Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,519 questions
Azure AI Speech content filter
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(220.8, 3%, 31%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJ%3C/text%3E%3C/svg%3E)
Julian
0
Reputation points
Hey everyone,
I am using the Azure AI Speech api for real time transcription of conversations. The problem I am facing is that the content filter recognizes words such as the german 'dick' as offensive. This might be true in english, however in german this is a totally normal word that should not be marked. The language is also set to german, which is why I would expect that content filtering is language specific and does not filter out words that might be offensive in other languages. Is there a way to bypass this behavior and still show filtered words? This has happened on multiple occasions and could be a deal breaker for using the Azure AI speech in production as these words might give relevant context.
Thank you for your help.
Best, Julian
{count} votes
-
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(153.6, 24%, 24%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ENM%3C/text%3E%3C/svg%3E)
navba-MSFT 19,735 Reputation points Microsoft Employee2024-07-05T05:51:37.7766667+00:00 @Julian Welcome to Microsoft Q&A Forum, Thank you for posting your query here!
.
Firstly, how are you using the Azure Speech AI service ? is it through REST API / Speech SDK ? Speech Studio ?
If you are using the Speech SDK, you can leverage
Profanity filter.Using this you can specify whether to mask, remove, or show profanity in the final transcribed text. Masking replaces profane words with asterisk (*) characters so that you can keep the original sentiment of your text while making it more appropriate for certain situations.The profanity filter options are:
-
Masked: Replaces letters in profane words with asterisk (*) characters. Masked is the default option. -
Raw: Include the profane words verbatim. -
Removed: Removes profane words.
Example:
speechConfig.SetProfanity(ProfanityOption.Raw);Please note, Microsoft also reserves the right to mask or remove any word that is deemed inappropriate. Such words will not be returned by the Speech service, whether or not you enabled profanity filtering.
.
Hope this helps. If you have any follow-up questions, please let me know. I would be happy to help.
-
-
Deleted
This comment has been deleted due to a violation of our Code of Conduct. The comment was manually reported or identified through automated detection before action was taken. Please refer to our Code of Conduct for more information.
Sign in to comment
1 answer
Sort by: Most helpful
-
Deleted
This answer has been deleted due to a violation of our Code of Conduct. The answer was manually reported or identified through automated detection before action was taken. Please refer to our Code of Conduct for more information.
Comments have been turned off. Learn more