora da UFPR, 2018. p. 35-86.

CARREIRO, Rodrigo. O papel da respiração no cinema de horror. E-Compós, v. 23, 2020.

CARREIRO, Rodrigo; OPOLSKI, Débora. O espectro do som como ferramenta de análise fílmica. PÓS: Revista do Programa de Pós-Graduação em Artes da EBA/UFMG, v. 12, n. 24, p. 388–414, 2022.

CARREIRO, Rodrigo. Construindo um cinema sensorial: música, voz e efeitos sonoros além de fronteiras. Revista Música, v. 25, n. 1, p. 377–401, 2025.

CARREIRO, Rodrigo; CÁNEPA, Laura Loguercio. Cinema de Horror: Uma Introdução. São Paulo: Gênio Editorial, 2025.

CHION, Michel. A audiovisão. Lisboa: Texto e Grafia, 2008.

COULTHARD, Lisa. Dirty sound: Haptic noise in new extremism. In: VERNALLIS, Carol; HERZOG, Amy; RICHARDSON, John (orgs.). The Oxford Handbook of Sound and Image in Digital Media. New York: Oxford University Press, p. 115-126, 2013.

DE MAN, Brecht et al. The mix evaluation dataset. In: 137th Audio Engineering Society Convention. Los Angeles: AES, 2014. Disponível em: https://www.aes.org/e-lib/browse.cfm?elib=17478. Acesso em: 24 nov. 2025.

FLORIAN, Brian. Learning from history: Cinema sound and EQ curves. Secrets of Home Theater and High Fidelity, v. 9, n. 2, 2002. Disponível em: https://hometheaterhifi.com/volume_9_2/feature-article-curves-6-2002.html. Acesso em: 24 nov. 2025.

HOLMAN, Tomlinson. Sound for film and television. London: Routledge, 2005.

HUTCHINGS, Peter. The Horror Film. Edimburgh: Person Education Limited, 2004.

INTERNATIONAL TELECOMMUNICATION UNION. Recommendation ITU-R BS.1770-4: Algorithms to measure audio programme loudness and true-peak audio level. Genebra: ITU, 2017. Disponível em: https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.1770-4-201510-I!!PDF-E.pdf. Acesso em: 24 nov. 2025.

KULEZIC-WILSON, Danijela. Sound design is the new score: theory, aesthetics, and erotics of the integrated soundtrack. Oxford: Oxford University Press, 2019.

LASTRA, James. Fidelity versus intelligibility. In: STERNE, Jonathan (org.). The Sound Studies Reader. New York: Routledge, 2012. p. 248-254.

MERA, Miguel. Materializing film music. In: COOKE, M.; FORD, F. (Eds.). The Cambridge companion to film music. Cambridge: Cambridge University Press, p. 157-172, 2016.

MOFFAT, David; SANDLER, Mark. Approaches in Intelligent Music Production. In: Arts. v. 8, n. 4, p. 125, 2019. Disponível em: https://www.mdpi.com/2076-0752/8/4/125. Acesso em: 24 nov. 2025.

PEARSON, Ben. Here's why movie dialogue has gotten more difficult to understand (and three ways to fix it). SlashFilm, 22 ago. 2022. Disponível em: https://www.slashfilm.com/673162/heres-why-movie-dialogue-has-gotten-more-difficult-to-understand-and-three-ways-to-fix-it/. Acesso em: 24 nov. 2025.

PRITCHARD, Huw. The Beatles: Get Back - The Technical Story. Sound on Sound, fev. 2022. Disponível em: https://www.soundonsound.com/techniques/beatles-get-back. Acesso em: 24 nov. 2025.

RESPEECHER. Recreating the Legendary Luke Skywalker Voice for Disney's The Mandalorian. Respeecher Case Studies, 23 ago. 2021. Disponível em: https://www.respeecher.com/case-studies/legendary-luke-skywalker-voice-mandalorian. Acesso em: 24 nov. 2025.

STERNE, Jonathan. The Audio-Visual Litany. In: STERNE, Jonathan (org.). The Sound Studies Reader. New York: Routledge, p. 3-12, 2012.

THORNTON, Mike. TV subtitle usage up to 80% – what is going wrong with dialogue mixes?. Production Expert, 17 nov. 2022. Disponível em: https://www.pro-tools-expert.com/production-expert-1/tv-subtitle-usage-up-to-80-what-is-going-wrong-with-dialogue-mixes. Acesso em: 24 nov. 2025.

WARD, Lauren. Speak up! Why some TV dialogue is so hard to understand. The Conversation, 27 abr. 2017. Disponível em: https://theconversation.com/speak-up-why-some-tv-dialogue-is-so-hard-to-understand-75423. Acesso em: 24 nov. 2025.

Downloads

Published

2026-07-10

How to Cite

OCTAVIO D’AZEVEDO CARREIRO, Rodrigo; OPOLSKI, Débora Regina. The spectator as co-mixer: Artificial Intelligence, intelligibility, and the customization of cinematic listening. Revista Cientí­fica/FAP, Curitiba, v. 34, n. 1, 2026. DOI: 10.33871/19805071.2026.34.1.11624. Disponível em: https://periodicos.unespar.edu.br/revistacientifica/article/view/11624. Acesso em: 12 sep. 2026.

Issue

Vol. 34 No. 1 (2026): Inteligência Artificial e as Artes

Section

Dossiê Temático

License

The authors retain the copyright, when licensing their production in Revista Cientí­fica/FAP, which is licensed under a Creative Commons license. When submitting the article, and upon acceptance, the author assigns his copyright for publication in that journal.

Readers can download, print and use the articles published in the journal, as long as there is always an explicit mention of the author (s) and the Revista Cientí­fica/FAP, no changes to the original work are allowed. When submitting an article to Revista Cientí­fica/FAP and after its being accepted for publication, the authors allow, without remuneration, to pass the following rights to the Journal: the first edition rights and the authorization for the editorial team to transfer, according to their judgment, this article and its metadata to indexing and reference services.