Zobrazeno 1 - 10
of 761
pro vyhledávání: '"Lane, Ian"'
Publikováno v:
Springer, Lecture Notes on Computer Science (LNAI,volume 14980), 2024
Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large language mod
Externí odkaz:
http://arxiv.org/abs/2409.11589
Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptation of models across multiple d
Externí odkaz:
http://arxiv.org/abs/2207.05071
Conformer has proven to be effective in many speech processing tasks. It combines the benefits of extracting local dependencies using convolutions and global dependencies using self-attention. Inspired by this, we propose a more flexible, interpretab
Externí odkaz:
http://arxiv.org/abs/2207.02971
Autor:
Elizalde, Benjamin, Revutchi, Radu, Das, Samarjit, Raj, Bhiksha, Lane, Ian, Heller, Laurie M.
In Psychology, actions are paramount for humans to identify sound events. In Machine Learning (ML), action recognition achieves high accuracy; however, it has not been asked whether identifying actions can benefit Sound Event Classification (SEC), as
Externí odkaz:
http://arxiv.org/abs/2104.12693
Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans. Video question answering is a specific scenario of such AI-human interaction where an
Externí odkaz:
http://arxiv.org/abs/1907.13280
Autor:
Chao, Guan-Lin, Lane, Ian
An important yet rarely tackled problem in dialogue state tracking (DST) is scalability for dynamic ontology (e.g., movie, restaurant) and unseen slot values. We focus on a specific condition, where the ontology is unknown to the state tracker, but t
Externí odkaz:
http://arxiv.org/abs/1907.03040
Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of overlapping sp
Externí odkaz:
http://arxiv.org/abs/1906.05962
This work presents a novel approach to leverage lexical information for speaker diarization. We introduce a speaker diarization system that can directly integrate lexical as well as acoustic information into a speaker clustering process. Thus, we pro
Externí odkaz:
http://arxiv.org/abs/1811.10761
Autor:
Zeng, Ming, Gao, Haoxiang, Yu, Tong, Mengshoel, Ole J., Langseth, Helge, Lane, Ian, Liu, Xiaobing
Publikováno v:
The International Symposium on Wearable Computers (ISWC) 2018
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant
Externí odkaz:
http://arxiv.org/abs/1810.04038
Autor:
Lane, Ian G., Portman, Zachary M., Herron-Sweet, Christina R., Petersen, Jessica D., Bruninga-Socolar, Bethanne, Cariveau, Daniel P.
Publikováno v:
In Biological Conservation March 2023 279