Browse Prior Art Database

A DEVICE AND METHOD FOR RESTORING OPTIMALLY CONFIGURED AUDIO SETTINGS

IP.com Disclosure Number: IPCOM000014499D
Original Publication Date: 2001-Feb-01
Included in the Prior Art Database: 2003-Jun-19
Document File: 1 page(s) / 50K

Publishing Venue

IBM

Abstract

Disclosed is an algorithm that will restore audio settings for a speech recognition application to provide an optimal audio environment. This algorithm takes pre-determined audio settings and saves them in a database to allow the user to have good speech recognition at their next speech recognition session without the overhead of setting the gain through a gain-setting program. In a typical embodiment the algorithm would work as follows: (1) When a speech recognition application was started it would open a database with an unique identifier for the user (their user id). (2) Stored in their user id database would be a field that tracked the last optimal gain setting for their system. If this field was filled in, the application would go to step 3. Otherwise it would go to step 2a.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 72% of the total text.

Page 1 of 1

  A DEVICE AND METHOD FOR RESTORING OPTIMALLY CONFIGURED AUDIO SETTINGS

  Disclosed is an algorithm that will restore audio settings for a speech recognition application to provide an optimal audio environment. This algorithm takes pre-determined audio settings and saves them in a database to allow the user to have good speech recognition at their next speech recognition session without the overhead of setting the gain through a gain-setting program.

In a typical embodiment the algorithm would work as follows:

(1) When a speech recognition application was started it would open a database with an unique identifier for the user (their user id).
(2) Stored in their user id database would be a field that tracked the last optimal gain setting for their system. If this field was filled in, the application would go to step 3. Otherwise it would go to step 2a.
(2a) If a value was not saved in the gain field of the user id, then the application would launch a gain-setting application that would adjust the gain of the audio subsystem to compensate for the user's speaking volume and the gain characteristics of the audio subsystem.
(2b) Once an optimal gain level was discovered, the audio subsystem would be set to this level.
(2c) This optimal gain level would be saved in the user's userid file in the gain field.
(3) When a speech application was launched the stored value would be read from the user id gain field.
(4) The stored value in the gain field would be compared with the curre...