Adapting an utterance cut-off period based on parse prefix detection

1. A method comprising:

detecting periods of voice activity and periods of no voice activity within a plurality of spoken words;

parsing the plurality of spoken words according to a first grammar and a second grammar determining whether the plurality of spoken words is a complete parse according to the first grammar and a prefix to another complete parse according to the second grammar;

accessing a no voice activity detection (NVAD) cut-off period calculated from prior speech; and

scaling the NVAD cut-off period, which prevents pre-mature cutting off slow voice activity and improves responsiveness to fast voice activity, based at least in part on determining whether the plurality of spoken words is a complete parse according to the first grammar and a prefix to another complete parse according to the second grammar.

2. The method of claim 1 , wherein parsing the plurality of spoken words according to a first grammar and a second grammar comprises producing a prefix hypothesis numerical score indicating a likelihood that the plurality of spoken words is both: (a) the complete parse and (b) the prefix to another complete parse and wherein scaling the NVAD cut-off period comprises scaling the NVAD cut-off period in accordance with the prefix hypothesis numerical score.

3. The method of claim 2 , wherein producing the prefix hypothesis numerical score comprises analyzing natural grammar rules determining that the plurality of spoken words is a complete parse prefix.

4. The method of claim 3 , wherein analyzing natural grammar rules comprises aggregating grammar rules from the first grammar and the second grammar.

5. The method of claim 2 , wherein scaling the NVAD cut-off period is based on the plurality of spoken words being a complete parse prefix.

6. The method of claim 1 , wherein detecting periods of voice activity and periods of no voice activity within the plurality of spoken words comprises detecting inter-word pause lengths.

7. The method of claim 1 , further comprising:

computing an average phoneme rate from the periods of voice activity and the periods of no voice activity within the plurality of spoken words; and

scaling the NVAD cut-off period based on the average phoneme rate.

8. A system comprising:

a processor; and

system memory coupled to the processor and storing instructions configured to cause the processor to:

detect periods of voice activity and periods of no voice activity within a plurality of spoken words;

parse the plurality of spoken words according to a first grammar and a second grammar determining whether the plurality of spoken words is a complete parse according to the first grammar and a prefix to another complete parse according to the second grammar;

access a no voice activity detection (NVAD) cut-off period calculated from prior speech; and

scale the NVAD cut-off period, which prevents pre-mature cutting off slow voice activity and improves responsiveness to fast voice activity, based at least in part on determining whether the plurality of spoken words is a complete parse according to the first grammar and a prefix to another complete parse according to the second grammar.

9. The system of claim 8 , wherein instructions configured to parse the plurality of spoken words according to a first grammar and a second grammar comprise instructions configured to produce a prefix hypothesis numerical score indicating a likelihood that the plurality of spoken words is both: (a) the complete parse and (b) the prefix to another complete parse, and wherein instructions configured to scale the NVAD cut-off period is in accordance with the prefix hypothesis numerical score.

10. The system of claim 9 , wherein instructions configured to produce the prefix hypothesis numerical score comprise instructions configured to analyze natural grammar rules determining that the plurality of spoken words is a complete parse prefix.

11. The system of claim 10 , wherein instructions configured to analyze natural grammar rules comprise instructions configured to aggregate grammar rules from the first grammar and the second grammar.

12. The system of claim 9 , wherein instructions configured to scale the NVAD cut-off period comprise instructions configured to scale the NVAD cut-off period based on the plurality of spoken words being a complete parse prefix.

13. The system of claim 8 , wherein instructions configured to detect periods of voice activity and periods of no voice activity within the plurality of spoken words comprise instructions configured to detect inter-word pause lengths.

14. The system of claim 8 , further comprising instructions configured to:

compute an average phoneme rate from the periods of voice activity and the periods of no voice activity within the plurality of spoken words; and

scale the NVAD cut-off period based on the average phoneme rate.

15. A method for adjusting a no voice activity detection (NVAD) cut-off period of an interface device that detects a plurality of spoken words and voice activities, the method comprising:

detecting periods of voice activity and periods of no voice activity within the plurality of spoken words;

parsing the plurality of spoken words according to a first grammar and a second grammar to determine if the plurality of spoken words is a complete parse according to the first grammar and a prefix to another complete parse according to the second grammar;

accessing the NVAD cut-off period calculated from a prior voice activity; and

generating a new NVAD cut-off period, which prevents cut-off of slow voice activity and improves response time to fast voice activity, by scaling the NVAD cut-off period based at least in part on determining if the plurality of spoken words is a complete parse according to the first grammar and a prefix to another complete parse according to the second grammar.