‘Fishial’ Recognition: Neural Network Identifies Coral Reef Sounds

Faster identification of fish sounds from acoustic recordings can improve research, conservation efforts

CUREE, an autonomous underwater robot, is used by the researchers to collect acoustic data for analysis. Image by Austin Greene, Woods Hole Oceanographic Institution

WASHINGTON, March 11, 2025 – Coral reefs are some of the world’s most diverse ecosystems. Despite making up less than 1% of the world’s oceans, one quarter of all marine species spend some portion of their life on a reef. With so much life in one spot, researchers can struggle to gain a clear understanding of which species are present and in what numbers.

In JASA, published on behalf of the Acoustical Society of America by AIP Publishing, researchers from Woods Hole Oceanographic Institution combined acoustic monitoring with a neural network to… click to read more

From: JASA
Article: Automated acoustic voice screening techniques for comorbid depression and anxiety disorders
DOI: 10.1121/10.0035829

Ouch! Commonalties Found in Pain Vocalizations and Interjections Across Cultures

Study investigates vocalizations and interjections for pain, joy, and disgust across 131 languages.

Vowel density maps reveal that distinct vowel spaces for vocalizations of pain, disgust, and joy remain consistent across languages. Credit: Ponsonnet et al.

WASHINGTON, Nov. 12, 2024 – There are an estimated 7,000 languages spoken worldwide, each offering unique ways to express human emotion. But do certain emotions show regularities in their vocal expression across languages?

In JASA, published on behalf of the Acoustical Society of America by AIP Publishing, an interdisciplinary team of linguists and bioacousticians led by Maïa Ponsonnet, Katarzyna Pisanski, and Christophe Coupé explored this by… click to read more

From: JASA
Article: Vowel signatures in emotional interjections and nonlinguistic vocalizations expressing pain, disgust and joy across languages
DOI: 10.1121/10.0032454

June 2024 JASA Cover

The June cover of JASA is now available! Check it out:

The cover image was selected to represent “Evidence for proactive and retroactive temporal pattern analysis in simultaneous masking,” by Bernhard Laback, Hisaaki Tabuchi, and Armin Kohlrausch. JASA Coordinating Editor for Psychological and Physiological Acoustics Emily Buss says, “[This article] describes basic psychoacoustic research into the way listeners use the temporal regularity of background sounds to maximize signal detection. Results speak to the basic mechanisms that listeners use to organize sound into an auditory scene.”

Some other research was also highlighted on the June JASA cover:

From Acoustical Oceanography, “Reflected acoustic energy from geological layers during seismic reflection surveys,” by Alexander S. Douglass, Shima Abadi, Benjamin J. Phrampus, and Warren T. Wood
From Architectural Acoustics, “Free-field method for inverse characterization of finite porous acoustic materials using feed forward neural networks,” by Mark Müller-Giebeler, Marco Berzborn, and Michael Vorländer
From Physical Acoustics, “Propagation of elastic waves in correlated dispersions of resonant scatterers,” by Alverède Simon, Quentin Baudis, Régis Wunenburger, and Tony Valier-Brasier
From Speech Communication, “Advanced accent/dialect identification and accentedness assessment with multi-embedding models and automatic speech recognition,” by Shahram Ghorbani and John H. L. Hansen

All the articles from the cover are free to read for a month after the cover is released, so be sure to check them out! You can find the whole issue at https://pubs.aip.org/asa/jasa/issue/155/6.

Diversity in Speech Science: Pride Month Highlights

ASA fosters inclusivity and understanding through groundbreaking research that highlights the unique experiences and voices of the LGBTQ+ community. For Pride Month, we would like to spotlight publications that underscore the intersection of speech science and gender diversity.

First up is “Acoustic Cues to Femininity and Masculinity in Spontaneous Speech” by Fredrik Nylén, Jenny Holmberg, and Maria Södersten. This recently published JASA research unravels the intricate acoustic properties that influence perceptions of gender in speech. The study explores how vocal characteristics can contribute to gender identity and offers critical insights that benefit gender-affirming voice training. With a comprehensive analysis of 132 voices and 121 listener evaluations, the researchers developed models explaining up to 89% of the variance in perceived femininity and masculinity. Their findings emphasize the importance of considering a range of acoustic properties beyond the primary cue of median fundamental frequency (f0).

Next up is “Spectral Analysis of Strident Fricatives in Cisgender and Transfeminine Speakers” by Nichole Houle, Mackenzie P. Lerario, and Susannah V. Levi, also published in the JASA. This research explores the acoustic properties of the sounds /s/ like in ‘said’ and /ʃ/ in ‘shed’, revealing how subtle nuances contribute to the sociophonetic perception of gender. By examining the speech of cisgender men, cisgender women, and transfeminine speakers, the study highlights the complexity and diversity of gender expression in vocal characteristics. It shows that while the spectral features of /s/ and /ʃ/ can signal gender group identification, they do not account for within-gender variation among transfeminine speakers. This nuanced approach moves beyond the binary classification of gender, offering a more inclusive understanding that acknowledges the spectrum of gender identities.

Finally, Melissa Baese-Berk and Paul E. Reed’s JASA article “Addressing Diversity in Speech Science Courses,” underscores the critical need to integrate cultural and linguistic diversity, including LGBTQ+ perspectives, into speech science education. Speech communication, the study of how speech is produced, transmitted, and perceived, is a cornerstone of disciplines like linguistics, communication disorders, cognitive science, and speech technology. Baese-Berk and Reed observe that speech science courses often lag in representing the full spectrum of cultural and linguistic diversity, particularly in terms of gender identity and sexual orientation. Their study argues that linguistic diversity should be a fundamental part of the curriculum, not relegated to a single module or course. By addressing linguistic diversity comprehensively, educators can better reflect the varied social identities of speakers, including those within the LGBTQ+ community.

As we celebrate Pride Month, it’s essential to recognize and honor the contributions of LGBTQ+ researchers and participants within the field of speech science. The studies highlighted here not only advance our scientific understanding but also promote inclusivity and respect for diverse voices. By embracing this research and its implications, we can continue to build a more inclusive and equitable scientific community. Happy Pride Month!

JASA Special Issue on Fish Bioacoustics: Hearing and Sound Communication

The collection for the JASA Special Issue on Fish Bioacoustics: Hearing and Sound Communication is now available online!

The field of fish bioacoustics—encompassing studies of fish hearing, sound production, and acoustic communication—is of increasing importance as investigators, regulators, and others now realize that anthropogenic sounds are likely to have a major impact on fishes, their ecosystems, and on the human food supply. To help better understand fish bioacoustics, this special issue of The Journal of the Acoustical Society of America brings together papers that explore the breadth of the topic, from historical perspectives to the latest findings on the impact of anthropogenic sounds on fishes.

Many thanks to Arthur N. Popper, Clara Amorim, Michael L. Fine, Dennis M. Higgs, Allen F. Mensinger, and Joseph A. Sisneros for serving as Guest Editors for this Special Issue.

Read more on this Special Issue in the Introduction and visit the collection of articles.

Image credit: Figure 2 from Deng et al (2023).