Dynamic model selection in speech-to-text processing

A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, the computer-program product including instructions operable to cause at least one processor to perform operations comprising:

• receive, from a requesting device via a network, a request to perform operations comprising speech-to-text conversion of a specified speech data set representing speech audio;
• and
• in response to the request, the at least one processor is caused to perform speech-to-text processing operations comprising:
• use an acoustic model to generate a first set of probabilities of speech sounds uttered within a portion of the speech audio;
• derive at least a first candidate word most likely spoken in the speech audio using the first set of probabilities;
• analyze the first set of probabilities to derive a degree of uncertainty of the first set of probabilities;
• compare the degree of uncertainty to a threshold degree of uncertainty;
• in response to at least the degree of uncertainty being less than the threshold degree of uncertainty, the at least one processor is caused to select the first candidate word as a next word most likely spoken in the speech audio;
• in response to at least the degree of uncertainty being greater than the threshold degree of uncertainty, the at least one processor is caused to select, as the next word most likely spoken in the speech audio, a second candidate word that is indicated as being most likely spoken based on a second set of probabilities generated by a language model;
• and
• add the next word most likely spoken to a transcript of the speech audio.

A computer-implemented method comprising:

• receiving, by at least one processor, and from a requesting device via a network, a request to perform operations comprising speech-to-text conversion of a specified speech data set representing speech audio;
• and
• the method comprises, in response to the request, performing speech-to-text processing operations comprising:
• using, by the at least one processor, an acoustic model to generate a first set of probabilities of speech sounds uttered within a portion of the speech audio;
• deriving, by the at least one processor, at least a first candidate word most likely spoken in the speech audio using the first set of probabilities;
• analyzing, by the at least one processor, the first set of probabilities to derive a degree of uncertainty of the first set of probabilities;
• comparing, by the at least one processor, the degree of uncertainty to a threshold degree of uncertainty;
• in response to at least the degree of uncertainty being less than the threshold degree of uncertainty, selecting, by the at least one processor, the first candidate word as a next word most likely spoken in the speech audio;
• in response to at least the degree of uncertainty being greater than the threshold degree of uncertainty, selecting, by the at least one processor, as the next word most likely spoken in the speech audio, a second candidate word that is indicated as being most likely spoken based on a second set of probabilities generated by a language model;
• and
• adding the next word most likely spoken to a transcript of the speech audio.