US 9,286,896 B2Granted

Document transcription system training

AssigneeMModal IP LLC

InventorsGirija Yegnanarayanan, Michael Finke, Juergen Fritsch, Detlef Koll, Monika Woszczyna

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Claims6

Dependent claims

A method for use with a system including a first document containing at least some information in common with a spoken audio stream, the method performed by at least one computer processor executing computer program instructions to perform steps of:

(A) identifying text in the first document, wherein the text represents a concept;
(B) identifying, based on the identified text and a repository of finite state grammars, a plurality of spoken forms of the concept, including at least one spoken form not contained in the first document, wherein all of the plurality of spoken forms have the same content as each other;
(C) replacing the identified text with a finite state grammar specifying the plurality of spoken forms of the concept to produce a second document, wherein the finite state grammar includes the identified text and text other than the identified text;
(D) generating a document-specific language model based on the second document, comprising generating at least some of the document-specific language model based on the finite state grammar;
and
(E) using the document-specific language model in a speech recognition process to recognize the spoken audio stream and thereby to produce a third document.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/280,041Filed 16 May 2014 · continuation
Priority: 20 Aug 2004
Published: US 2014/0249818 A14 Sep 2014
Granted: 15 Mar 2016
Term ends: Not estimatedThe source records don’t support an estimate.

Classification4 codes

G10L 15/063
Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice: training
G10L 15/193
Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules: formal grammars, e.g. finite state automata,…
G10L 15/26
Speech recognition: speech to text systems
G10L
Speech analysis techniques or speech synthesis

Family

Application10/922,513Parent of this continuation · filed 20 Aug 2004
Application13/691,249Parent of this continuation · filed 30 Nov 2012
US 8,335,688 B2Parent of this continuation · filed 18 Dec 2012
US 2014/0249818 A1Pre-grant publication · published 4 Sep 2014
US 8,731,920 B2Parent of this continuation
US 2006/0041427 A1Published application
US 2013/0103400 A1Published application
US 9,286,896 B2This patent

From the US filing history. Foreign family members aren’t listed.