Text-to-speech conversion with associated mood tag

• US 20050144002A1
• Filed: 12/09/2004
• Published: 06/30/2005
• Est. Priority Date: 12/09/2003
• Status: Abandoned Application

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: PS, Janardhanan
• Application Number:
  US11/008,406
• Publication Number:
  US 20050144002A1
• Time in Patent Office: Days
• US Class Current: 704/266
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A method (and associated apparatus) comprises associating a mood tag with text. The mood tag specifies a mood to be applied when the text is subsequently converted to an audio signal. In accordance with another embodiment, a method (and associated apparatus) comprises receiving text having an associated mood tag and converting the text to speech in accordance with the associated mood tag.

Claims

1. A method, comprising:

associating a mood tag with text, wherein said mood tag specifies a mood to be applied when said text is subsequently converted to an audio signal.

2. The method of claim 1 wherein associating a mood tag comprises using a mood tag that corresponds to a mood selected from a group consisting of interrogation, contradiction, assertion, nervous, shy, happy, frustrated, threaten, regret, surprise, love, virtue, sorrow, laugh, fear, disgust, anger, and peace.

3. The method of claim 1 further comprising associating a plurality of mood tags with text in a document.

4. The method of claim 1 further comprising associating a plurality of mood tags with text in a document, the plurality of mood tags not all corresponding to the same moods.

5. The method of claim 4 wherein the moods are selected from a group consisting of interrogation, contradiction, assertion, nervous, shy, happy, frustrated, threaten, regret, surprise, love, virtue, sorrow, laugh, fear, disgust, anger, and peace.

6. The method of claim 1 further comprising converting said text to audio in accordance with the mood tag.

24. The system of claim 2 wherein the means for converting text to a speech signal is also for configuring a prosodic parameter to be applied to said text.

7. A method, comprising:

receiving text having an associated mood tag; and

converting said text to speech in accordance with said associated mood tag.

8. The method of claim 7 wherein the mood tag is associated with a mood selected from a group consisting of interrogation, contradiction, assertion, nervous, shy, happy, frustrated, threaten, regret, surprise, love, virtue, sorrow, laugh, fear, disgust, anger, and peace.

9. The method of claim 7 comprising converting different portions of said text to speech in accordance with a mood tag associated with each portion.

10. The method of claim 9 wherein the mood tag associated with each portion differs from at least one other mood value.

11. The method of claim 7 wherein converting said text to speech in accordance with the mood tag comprises configuring one or more parameters associated with a speech synthesizer.

12. The method of claim 11 wherein configuring a parameter comprises configuring an parameter selected from a group consisting of pitch, pitch range, rate, and volume.

13. The method of claim 7 wherein converting said text to speech in accordance with the mood tag comprises configuring a plurality of parameters associated with a speech synthesizer.

14. The method of claim 7 wherein converting said text to speech in accordance with the mood value comprises applying a set of rules for modifying prosody.

15. The method of claim 14 wherein applying a set of rules for modifying prosody comprises applying a set of rules for modifying a prosodic parameter selected from a group consisting of pitch, pitch range, rate, and volume.

16. A system, comprising:

a document server;

a mood translator coupled to the document server; and

a text-to-speech (TTS) converter coupled to the mood translator, wherein said TTS converter converts text to a speech signal;

wherein a mood tag is embedded in the voice user interface document and said mood translator passes stored prosodic parameters to the TTS converter which produces speech signal as specified by the mood tag.

17. The system of claim 16 wherein the TTS converter provides the speech signal to be heard via a telephone.

18. The system of claim 16 wherein the mood specified by the mood tag is selected from a group consisting of interrogation, contradiction, assertion, nervous, shy, happy, frustrated, threaten, regret, surprise, love, virtue, sorrow, laugh, fear, disgust, anger, and peace.

19. The system of claim 16 wherein the TTS converter configures one or more prosodic parameters to produce the speech signal as specified by the mood tag.

20. The system of claim 16 wherein the TTS converter configures at least one of pitch, pitch range, rate, and volume to produce the speech signal as specified by the mood tag.

21. The system of claim 16 wherein the TTS converter implements a plurality of prosodic parameters in accordance with converting the text to the speech signal, and said TTS converter configures the prosodic parameters to implement the mood specified by the mood tag.

22. A system, comprising:

means for converting text to a speech signal in accordance with a mood tag embedded in the text, said mood tag specifying a mood;

means for producing sound based on the speech signal;

23. The system of claim 22 wherein the mood specified by the mood tag is selected from a group consisting of interrogation, contradiction, assertion, nervous, shy, happy, frustrated, threaten, regret, surprise, love, virtue, sorrow, laugh, fear, disgust, anger, and peace.

25. A mood translation module, comprising

a CPU;

software running on the CPU that causes the CPU to modify a prosodic parameter to generate a speech signal in accordance with a mood specified for a text segment.

26. The mood translation module of claim 25 wherein the mood is selected from the group consisting of interrogation, contradiction, assertion, nervous, shy, happy, frustrated, threaten, regret, surprise, love, virtue, sorrow, laugh, fear, disgust, anger, and peace.