Personalized voice playback for screen reader

• US 20060031073A1
• Filed: 08/05/2004
• Published: 02/09/2006
• Est. Priority Date: 08/05/2004
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Anglin, Debbie Ann, Kline, Nyralin Novella, Anglin, Howard Neil
• Granted Patent: US 7,865,365 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A method, system, and computer program product is disclosed for customizing a synthesized voice based upon audible input voice data. The input voice data is typically in the form of one or more predetermined paragraphs being read into a voice recorder. The input voice data is then analyzed for adjustable voice characteristics to determine basic voice qualities (e.g., pitch, breathiness, tone, speed; variability of any of these qualities, etc.) and to identify any “specialized speech patterns”. Based upon this analysis, the characteristics of the voice utilized to read text appearing on the screen are modified to resemble the input voice data. This allows a user of the system to easily and automatically create a voice that is familiar to the user.

Claims

1. A method for automatically customizing an output voice used with a text-reading system, comprising:

creating one or more speech samples using an input voice;

analyzing each of said speech samples to identify sound parameters associated with personal speech characteristics of said input voice;

creating a customized output voice emulating said input voice by adjusting sound parameters of said customized output voice to match said identified sound parameters of said personal speech characteristics of said input voice; and

using said customized output voice with said text-reading system.

2. The method of claim 1, wherein said sound parameters identified by said analysis step include sound parameters related to at least one of the following:

pitch, tone, speed, volume.

3. The method of claim 1, wherein the step of creating one or more speech samples using an input voice includes eliciting specialized voice characteristics of said input voice, and wherein said analysis step includes identifying sound parameters associated with said specialized voice characteristics of said input voice.

4. The method of claim 3, wherein said text-reading system analyzes a portion of text to be read by said text-reading system to determine if said portion of text contains one or more triggers associated with one or more specialized speech characteristics;

and

if any of said one or more triggers are detected, utilizing the specialized voice characteristic with said output voice when said text-reading system reads said portion of text.

5. A system for automatically customizing an output voice used with a text-reading system, comprising:

means for creating one or more speech samples using an input voice;

means for analyzing each of said speech samples to identify sound parameters associated with personal speech characteristics of said input voice;

means for creating a customized output voice emulating said input voice by adjusting sound parameters of said customized output voice to match said identified sound parameters of said personal speech characteristics of said input voice; and

means for using said customized output voice with said text-reading system.

6. The system of claim 5, wherein said sound parameters identified by said analysis means include sound parameters related to at least one of the following:

pitch, tone, speed, volume.

7. The system of claim 5, wherein said means for creating one or more speech samples using an input voice includes means for eliciting specialized voice characteristics of said input voice, and wherein said analysis means includes means for identifying sound parameters associated with said specialized voice characteristics of said input voice.

8. The system of claim 7, wherein said text-reading system includes means for analyzing a portion of text to be read by said text-reading system to determine if said portion of text contains one or more triggers associated with one or more specialized speech characteristics;

and

if any of said one or more triggers are detected, utilizing the specialized voice characteristic with said output voice when said text-reading system reads said portion of text.

9. A computer program product for automatically customizing an output voice used with a text-reading system, the computer program product comprising a computer-readable storage medium having computer-readable program code embodied in the medium, the computer-readable program code comprising:

computer-readable program code that creates one or more speech samples using an input voice;

computer-readable program code that analyzes each of said speech samples to identify sound parameters associated with personal speech characteristics of said input voice;

computer-readable program code that creates a customized output voice emulating said input voice by adjusting sound parameters of said customized output voice to match said identified sound parameters of said personal speech characteristics of said input voice; and

computer-readable program code that uses said customized output voice with said text-reading system.

10. The computer program product of claim 9, wherein said identified sound parameters include sound parameters related to at least one of the following:

pitch, tone, speed, volume.

11. The computer program product of claim 9, wherein said computer-readable program code creating one or more speech samples using an input voice includes eliciting specialized voice characteristics of said input voice, and wherein said analysis step includes identifying sound parameters associated with said specialized voice characteristics of said input voice.

12. The computer program product of claim 11, wherein said text-reading system analyzes a portion of text to be read by said text-reading system to determine if said portion of text contains one or more triggers associated with one or more specialized speech characteristics;

and

if any of said one or more triggers are detected, utilizing the specialized voice characteristic with said output voice when said text-reading system reads said portion of text.