AuditoryLab

Congratulations to Yi Fei Cheng on his successful presentation of "First or Third-Person Hearing?" in which we explore the effect of spatial audio on avatar embodiment in VR.

@CyLab @CarnegieMellon This project was possible thanks to Hafsa OUAJDI, Oussama Hadder, @ModanTailleur, and Mathieu Lagrange from École Centrale Nantes, participants in the 2023 DCASE synthesis challenge (Task 7) who shared their sounds, and research assistants Anjelica Ferguson and Justine Sullivan.

Laurie Heller (@auditorylabinfo), @CarnegieMellon Professor of Psychology, and a team of researchers have developed a deep neural network detector to automatically classify environmental sounds as either real or #AI-generated. Learn more: cylab.cmu.edu/news/2024/09/1…

"Correlation of Frechet Audio Distance with Human Perception of Environmental Audio is Embedding Dependent” was led by graduate students Modan Tailleur and Junwon Lee, followed by M Lagrange (presenter), K Choi, LM Heller, K Imoto; Y Okamoto. eurasip.org/Proceedings/Eu…

How can objective metrics of sound organization be better aligned with human perception? At #EUSIPCO2024 we showed how audio embeddings affect this alignment for Fréchet Audio Distance. @ModanTailleur @jnwnlee M Lagrange @keunwoochoi LM Heller @KeisukeImoto @YukiOkamoto19

🚨 Call for #APCAM2024 submissions! Share your research on music cognition, speech perception, and more by Sept. 15! 🎶 Don’t miss out on travel awards and mentorship meetups—apply today! 🔗 apcsociety.org/apcam-call.html

The conference paper is “Detection of Deepfake Environmental Audio,” by H Ouajdi, H Oussama, M Tailleur, M Lagrange, LM Heller. eurasip.org/Proceedings/Eu…

Would you like to discriminate fake from real sounds? 👂Today, at #EUSIPCO2024, Prof. Lagrange presented an accurate system for detecting fake (ai-generated) everyday sounds, led by students Ouajdi & Oussama. We also showed human performance and strategies for detection.

@jnwnlee Fantastic results! Congratulations.

Video-Foley: excited to share my new research on Controllable Video-to-Sound 🎥→🔊 generation! Check out the video demo: youtube.com/watch?v=5FWNL6…

Congratulations Dr. Hassan Azad (U of Florida) on a great presentation today about the effects of noise on school children at Internoise 2024! He's first author on our conference paper, ASSESSMENT OF ANNOYANCE FROM TRAFFIC NOISE INSIDE AND OUTSIDE A SCHOOL. @internoise2024

🏅 📢 Congratulations to the top 4 ranked generative text-to-audio systems in our Sound Scene Synthesis challenge for DCASE 2024! dcase.community/challenge2024/… @ModanTailleur @jnwnLee @KeisukeImoto @keunwoochoi @YukiOkamoto19 @functiontelechy

📣Want to break the silence of AI-generated videos? Generate sound scenes from text prompts in our new challenge, Task 7 of DCASE 2024: “Sound Scene Synthesis.” @acousticsorg @IEEEsps @forthshinji @ModanTailleur @jnwnLee @KeisukeImoto @functiontelechy @YukiOkamoto19 @keunwoochoi

🔊 Hi folks! Looking forward to exploring the latest in auditory science and sharing updates about #APCAM2024 and the Auditory Perception & Cognition Society with you along the way!

Did you know that louder sounds 📢are easier to recognize, but more unpleasant? So, is it valid to "equalize" sound levels in the lab to test sound recognition and pleasantness? See our new paper in @ASA_JASAEL, funded by @misophoniafund, to find out. pubs.aip.org/asa/jel/articl…

Great job today by graduate student Urszula Oszczapinska! She presented our research on misophonia, funded by @misophoniafund: Altering the Perceived Cause of Unpleasant and Misophonic Sounds with Videos and Words at #AROMWM2024. aro.societyconference.com/v2/

#APCAM2023 is today in San Francisco! There are presentations on: auditory scene analysis, cross-model perception, music perception, speech perception, language processing, and healthy/disordered hearing. Our lab is presenting on misophonic sounds. apcsociety.org

Thanks to @KeisukeImoto and Mathieu Lagrange for presenting our conference paper last week at the DCASE Workshop in Finland on @DCASE_Challenge Task 7, Foley sound. 📢#Choi2023" target="_blank" rel="nofollow noopener">dcase.community/workshop2023/p… @keunwoochoi @osalooloo @forthshinji @YukiOkamoto19 Brian McFee

Just came back from a meeting filled with talks about ongoing research on ways to understand, diagnose and treat misophonia! #MRFannualmeeting. I presented my lab's research funded by misophoniaresearchfund.org and got to hear about all the fascinating progress being made.

The call for abstracts is open for the 22nd annual Auditory Perception, Cognition, and Action Meeting (APCAM) on Nov 16th in San Francisco, CA. Deadline 09/17/23 for abstract submission and travel award applications. Visit apcsociety.org . @acousticsorg @AuditoryAPCAM

@DCASE_Challenge @keunwoochoi @osalooloo @KeisukeImoto @forthshinji @YukiOkamoto19 For more information on how we combined subjective & objective evaluations to compare 18 generative systems, see this paper: arxiv.org/abs/2304.12521

Worked hard, learned a lot, and met a great team during the first-ever competition for generative everyday sounds at @DCASE_Challenge, Task 7 Foley sound! @keunwoochoi @osalooloo @KeisukeImoto @forthshinji @YukiOkamoto19 Mathieu Lagrange, Brian McFee.

Our lab at @CarnegieMellon is recruiting 18+ #misophonics in the Pittsburgh area for an in-person study on #misophonia! 🔊 1.5-2hrs at $12/hr 🔊 Listen to everyday sounds while being monitored by our team Please share with your networks! More info below