Search

Jan Robin Rohlicek

from Watertown, MA
Age ~65
Get Report
Also known as:
Jan R Rohlicek, Jrobin R Rohlicek
Phone and address:
86 Standish Rd, Watertown, MA 02472
(617) 924-5356
Connected to:
Erin N Rohlik, 38Teresa A Rohlin, 64Audrey A Rohlinger, 81Belinda L Rohling, 32Brittany M Rohling, 33Elizabeth K Rohling, 61Gregory A Rohling, 58Hermann W Rohling, 74Jane M Rohling, 71Mark A Rohlinger, 62

Jan Rohlicek Phones & Addresses

  • 86 Standish Rd, Watertown, MA 02472 (617) 924-5356 (617) 797-8669
  • Arlington, MA
  • Cambridge, MA
  • Worcester, MA
  • 86 Standish Rd, Watertown, MA 02472 (617) 797-8669

Work

Company: Occhiuti Rohlicek Tsao LLP Address: 321 Summer St, Boston, MA 02210 Specialities: Commercial - 34% • Telecommunications - 33% • Government - 33%

Education

Degree: JD School / High School: Boston College Law School

Ranks

Licence: Massachusetts - Active Date: 2002

Professional Records

Lawyers & Attorneys

Jan Rohlicek Photo 1

Jan Robin Rohlicek, Boston MA - Lawyer

View page
Address:
Occhiuti Rohlicek Tsao LLP
321 Summer St, Boston, MA 02210
(617) 500-2502 (Office), (617) 500-2499 (Fax)
Licenses:
Massachusetts - Active 2002
Education:
Boston College Law School
Degree - JD
Specialties:
Commercial - 34%
Telecommunications - 33%
Government - 33%

Publications

Us Patents

Topic Discriminator Using Posterior Probability Or Confidence Scores

View page
US Patent:
56257481, Apr 29, 1997
Filed:
Apr 18, 1994
Appl. No.:
8/228755
Inventors:
John W. McDonough - Brighton MA
Herbert Gish - Newton MA
Jan R. Rohlicek - Watertown MA
Kenney Ng - Boston MA
Phillippe Jeanrenaud - Arlington MA
Assignee:
BBN Corporation - Cambridge MA
International Classification:
G10L 506
G10L 900
US Classification:
395 26
Abstract:
An improved topic discriminator includes an integrated speech recognizer or word and phrase spotter as part of a speech event detector, and a topic classifier trained on topic-dependent event frequencies. The event frequencies are determined from either or both transcribed data with a text event detector and untranscribed speech data with a speech event detector. In accordance with another aspect of the present invention, the phrase spotter is used to detect the presence of phrases without the need of parsing the output of a speech recognizer's hypothesized transcription. In accordance with another aspect of the invention, an improved technique is used to select a subset of the potential speech events on whose event frequencies the topic discrimination decision is made. Finally, in accordance with another aspect of the invention, an improved method of topic modeling is used to improve the performance of the topic discriminator.
Control profile
Jan Robin Rohlicek from Watertown, MA, age ~65 Get Report