Automated domain-specific constrained decoding from speech inputs to structured resources

1. A computer-implemented method comprising:

converting at least a portion of at least one user-provided speech utterance into text by processing the at least one user-provided speech utterance using an artificial intelligence-based automatic speech recognition model;

automatically training an artificial intelligence-based decoding engine, wherein automatically training the artificial intelligence-based decoding engine comprises constraining the artificial intelligence-based decoding engine based at least in part on a domain-specific model, one or more structured resources, and the artificial intelligence-based automatic speech recognition model, wherein the one or more structured resources comprise one or more web forms associated with the domain;

generating one or more domain-specific text outputs and automatically inserting at least a portion of the one or more domain-specific text outputs into at least one of the one or more web forms associated with the domain associated with the domain by processing at least a portion of the text using the artificial intelligence-based decoding engine; and

automatically performing one or more domain-specific actions within the one or more web forms associated with the domain by processing at least a portion of the text using the artificial intelligence-based decoding engine;

wherein the method is carried out by at least one computing device.

2. The computer-implemented method of claim 1 , further comprising:

automatically executing the one or more domain-specific action outputs.

3. The computer-implemented method of claim 2 , wherein automatically executing the one or more domain-specific action outputs comprises automatically selecting one or more radio buttons in connection with the one or more structured resources associated with the domain.

4. The computer-implemented method of claim 1 , wherein the artificial intelligence-based decoding engine comprises a set of one or more hierarchical long short-term memory decoders.

5. The computer-implemented method of claim 1 , wherein the artificial intelligence-based decoding engine comprises one or more combined attention mechanism and long short-term memory model (ATT-LSTM) components.

6. The computer-implemented method of claim 1 , wherein converting at least a portion of the at least one user-provided speech utterance into text comprises determining multiple phonetic variations of the user-provided speech utterance based at least in part on one or more phonemes by processing the at least one user-provided speech utterance using the artificial intelligence-based automatic speech recognition model.

7. The computer-implemented method of claim 1 , wherein the artificial intelligence-based automatic speech recognition model comprises a supervised encoder pertaining to speech representations.

8. The computer-implemented method of claim 1 , further comprising:

automatically training the domain-specific model using domain environment information.

9. The computer-implemented method of claim 1 , wherein the domain-specific model comprises at least one of a model pertaining to a specific language and a model pertaining to a specific topic.

10. The computer-implemented method of claim 1 , wherein the one or more web forms comprise one or more Hypertext Markup Language-based web forms.

11. The computer-implemented method of claim 1 , further comprising:

retraining the artificial intelligence-based decoding engine based at least in part on at least one of the one or more domain-specific text outputs and the one or more domain-specific action outputs.

12. The computer-implemented method of claim 1 , wherein software implementing the method is provided as a service in a cloud environment.

13. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

convert at least a portion of at least one user-provided speech utterance into text by processing the at least one user-provided speech utterance using an artificial intelligence-based automatic speech recognition model;

automatically train an artificial intelligence-based decoding engine, wherein automatically training the artificial intelligence-based decoding engine comprises constraining the artificial intelligence-based decoding engine based at least in part on a domain-specific model, one or more structured resources, and the artificial intelligence-based automatic speech recognition model, wherein the one or more structured resources comprise one or more web forms associated with the domain;

generate one or more domain-specific text outputs and automatically inserting at least a portion of the one or more domain-specific text outputs into at least one of the one or more web forms associated with the domain associated with the domain by processing at least a portion of the text using the artificial intelligence-based decoding engine; and

automatically perform one or more domain-specific actions within the one or more web forms associated with the domain by processing at least a portion of the text using the artificial intelligence-based decoding engine.

14. The computer program product of claim 13 , wherein the program instructions executable by a computing device to cause the computing device to:

automatically execute the one or more domain-specific action outputs.

15. The computer program product of claim 14 , wherein automatically executing the one or more domain-specific action outputs comprises automatically selecting one or more radio buttons in connection with the one or more structured resources associated with the domain.

16. A system comprising:

a memory configured to store program instructions; and

a processor operatively coupled to the memory to execute the program instructions to:

convert at least a portion of at least one user-provided speech utterance into text by processing the at least one user-provided speech utterance using an artificial intelligence-based automatic speech recognition model;

automatically train an artificial intelligence-based decoding engine, wherein automatically training the artificial intelligence-based decoding engine comprises constraining the artificial intelligence-based decoding engine based at least in part on a domain-specific model, one or more structured resources, and the artificial intelligence-based automatic speech recognition model, wherein the one or more structured resources comprise one or more web forms associated with the domain;

generate one or more domain-specific text outputs and automatically inserting at least a portion of the one or more domain-specific text outputs into at least one of the one or more web forms associated with the domain associated with the domain by processing at least a portion of the text using the artificial intelligence-based decoding engine; and

automatically perform one or more domain-specific actions within the one or more web forms associated with the domain by processing at least a portion of the text using the artificial intelligence-based decoding engine.

17. The system of claim 16 , wherein converting at least a portion of the at least one user-provided speech utterance into text comprises determining multiple phonetic variations of the user-provided speech utterance based at least in part on one or more phonemes by processing the at least one user-provided speech utterance using the artificial intelligence-based automatic speech recognition model.

18. The system of claim 16 , wherein the artificial intelligence-based decoding engine comprises a set of one or more hierarchical long short-term memory decoders.

19. The system of claim 16 , wherein the artificial intelligence-based decoding engine comprises one or more combined attention mechanism and long short-term memory model (ATT-LSTM) components.

20. The system of claim 16 , wherein the artificial intelligence-based automatic speech recognition model comprises a supervised encoder pertaining to speech representations.