Anne B Rogers

US Patent:

6374212, Apr 16, 2002

Filed:

Mar 13, 2001

Appl. No.:

09/804041

Inventors:

Steven Phillips - New York NY
Anne Rogers - Summit NJ

Assignee:

ATT Corp. - New York NY

International Classification:

G10L 1528

US Classification:

704231, 704256

Abstract:

A continuous, speaker independent, speech recognition method and system for recognizing a variety of vocabulary input signals. A language model which is an implicit description of a graph consisting of a plurality of states and arcs is inputted into the system. An input speech signal, corresponding to a plurality of speech frames is received and processed using a shared memory multipurpose machine having a plurality of microprocessors working in parallel to produce a textual representation of the speech signal.

US Patent:

62497618, Jun 19, 2001

Filed:

Sep 30, 1997

Appl. No.:

8/941379

Inventors:

Steven Phillips - New York NY
Anne Rogers - Summit NJ

Assignee:

AT&T Corp. - New York NY

International Classification:

G10L 1528
G10L 1514

US Classification:

704231

Abstract:

A continuous, speaker independent, speech recognition method and system recognizes a variety of vocabulary input signals. A language model, which is an implicit description of a graph consisting of a plurality of states and arcs, is input into the system. An input speech signal, corresponding to a plurality of speech frames, is received and processed using a shared memory multipurpose machine having a plurality of microprocessors. Threads are created and assigned to processors, and active state subsets and active arc subsets are created and assigned to specific threads and associated microprocessors. Active state subsets and active arc subsets are processed in parallel to produce a textual representation of the speech signal. Embodiments of the invention include a two-level Viterbi search algorithm to match the input speech signals to context dependent units, an on-demand composition of finite state transducers to map context dependent units to sentences, and a determination whether a particular likelihood calculation needs to be performed or recalled from memory. The on-demand composition of finite state transducers is accomplished by multi-threading the calculation in accordance with the parallel processing feature of the system.