RecognizedPhrase Fields |
The RecognizedPhrase type exposes the following members.
Name | Description | |
---|---|---|
![]() | Confidence |
A value representing high, medium or low confidence.
|
![]() | DisplayText |
The recognized phrase with inverse text normalization, capitalization, punctuation and profanity masking applied.
Profanity is masked with asterisks after the initial character, e.g. "d***". This form is optimal for use by
applications that display the speech recognition results to a user.
Inverse Text Normalization (ITN) has also been applied. An example of ITN is converting result text from "go to fourth street"
to "go to 4th st".
This form is optimal for use by applications that display the speech recognition results to a user.
|
![]() | InverseTextNormalizationResult |
Inverse text normalization (ITN) converts phrases like "one two three four" to a normalized form such as "1234".
Another example is converting result text from "go to fourth street" to "go to 4th st".
This form is optimal for use by applications that interpret the speech recognition results as commands or
which perform queries based on the recognized text.
|
![]() | LexicalForm |
The recognized phrase, without any post-processing.
This form is optimal for use by applications that need the raw, unprocessed speech recognition result.
|
![]() | MaskedInverseTextNormalizationResult |
The recognized phrase with inverse text normalization and profanity masking applied, but not capitalization or punctuation.
Profanity is masked with asterisks after the initial character, e.g. "d***". This form is optimal for use by
applications that display the speech recognition results to a user.
Inverse Text Normalization (ITN) has also been applied. An example of ITN is converting result text from "go to fourth street"
to "go to 4th st".
This form is optimal for use by applications that use the unmasked ITN results but also need to display the command or query to the user.
|