Gasser Elbanna
@gelbanna.bsky.social
PhD student in Speech and Hearing at Harvard/MIT. Building ANNs to study how humans perceive/produce speech and voice.
Working with @joshhmcdermott.bsky.social
https://gasserelbanna.github.io/
MSc. at EPFL
BSc. at Cairo University
ex Logitech and IDIAP
Working with @joshhmcdermott.bsky.social
https://gasserelbanna.github.io/
MSc. at EPFL
BSc. at Cairo University
ex Logitech and IDIAP
3. We manipulated the model’s access to past and future speech cues, revealing the importance of the acoustic context and its directionality in human speech recognition.
Come to our poster to learn more!
🧵4/4
Come to our poster to learn more!
🧵4/4
June 5, 2025 at 12:02 AM
3. We manipulated the model’s access to past and future speech cues, revealing the importance of the acoustic context and its directionality in human speech recognition.
Come to our poster to learn more!
🧵4/4
Come to our poster to learn more!
🧵4/4
2. These tasks allowed us to compute the first full phoneme confusion matrix in humans at scale. This enabled the first systematic comparison of human–model phoneme confusions, revealing that humans and models share not only similar response patterns but also similar patterns of confusions.
🧵3/4
🧵3/4
June 5, 2025 at 12:02 AM
2. These tasks allowed us to compute the first full phoneme confusion matrix in humans at scale. This enabled the first systematic comparison of human–model phoneme confusions, revealing that humans and models share not only similar response patterns but also similar patterns of confusions.
🧵3/4
🧵3/4
This work has 3 main contributions:
1. We developed new models of continuous speech recognition alongside novel behavioral tasks to compare both models and humans on speech perception without conflating speech and language.
🧵2/4
1. We developed new models of continuous speech recognition alongside novel behavioral tasks to compare both models and humans on speech perception without conflating speech and language.
🧵2/4
June 5, 2025 at 12:02 AM
This work has 3 main contributions:
1. We developed new models of continuous speech recognition alongside novel behavioral tasks to compare both models and humans on speech perception without conflating speech and language.
🧵2/4
1. We developed new models of continuous speech recognition alongside novel behavioral tasks to compare both models and humans on speech perception without conflating speech and language.
🧵2/4