Toward Zero Oracle Word Error Rate on the Switchboard Benchmark

Autor: Faria, Arlo, Janin, Adam, Riedhammer, Korbinian, Adkoli, Sidhi

The "Switchboard benchmark" is a very well-known test set in automatic speech recognition (ASR) research, establishing record-setting performance for systems that claim human-level transcription accuracy. This work highlights lesser-known practical c

Externí odkaz: http://arxiv.org/abs/2206.06192

The YLI-MED Corpus: Characteristics, Procedures, and Plans

Autor: Bernd, Julia, Borth, Damian, Elizalde, Benjamin, Friedland, Gerald, Gallagher, Heather, Gottlieb, Luke, Janin, Adam, Karabashlieva, Sara, Takahashi, Jocelyn, Won, Jennifer

The YLI Multimedia Event Detection corpus is a public-domain index of videos with annotations and computed features, specialized for research in multimedia event detection (MED), i.e., automatically identifying what's happening in a video by analyzin

Externí odkaz: http://arxiv.org/abs/1503.04250

Scientific kernels on VIRAM and imagine media processors

Autor: Narayanan, Manikamdan, Oliker, Leonid, Janin, Adam, Husbands, Parry, Li, Xiaoye S.

Publikováno v: Narayanan, Manikamdan; Oliker, Leonid; Janin, Adam; Husbands, Parry; & Li, Xiaoye S.(2002). Scientific kernels on VIRAM and imagine media processors. Lawrence Berkeley National Laboratory. Lawrence Berkeley National Laboratory: Lawrence Berkeley National Laboratory. Retrieved from: http://www.escholarship.org/uc/item/37v9j259

Many high performance applications run well below the peak arithmetic performance of the underlying machine, with inefficiencies often attributed to a lack of memory bandwidth. In this work we examine two emerging media processors designed to address

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______325::6b73bd337d77541e6f73c535ceffe70d
http://www.escholarship.org/uc/item/37v9j259

Reducing errors by increasing the error rate: MLP Acoustic Modeling for Broadcast News Transcription

Autor: Morgan, Nelson, Ellis, Daniel P. W., Fosler-Lussier, Eric, Janin, Adam, Kingsbury, Brian

We describe some aspects of a Broadcast News recognition system based on hybrid HMM/MLP acoustic modeling. These include the use of novel 'modulation spectrogram' features which are combined with conventional models at the posterior probability level

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::252b8b1af160f362d8064202bea0b28f

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.