Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Penn, Gerald"'
Publikováno v:
Proceedings of Interspeech 2024
A long-standing question in automatic speech recognition research is how to attribute errors to the ability of a model to model the acoustics, versus its ability to leverage higher-order context (lexicon, morphology, syntax, semantics). We validate a
Externí odkaz:
http://arxiv.org/abs/2407.16537
Functional Faithfulness in the Wild: Circuit Discovery with Differentiable Computation Graph Pruning
In this paper, we introduce a comprehensive reformulation of the task known as Circuit Discovery, along with DiscoGP, a novel and effective algorithm based on differentiable masking for discovering circuits. Circuit discovery is the task of interpret
Externí odkaz:
http://arxiv.org/abs/2407.03779
We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascent thesis proposes that facts are recalled from the training corpus thr
Externí odkaz:
http://arxiv.org/abs/2405.02421
Triangular, overlapping Mel-scaled filters ("f-banks") are the current standard input for acoustic models that exploit their input's time-frequency geometry, because they provide a psycho-acoustically motivated time-frequency geometry for a speech si
Externí odkaz:
http://arxiv.org/abs/1901.00072
Autor:
Penn, Gerald
Constraint Handling Rules (CHR) have provided a realistic solution to an over-arching problem in many fields that deal with constraint logic programming: how to combine recursive functions or relations with constraints while avoiding non-termination
Externí odkaz:
http://arxiv.org/abs/cs/0007013
Autor:
Penn, Gerald
Publikováno v:
Journal of Logic, Language, and Information, 2011 Jul 01. 20(3), 273-275.
Externí odkaz:
https://www.jstor.org/stable/41488478
Autor:
Penn, Gerald
Publikováno v:
In Theoretical Computer Science 2006 354(1):72-81
Triangular, overlapping Mel-scaled filters ("f-banks") are the current standard input for acoustic models that exploit their input's time-frequency geometry, because they provide a psycho-acoustically motivated time-frequency geometry for a speech si
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e699bccd1a85aec0e3750d38fdee04f1
Publikováno v:
Philippe de Groote; Frank Drewes; Gerald Penn. Jul 2019, Toronto, Canada. Association for Computational Linguistics, 2019
Philippe de Groote; Frank Drewes; Gerald Penn. Association for Computational Linguistics, 2019
Philippe de Groote; Frank Drewes; Gerald Penn. Association for Computational Linguistics, 2019
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::252a2f0f8d4b8a8045a6bb7a8a668b77
https://hal.inria.fr/hal-02268054
https://hal.inria.fr/hal-02268054