Speech system barge-in control

• US 20020184031A1
• Filed: 05/31/2002
• Published: 12/05/2002
• Est. Priority Date: 06/04/2001
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett Packard Company (HP Inc.)
• Inventors: Tucker, Roger Cecil Ferry, Brittan, Paul St John
• Granted Patent: US 7,062,440 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A speech system has a speech input channel including a speech recognizer, and a speech output channel including a text-to-speech converter. Associated with the input channel is a barge-in control for setting barge-in behavior parameters determining how the apparatus handles barge-in by a user during speech output by the apparatus. In order to make the barge-in control more responsive to the actual speech output from the output channel, a barge-in prediction arrangement is provided that is responsive to feature values produced during the operation of the text-to-speech converter to produce indications as to the most likely barge-in points. The barge-in control is responsive to these indications to adjust at least one of the barge-in behavior parameters for periods corresponding to the most likely barge-in points.

Claims

1. Speech apparatus comprising:

a speech input channel including a speech recogniser;

a speech output channel including a text-to-speech converter;

a barge-in control for setting barge-in behaviour parameters determining how the apparatus handles barge-in by a user during speech output by the apparatus; and

a barge-in prediction arrangement responsive to operation of the text-to-speech converter to produce indications as to the most likely barge-in points;

the barge-in control being responsive to the said indications to adjust at least one said barge-in behaviour parameter for periods corresponding to the most likely barge-in points.

2. Apparatus according to claim 1, wherein the barge-in prediction arrangement is operative to assess the overall quality of the speech form produced by the text-to-speech converter from an input text-form utterance whereby to produce said indication at points in the utterance where the current speech form is inadequate.

3. Apparatus according to claim 2, wherein the text-to-speech converter is arranged to generate, in the course of converting a text-form utterance into speech form, values of predetermined features that are indicative of the overall quality of the speech form of the utterance, the barge-in prediction arrangement comprising:

a classifier responsive to the feature values generated by the text-to-speech converter to provide a confidence measure of the speech form of the utterance concerned; and

a comparator for comparing confidence measures produced by the classifier against one or more stored threshold values, in order to determine when a said indication is to be produced.

4. Apparatus according to claim 2, wherein the text-to-speech converter includes a concatenative speech generator which in generating a speech-form utterance, produces an accumulated unit selection cost in respect of the speech units used to make up the speech-form utterance;

the barge-in prediction arrangement comprising a comparator for comparing the selection cost produced by the speech generator against one or more stored threshold values, in order to determine when a said indication is to be produced.

5. Apparatus according to claim 1, wherein the barge-in prediction arrangement is operative to monitor a specific parameter of a current utterance being processed by the text-to-speech converter in order to determine when a said indication is to be produced.

6. Apparatus according to claim 5, wherein said specific parameter is a set of intonation contours for the utterance.

7. Apparatus according to claim 1, wherein the text-to-speech converter is responsive to the generation of a said indication to insert a pause in a corresponding location in the speech-form output of the current utterance.

8. A method of controlling barge-in in speech apparatus that has both a speech input channel including a speech recogniser and a speech output channel including a text-to-speech converter;

the method comprising the steps of;

(a) monitoring operation of the text-to-speech converter to produce indications as to the most likely barge-in points; and

(b) adjusting, for periods corresponding to the most likely barge-in points as indicated by said indications, at least one barge-in behaviour parameter that determines how the apparatus handles barge-in by a user during speech output by the apparatus.

9. A method according to claim 8, wherein step (a) involves assessing the overall quality of the speech form produced by the text-to-speech converter from an input text-form utterance whereby to produce said indication at points in the utterance where the current speech form is inadequate.

10. A method according to claim 9, wherein the text-to-speech converter generates, in the course of converting a text-form utterance into speech form, values of predetermined features that are indicative of the overall quality of the speech form of the utterance, step (a) involving:

using a classifier responsive to the feature values generated by the text-to-speech converter to provide a confidence measure of the speech form of the utterance concerned; and

comparing said confidence measures against one or more stored threshold values, in order to determine when a said indication is to be produced.

11. A method according to claim 9, wherein the text-to-speech converter includes a concatenative speech generator which in generating a speech-form utterance, produces an accumulated unit selection cost in respect of the speech units used to make up the speech-form utterance;

step (a) involving comparing the selection cost produced by the speech generator against one or more stored threshold values, in order to determine when a said indication is to be produced.

12. A method according to claim 8, wherein step (a) involves monitoring a specific parameter of a current utterance being processed by the text-to-speech converter in order to determine when a said indication is to be produced.

13. A method according to claim 12, wherein said specific parameter is a set of intonation contours for the utterance.

14. A method according to claim 8, comprising the further step of inserting, in response to the generation of a said indication, a pause in a corresponding location in the speech-form output of the current utterance.

15. A method of controlling barge-in in speech apparatus that has both a speech input channel and a speech output channel;

the method comprising the steps of;

(a) assessing the overall quality of the speech form output by the speech output channel to determine when the current speech form is inadequate; and

(b)adjusting, for periods corresponding to when the speech form output by the speech output channel is determined to be inadequate, how the speech input channel handles barge-in by a user.