Identifying a voicemail message as spam based on a similarity to a spam message
Voicemail spam detection is performed based on content of voicemail messages. The content of an incoming voicemail message is compared to a spam template that includes a representation of a spam voicemail. Spam templates may be generated based on spam indications provided by users for voicemail messages they have received. User indications for sufficiently similar voicemail messages may be aggregated by maintaining a vote count for a spam template that reflects how many times a user has indicated a matching voicemail message is spam. A spam template may also include an occurrence count that reflects how many times voicemail messages matching a spam template have been detected in a telephony system. An incoming voicemail message may be compared to spam templates and, responsive to a match of content and/or a corresponding vote count or occurrence count meeting a condition, the voicemail message may be identified as spam.
1 . A method, comprising: determining a cosine similarity between one or more word vectors representing a voicemail message and one or more word vectors of a spam message; and responsive to the cosine similarity between the voicemail message and the spam message exceeding a threshold, identifying the voicemail message as spam, wherein the spam message is an audio recording, and wherein the cosine similarity is determined based on a distance metric between the audio recording of the spam message and an audio recording of the voicemail message.
2 . The method of claim 1 , wherein the spam message includes a vote count that reflects a number of times that one or more users have indicated that a second voicemail message matching the spam message is spam.
3 . The method of claim 2 , comprising:
comparing the vote count of the spam message to a spam threshold; and
invoking a spam mitigation measure on the voicemail message when the vote count exceeds the spam threshold.
4 . The method of claim 1 , wherein the spam message further comprises an occurrence count reflecting a number of received voicemail messages that have been matched to the spam message, and further comprising:
comparing the occurrence count of the spam message to a second threshold, wherein the voicemail message is identified as spam responsive to the occurrence count exceeding the second threshold.
5 . The method of claim 1 , further comprising:
receiving an indication from a user that a second voicemail message is spam;
comparing the second voicemail message to the spam message; and
responsive to a match between the second voicemail message and the spam message, incrementing a vote count of the spam message.
6 . The method of claim 1 , further comprising:
blocking the voicemail message from entering a voicemail inbox of a user.
7 . The method of claim 1 , further comprising:
deleting the voicemail message.
8 . The method of claim 1 , further comprising:
displaying a message in a user interface indicating that the voicemail message is spam.
9 . A system, comprising: a processor, and a memory, wherein the memory stores instructions executable by the processor to: determine a cosine similarity between one or more word vectors representing a voicemail message and one or more word vectors of a spam message; and responsive to the cosine similarity between the voicemail message and the spam message exceeding a threshold, identify the voicemail message as spam, wherein the spam message is an audio recording, and wherein the cosine similarity is determined based on a distance metric between the audio recording of the spam message and an audio recording of the voicemail message.
10 . The system of claim 9 , wherein the spam message includes a vote count that reflects a number of times that one or more users have indicated that a second voicemail message matching the spam message is spam.
11 . The system of claim 10 , wherein the memory stores instructions executable by the processor to:
compare the vote count of the spam message to a spam threshold; and
invoke a spam mitigation measure on the voicemail message when the vote count exceeds the spam threshold.
12 . The system of claim 9 , wherein the spam message further comprises an occurrence count reflecting a number of received voicemail messages that have been matched to the spam message, and wherein the memory stores instructions executable by the processor to:
compare the occurrence count of the spam message to a second threshold, wherein the voicemail message is identified as spam responsive to the occurrence count exceeding the second threshold.
13 . The system of claim 9 , wherein the memory stores instructions executable by the processor to:
receive an indication from a user that a second voicemail message is spam;
compare the second voicemail message to the spam message; and
responsive to a match between the second voicemail message and the spam message, increment a vote count of the spam message.
14 . A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising: determining a cosine similarity between one or more word vectors representing a voicemail message and one or more word vectors of a spam message; and responsive to the cosine similarity between the voicemail message and the spam message exceeding a threshold, identifying the voicemail message as spam, wherein the spam message is an audio recording, and wherein the cosine similarity is determined based on a distance metric between the audio recording of the spam message and an audio recording of the voicemail message.
15 . The non-transitory computer-readable storage medium of claim 14 , wherein the spam message includes a vote count that reflects a number of times that one or more users have indicated that a second voicemail message matching the spam message is spam.
16 . The non-transitory computer-readable storage medium of claim 15 , wherein the operations further comprise:
comparing the vote count of the spam message to a spam threshold; and
invoking a spam mitigation measure on the voicemail message when the vote count exceeds the spam threshold.
17 . The non-transitory computer-readable storage medium of claim 14 , wherein the spam message further comprises an occurrence count reflecting a number of received voicemail messages that have been matched to the spam message, and wherein the operations further comprise:
comparing the occurrence count of the spam message to a second threshold, wherein the voicemail message is identified as spam responsive to the occurrence count exceeding the second threshold.