Filtering sensitive topic speech within a conference audio stream
A portion of an audio stream representing speech of a conference participant is filtered based on a determination that the portion of the audio stream corresponds to a predefined sensitive topic. An audio stream representing speech of a user of a participant device connected to a conference is obtained. First hash values are determined for portions of the speech. A determination is made, by comparing the first hash values against second hash values for records of a data store, that a portion of the speech corresponds to a predefined sensitive topic indicated within the records. A filter is applied against the portion of the speech to produce a modified audio stream within which the predefined sensitive topic is sanitized. An output, within the conference, of the modified audio stream is then caused in place of the audio stream.
1. A method, comprising:
obtaining an audio stream representing speech of a user of a participant device connected to a conference;
determining first hash values for portions of the speech;
determining, by comparing the first hash values against second hash values for records of a data store, that a portion of the speech corresponds to a predefined sensitive topic indicated within the records;
applying a filter against the portion of the speech to produce a modified audio stream within which the predefined sensitive topic is sanitized; and
causing an output, within the conference, of the modified audio stream in place of the audio stream.
2. The method of claim 1 , wherein portions of the speech other than the portion of the speech remain unfiltered within the modified audio stream.
3. The method of claim 1 , wherein the records of the data store are populated by an entity having a domain with which a conference user account used at the participant device is associated.
4. The method of claim 1 , wherein each record of the data store indicates a different predefined sensitive topic, and wherein a record of the data store is removed from the data store upon a public disclosure of an associated predefined sensitive topic.
5. The method of claim 1 , wherein the predefined sensitive topic relates to confidential information.
6. The method of claim 1 , wherein the application of the filter causes an omission of the portion of the speech from within the modified audio stream.
7. The method of claim 1 , wherein the application of the filter causes an obfuscation of the portion of the speech from within the modified audio stream.
8. The method of claim 1 , wherein the application of the filter causes a replacement of the portion of the speech from within the modified audio stream with other audible content.
9. A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:
obtaining an audio stream representing speech of a user of a participant device connected to a conference;
determining first hash values for portions of the speech;
determining, by comparing the first hash values against second hash values for records of a data store, that a portion of the speech corresponds to a predefined sensitive topic indicated within the records;
applying a filter against the portion of the speech to produce a modified audio stream within which the predefined sensitive topic is sanitized; and
causing an output, within the conference, of the modified audio stream in place of the audio stream.
10. The non-transitory computer readable medium of claim 9 , wherein the operations for causing the output of the modified audio stream in place of the audio stream comprise:
causing the modified audio stream to be output at one or more participant devices connected to the conference based on conference user accounts used at the one or more participant devices corresponding other than to a domain associated with a conference user account used at the participant device from which the audio stream is obtained.
11. The non-transitory computer readable medium of claim 9 , wherein the operations for causing the output of the modified audio stream in place of the audio stream comprise:
transmitting the modified audio stream to one or more participant devices connected to the conference to cause the modified audio stream to be output at the one or more participant devices.
12. The non-transitory computer readable medium of claim 9 , wherein the predefined sensitive topic corresponds to a codename.
13. The non-transitory computer readable medium of claim 9 , wherein the conference is implemented by a unified communications as a service software platform.
14. An apparatus, comprising:
a memory; and
a processor configured to execute instructions stored in the memory to:
obtain an audio stream representing speech of a user of a participant device connected to a conference;
determine first hash values for portions of the speech;
determine, by comparing the first hash values against second hash values for records of a data store, that a portion of the speech corresponds to a predefined sensitive topic indicated within the records;
apply a filter against the portion of the speech to produce a modified audio stream within which the predefined sensitive topic is sanitized; and
cause an output, within the conference, of the modified audio stream in place of the audio stream.
15. The apparatus of claim 14 , wherein the processor is configured to execute the instructions to:
determine to compare the first hash values against the second hash values based on a mismatch between a first domain associated with a first conference user account used at the participant device and a second domain associated with a second conference user account used at another participant device connected to the conference.
16. The apparatus of claim 14 , wherein the processor is configured to execute the instructions to:
determine to apply the filter against the portion of the speech based on a mismatch between a first domain associated with a first conference user account used at the participant device and a second domain associated with a second conference user account used at another participant device connected to the conference.
17. The apparatus of claim 14 , wherein the modified audio stream is output to a first subset of participant devices connected to the conference and the audio stream is output to a second subset of the participant devices, wherein conference user accounts used at the first subset of the participant devices are associated with a first domain different from a second domain with which a conference user account used at the participant device is associated with, and wherein conference user accounts used at the second subset of the participant devices are associated with the second domain.
18. The apparatus of claim 14 , wherein a control policy restricts users of participant devices connected to the conference from altering the records of the data store.
19. The apparatus of claim 14 , wherein the modified audio stream is produced and output while the conference remains ongoing.
20. The apparatus of claim 14 , wherein the modified audio stream is produced and output during playback of a recording of the conference.