Compensating for ambient noise levels in text-to-speech applications

• US 20040193422A1
• Filed: 03/25/2003
• Published: 09/30/2004
• Est. Priority Date: 03/25/2003
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Fado, Francis, Guasti, Peter J.
• Granted Patent: US 6,988,068 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: H03G 3/32 the control being dependent upon ambient noise level or sound level

Abstract

A method of automatically adjusting volume of speech generated by a text-to-speech application can include measuring an ambient noise level of an audio environment. A target volume for speech output generated by a text-to-speech application can be calculated based in part upon the ambient noise level. A volume of speech generated by the text-to-speech application can be automatically adjusted responsive to the performed calculation.

Claims

1. A method of automatically adjusting volume of speech generated by a text-to-speech application comprising the steps of:

measuring an ambient noise level of an audio environment;

calculating a target volume for speech output generated by a text-to-speech application based in part upon said ambient noise level; and

,

automatically adjusting volume of speech generated by said text-to-speech application responsive to said calculating step.

2. The method of claim 1, wherein said adjusting step further comprising the step of:

adjusting an amplitude of a speech output via software configured to modify signals, wherein said software is a component of said text-to-speech application.

3. The method of claim 1, wherein said adjusting step adjusts an amplifier external to said text-to-speech application.

4. The method of claim 1, further comprising the steps of:

detecting a sound pressure level for played speech;

comparing said sound pressure level with a sound pressure level associated with said target volume; and

,

responsively adjusting said volume of speech generated by said text-to-speech application.

5. The method of claim 1, further comprising the step of:

limiting said target volume to a volume range.

6. The method of claim 1, wherein said calculating step further comprising the step of:

calculating said target volume based in part upon a signal-to-noise ratio value.

7. The method of claim 1, wherein said measuring step further comprising the step of:

receiving an input from a microphone configured to receive speech input for a voice recognition application.

8. The method of claim 1, further comprising the step of:

identifying output characteristics of at least one audio transducer that plays speech, wherein said calculating step utilizes said output characteristics.

9. The method of claim 8, wherein said at least one audio transducer comprises a plurality of audio transducers, said method further comprising the steps of:

selecting one of said plurality of audio transducers; and

adjusting said target volume based upon said output characteristics of said selected audio transducer.

10. A system for automatically adjusting a volume of speech generated by a text-to-speech application comprising:

a receiving transducer configured to detect an ambient noise level;

a text-to-speech application;

a calculation engine configured to calculate a target volume based in part upon said ambient noise level; and

,

an audio transducer configured to play speech generated by said text-to-speech application, wherein an output level of said speech is automatically adjusted based upon said target volume.

11. A machine-readable storage having stored thereon, a computer program having a plurality of code sections, said code sections executable by a machine for causing the machine to perform the steps of:

measuring an ambient noise level of an audio environment;

calculating a target volume for speech output generated by a text-to-speech application based in part upon said ambient noise level; and

,

automatically adjusting volume of speech generated by said text-to-speech application responsive to said calculating step.

12. The machine-readable storage of claim 11, wherein said adjusting step further comprising the step of:

adjusting an amplitude of a speech output via software configured to modify signals, wherein said software is a component of said text-to-speech application.

13. The machine-readable storage of claim 11, wherein said adjusting step adjusts an amplifier external to said text-to-speech application.

14. The machine-readable storage of claim 11, further comprising the steps of:

detecting a sound pressure level for played speech;

comparing said sound pressure level with a sound pressure level associated with said target volume; and

,

responsively adjusting said volume of speech generated by said text-to-speech application.

15. The machine-readable storage of claim 11, further comprising the step of:

limiting said target volume to a volume range.

16. The machine-readable storage of claim 11, wherein said calculating step further comprising the step of:

calculating said target volume based in part upon a signal-to-noise ratio value.

17. The machine-readable storage of claim 11, wherein said measuring step further comprising the step of:

receiving an input from a microphone configured to receive speech input for a voice recognition application.

18. The machine-readable storage of claim 11, further comprising the step of:

identifying output characteristics of at least one audio transducer that plays speech, wherein said calculating step utilizes said output characteristics.

19. The machine-readable storage of claim 18, wherein said at least one audio transducer comprises a plurality of audio transducers, said method further comprising the steps of:

selecting one of said plurality of audio transducers; and

adjusting said target volume based upon said output characteristics of the selected audio transducer.