Apparatus for recording speech for subsequent text generation

• US 5,809,464 A
• Filed: 09/22/1995
• Issued: 09/15/1998
• Est. Priority Date: 09/24/1994
• Status: Expired due to Term

• Current Assignee: Alcatel NV (Nokia Corporation)
• Original Assignee: Alcatel NV (Nokia Corporation)
• Inventors: Hackbarth, Heidi, Kopp, Dieter
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/532,115
• Time in Patent Office: 1,089 Days
• Field of Search: 395/2.44, 395/2.79, 395/2.84, 395/2.09, 395/2.6, 395/2.42, 395/2.52, 395/2.67, 704/235, 704/200, 704/270, 704/272
• US Class Current: 704/235
• CPC Class Codes: G11C 2207/16 Solid state audio deprecated, only for historical reasons, G06F3/16, G11B
• CPC Class Codes: G11C 7/16 Storage of analogue signals in digital stores using an arrangement comprising analogue/digital [A/D] converters, digital memories and digital/analogue [D/A] converters
• CPC Class Codes: H04M 3/5307 for recording messages comprising any combination of audio and non-audio components

Abstract

An apparatus for recording speech for subsequent generation of a text includes an acoustic input (M) and an acoustic output (L) for inputting and outputting analog speech respectively. An analog-to-digital/digital-to-analog (AD/DA) converter converts the inputted analog speech into a digitized speech and converts digitized speech into analog speech. A preprocessor (VV) preprocesses the digitized speech converted by the converter (AD/DA), and extracts spectral component characteristics from the digitized speech. A digital memory (MEM) stores the digitized preprocessed speech and a controller (CON) controls an execution of inputted operating functions by at least one of the preprocessor and the digital memory. The method of recording speech for subsequent generation of a text using a speech-processing system includes digitizing an input analog speech data, preprocessing the digitized analog speech data by extracting spectral component characteristics from the digitized analog speech for subsequent generation of a text by a speech recognition process, storing the digitized preprocessed speech in a digital memory, and subsequently retrieving the digitized preprocessed analog speech from the digital memory and converting the retrieved speech into a text by use of a speech-processing system that includes a speech recognition program.

Claims

1. An apparatus for recording speech for subsequent generation of a text, comprising:

acoustic input and output means (L,M) for inputting and outputting analog speech respectively;

an analog-to-digital/digital-to-analog converter (AD/DA) for converting the inputted analog speech to digitized speech and for converting the digitized speech to analog speech;

preprocessing means (VV) for preprocessing the digitized speech digitized by the converter (AD/DA) by extracting component characteristics from the digitized speech;

a digital memory means (MEM) for storing the digitized, preprocessed speech;

a controller (CON) for controlling execution of inputted operating functions by at least one of the preprocessing means (VV) and the digital memory means (MEM); and

a data link (11) for transmitting the digitized, preprocessed speech stored in the digital memory means (MEM) via a communication network (14) to a remote text generator (12) for generating text corresponding to the inputted analog speech.

2. An apparatus as claimed in claim 1, further comprising:

a coder-decoder (CODEC) for coding the digitized speech received from the converter (AD/DA) before the digitized speech is stored in the digital memory (MEM).

3. An apparatus as claimed in claim 2, wherein the digital memory means (MEM) comprises one of a nonvolatile nonremovable EEPROM functioning as a random-access memory, and a removable PCMCIA card functioning as a random access memory.

4. An apparatus as claimed in claim 3, wherein the communication network (14) comprises one of a radio network (16) and a telecommunication network (17).

5. An apparatus as claimed in claim 1, wherein the digital memory means (MEM)comprises one of a nonvolatile nonremovable EEPRON functioning as a random-access memory, and a removable PCMCIA card functioning as a random-access memory.

6. An apparatus as claimed in claim 5, wherein the communication network (14) comprises one of a radio network (16) and a telecommunication network (17).

7. The apparatus as claimed in claim 1, wherein the preprocessing means (VV) extracts spectral components from the digitized speech.

8. A method of recording speech for subsequent generation of a text using a speech-processing system, said method comprising:

digitizing an input analog speech;

preprocessing the digitized analog speech by extracting spectral component characteristics from the digitized analog speech for subsequent generation of a text by means of speech recognition processing;

storing the digitized, preprocessed analog speech in a digital memory;

transmitting the digitized, preprocessed analog speech from the digital memory to a remote text generator (12) by means of a data link (11) via a communication network (14); and

converting the transmitted speech into text by means of a speech-processing system that includes a speech recognition processing program.

9. The method as claimed in claim 8, further comprising:

encoding and storing the digitized analog speech in parallel with the preprocessing and storing steps; and

after the conversion of the digitized, preprocessed speech into the text, then decoding the encoded speech;

converting the encoded digitized speech into the input analog speech; and

correcting the text by comparing the text generated by the speech processing system with the input analog speech.

10. The method according to claim 9, wherein the preprocessing step extracts spectral component characteristics from the digitized speech.