N-best search for continuous speech recognition using viterbi pruning for non-output differentiation states
First Claim
Patent Images
1. A method of performing N-best speech recognition searching comprising the steps of:
- Viterbi pruning non-output differentiation states to keep the best path; and
keeping N-best sub-optimal paths for output differentiation states where different paths result in different outputs.
1 Assignment
0 Petitions
Accused Products
Abstract
A method for N-best search for continuous speech recognition with limited storage space includes the steps of Viterbi pruning word level (same word, different time alignment, thus non-output differentiation) states and keeping the N-best sub-optimal paths for sentence level (output differentiation) states.
57 Citations
3 Claims
-
1. A method of performing N-best speech recognition searching comprising the steps of:
-
Viterbi pruning non-output differentiation states to keep the best path; and
keeping N-best sub-optimal paths for output differentiation states where different paths result in different outputs. - View Dependent Claims (2, 3)
-
Specification
-
- Resources
Litigation Campaign Assessment
Thank you for your request. You will receive a custom alert email when the Litigation Campaign Assessment is available.
×
-
Current AssigneeTexas Instruments, Inc.
-
Original AssigneeTexas Instruments, Inc.
-
InventorsKao, Yu-Hung
-
Primary Examiner(s){haeck over (S)}mits, Tãlivaldis Ivars
-
Application NumberUS09/353,969Time in Patent Office1,006 DaysField of Search704/242, 704/256, 704/255US Class Current704/255CPC Class CodesG10L 15/08 Speech classification or se...G10L 15/083 Recognition networks G10L15...G10L 2015/085 Methods for reducing search...
