Koninklijke Philips Corporation N.v.

U.S. Philips Corporation

Heribert Wutte

Gabor Janek

Eric Thelen

Attila Muszta

Manfred Grabherr

Harald R&ouml;ggla

A speech recognition method () with a text editing method of editing a text information part (TW) erroneously recognized in first text information (TI) with a four-word spoken command (SB) recognized in second text information (TI) is disclosed. The speech recognition method comprises the steps of receiving speech information (SI) and recognizing the first text information (TI) and the second text information (T), checking whether a word at the first position in the second text information (TI) matches a first spoken command part (SB) and checking whether a word at the third or further position in the second text information (TI) matches a third spoken command part (SB) while, in the event of a positive result of the checks, the next step of the text editing method is executed, checking whether the first text information (TI) contains the erroneously recognized text information part (TW) which is featured by a second spoken command part (SB) in the second text information (TI) between the first spoken command part (SB) and the third spoken command (SB) while, in the event of a positive result of the check, the next step of the text editing method is executed, replacing the erroneously recognized text information part (TW) in the first text information TIwith new text information part (TN) which the second text information (TI) contains as a fourth spoken command part (SB) of the four-word spoken command (SB) after the third spoken command part (SB).

Speech recognition method with a replace command

In a speech recognition device () comprising receiving means () for receiving voice information (AI) uttered by a speaker and including speech coefficient storage means () for storing a speech coefficient indicator (SKI, PRI, SMI, WI) and including speech recognition means () which are arranged for recognizing text information (RTI) which corresponds to the received voice information (AI) by evaluating the voice information (AI) and the speech coefficient indicator (SKI, PRI, SMI, WI), transfer means () are now provided which enable to import a speech coefficient indicator (SKI, PRI, SMI, WI) and to store the imported speech coefficient indicator (SKI, PRI, SMI, WI) in the speech coefficient storage means ().

Speech recognition device with transfer means

In a text processing system ( ) are provided a speech recognition device ( ) to which a spoken command information signal (SI) can be applied in a command inputting mode of the speech recognition device ( ) and which is arranged for producing a control data (CI) assigned to one of the applied spoken command information signals (SI), and a text processing device ( ) which can be brought to an active state for processing a text data (TI), while a text-block data (MT) of a stored text data (TI) can be featured in the text processing device ( ) and the text processing device ( ) can be supplied with a control data (CI) by the speech recognition device ( ) for changing a featured text-block data (MT) and, furthermore, text change means ( ) are provided to which a further control data (BI) assigned to a further spoken command information signal (SI) can be delivered in the command inputting mode of the speech recognition device ( ), while the text change means ( ) are arranged for changing a text-block data (MT) featured in the text processing device ( ) in accordance with the further spoken command information signal (SI) applied to the speech recognition device ( ).

Text processing system including a speech recognition device and text change means for changing a text-block data

In a speech recognition system, the received speech and the sequence of words, recognized in the speech by a recognizer ( ), are stored in a memory ( ). Markers are stored as well, indicating a correspondence between the word and a segment of the received signal in which the word was recognized. In a synchronous reproduction mode, a controller ( ) ensures that the speech is played-back via speakers ( ) and that for each speech segment a word, which has been recognized for the segment, is indicated (e.g. highlighted) on a display ( ). The controller ( ) can detect whether the user has provided an editing instruction, while the synchronous reproduction is active. If so, the synchronous reproduction is automatically paused and the editing instruction executed.

Synchronous reproduction in a speech recognition system

With a method of and an arrangement for speech recognition a measurement of the speech velocity rate is carried out in a measuring unit ( ) so as to reduce the error rate of the recognition result, which speech velocity is announced to the speaker via an output unit ( ) and warning is given if the velocity is out of speech recognition adaptation range.

Method of an arrangement for speech recognition with speech velocity adaptation

In a product including a speech recognition device for controlling at least one processing unit while using a command lexicon containing commands which depends as regards its contents on an activated operating state of a processing unit and which speech recognition device includes a command lexicon memory in which commands of the command lexicon can be stored in the form of command information and identification information assigned to the latter, and which speech recognition device includes speech recognition means for detecting command information&mdash;contained in speech information representing a spoken command&mdash;and delivers command information to the at least one processing unit, generating means are provided which are arranged for generating&mdash;after an operating state of a processing unit has been activated&mdash;which may be effected with the aid of command information detected in a spoken command&mdash;a command lexicon assigned to only this one activated operating state and for storing this command lexicon in the command lexicon memory.

Growing community of inventors

Graz, Austria

Heribert Wutte