Integrating keyword spotting with graph decoder to improve the robustness of speech recognition

1. A system, comprising:

a graph-decoder based speech recognition mechanism for recognizing a word sequence, from input speech data, based on a language model using a graph decoder, the graph-decoder based speech recognition mechanism having a recognition acceptance mechanism to determine whether the graph decoder based speech recognition mechanism fails; and

a keyword based speech recognition mechanism for recognizing, when the graph-decoder based speech recognition mechanism fails, the word sequence, the keyword based speech recognition mechanism including:

a keyword spotting mechanism to detect, using at least one acoustic model, at least one keyword from the input speech data based on a keyword list; and

a keyword based recognition mechanism to recognize the word sequence using the at least one keyword, detected by the keyword spotting mechanism, based on the language model.

2. The system according to claim 1 , wherein the graph decoder based speech recognition mechanism comprises:

a graph decoder for recognizing the word sequence from the input speech data based on at least one acoustic feature to generate a recognition result, the recognizing being performed according to the at least one acoustic model and the language model; and

the recognition acceptance mechanism for determining whether to accept the recognition result generated by the graph decoder based speech recognition mechanism or to activate, when the recognition result from the graph decoder based recognition mechanism is not accepted, the keyword based speech recognition mechanism.

3. The system according to claim 1 , further comprising an acoustic feature extractor to extract the at least one acoustic feature from the input speech data.

4. The system according to claim 2 , wherein the keyword spotting mechanism is activated by the recognition acceptance mechanism if the recognition result from the graph decoder based recognition mechanism is not accepted.

5. A method, comprising:

recognizing, by a graph decoder, a word sequence from input speech data based on at least one acoustic features, the recognizing being performed using at least one acoustic model and a language model;

determining, by a recognition acceptance mechanism, whether to accept the word sequence or to activate a keyword spotting mechanism;

detecting, by the keyword spotting mechanism when activated, at least one keyword, according to a keyword list, from the input speech data based on the at least one acoustic model; and

recognizing, by a keyword based recognition mechanism, the word sequence using the at least one keyword based on the language model.

6. The method according to claim 5 , further comprising:

receiving the input speech data; and

extracting, by an acoustic feature extractor, the at least one acoustic feature from the input speech data.

7. A computer-readable medium encoded with a program, the program, when executed, causing:

recognizing, by a graph decoder, a word sequence from input speech data based on at least one acoustic features, the recognizing being performed using at least one acoustic model and a language model;

determining, by a recognition acceptance mechanism, whether to accept the word sequence or to activate a keyword spotting mechanism;

detecting, by the keyword spotting mechanism when activated, at least one keyword, according to a keyword list, from the input speech data based on the at least. one acoustic model; and

recognizing, by a keyword based recognition mechanism, the word sequence using the at least one keyword based on the language model. model.

8. The medium according to claim 7 , the program, when executed, further causing:

receiving the input speech data; and

extracting, by an acoustic feature extractor, the at least one acoustic feature from the input speech data.