Zobrazeno 1 - 10
of 520
pro vyhledávání: '"Shamma, Shihab"'
While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it differentiable, so tha
Externí odkaz:
http://arxiv.org/abs/2409.08997
Publikováno v:
Interspeech 2023
Most organisms including humans function by coordinating and integrating sensory signals with motor actions to survive and accomplish desired tasks. Learning these complex sensorimotor mappings proceeds simultaneously and often in an unsupervised or
Externí odkaz:
http://arxiv.org/abs/2210.16454
End-to-end learning models have demonstrated a remarkable capability in performing speech segregation. Despite their wide-scope of real-world applications, little is known about the mechanisms they employ to group and consequently segregate individua
Externí odkaz:
http://arxiv.org/abs/2206.09556
Multi-resolution spectro-temporal features of a speech signal represent how the brain perceives sounds by tuning cortical cells to different spectral and temporal modulations. These features produce a higher dimensional representation of the speech s
Externí odkaz:
http://arxiv.org/abs/2203.05780
Recent advancements in deep learning have led to drastic improvements in speech segregation models. Despite their success and growing applicability, few efforts have been made to analyze the underlying principles that these networks learn to perform
Externí odkaz:
http://arxiv.org/abs/2203.04420
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Experiments to understand the sensorimotor neural interactions in the human cortical speech system support the existence of a bidirectional flow of interactions between the auditory and motor regions. Their key function is to enable the brain to `lea
Externí odkaz:
http://arxiv.org/abs/2110.05695
Publikováno v:
In Hearing Research May 2021 404
Autor:
Liberto, Giovanni M. Di, Nie, Jingping, Yeaton, Jeremy, Khalighinejad, Bahar, Shamma, Shihab A., Mesgarani, Nima
Publikováno v:
In NeuroImage 15 February 2021 227
We consider the problem of estimating the sparse time-varying parameter vectors of a point process model in an online fashion, where the observations and inputs respectively consist of binary and continuous time series. We construct a novel objective
Externí odkaz:
http://arxiv.org/abs/1507.04727
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.