Custom display post processing in speech recognition

A system comprising:

• a processor;
• and
• a computer-readable medium storing instructions that are operative upon execution by the processor to:
• receive, by a customized multi-stage display post processing (DPP) pipeline, a first stream of tokens, each token representing an element of human speech in a lexical form;
• for a first transformation stage of the DPP pipeline, receive the first stream of tokens, by a first upstream filter, a first base model stage, and a first downstream filter and:
• transform, by the first transformation stage of the DPP pipeline, a first aspect of the first stream of tokens from lexical form into display form;
• and
• alter, by the first upstream filter, the first downstream filter, or both, the first stream of tokens;
• receive, by a second transformation stage of the DPP pipeline, from the first transformation stage, the first stream of tokens;
• transform, by the second transformation stage of the DPP pipeline, a second aspect of the first stream of tokens from lexical form into display form;
• output a final text representing the transformed first stream of tokens;
• and
• provide a user interface that enables a user to at least one of accept, edit, or upload
• a rule, for at least one of the first upstream filter or the first downstream filter.

A computerized method comprising:

• receiving, by a customized multi-stage display post processing (DPP) pipeline, a first stream of tokens, each token representing an element of human speech in a lexical form;
• for a first transformation stage of the DPP pipeline, receiving the first stream of tokens, by a first upstream filter, a first base model stage, and a first downstream filter and:
• transforming, by the first transformation stage, a first aspect of the first stream of tokens from lexical form into display form;
• and
• altering, by the first upstream filter, the first downstream filter, or both, the first stream of tokens;
• receiving, by a second transformation stage of the DPP pipeline, from the first transformation stage, the first stream of tokens;
• transforming, by the second transformation stage of the DPP pipeline, a second aspect of the first stream of tokens from lexical form into display form;
• outputting a final text representing the transformed first stream of tokens;
• and
• providing a user interface that enables a user to at least one of accept, edit, or upload a rule, for at least one of the first upstream filter or the first downstream filter.

One or more computer storage media having computer-executable instructions stored thereon, which, on execution by a computer, cause the computer to perform operations comprising:

• receiving, by a customized multi-stage display post processing (DPP) pipeline, a first stream of tokens, each token representing an element of human speech in a lexical form;
• for a first transformation stage of the DPP pipeline, receiving the first stream of tokens, by a first upstream filter, a first transformation stage, and a first downstream filter and:
• transforming, by the first transformation stage, a first aspect of the first stream of tokens from lexical form into display form;
• and
• altering, by the first upstream filter, the first downstream filter, or both, the first stream of tokens;
• receiving, by a second transformation stage of the DPP pipeline, from the first transformation stage, the first stream of tokens;
• transforming, by the second transformation stage of the DPP pipeline, a second aspect of the first stream of tokens from lexical form into display form;
• outputting a final text representing the transformed first stream of tokens;
• and
• providing a user interface that enables a user to at least one of accept, edit, or upload a rule, for at least one of the first upstream filter or the first downstream filter.