Filtering spurious voicemail messages

• US 8,229,092 B2
• Filed: 06/01/2006
• Issued: 07/24/2012
• Est. Priority Date: 06/01/2006
• Status: Active Grant

• Current Assignee: Audiocodes Limited
• Original Assignee: Audiocodes Limited
• Inventors: Richardson, Eitan
• Primary Examiner(s): Elahee, Md S
• Assistant Examiner(s): BEZUAYEHU, SOLOMON G
• Application Number:
  US11/421,753
• Publication Number:
  US 20070280432A1
• Time in Patent Office: 2,245 Days
• Field of Search: 379/80, 379/88.01, 379/88.16, 379/88.18, 379/88.26, 379/406.03, 455/413
• US Class Current: 379/88.23
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2203/303 Marking
• CPC Class Codes: H04M 3/436 Arrangements for screening incoming calls , i.e. evaluating the characteristics of a call before deciding whether to answer it based on the calling party profile H04M3/42059; based on location H04M3/42348; based on presence H04M3/42365; diversion H04M3/54
• CPC Class Codes: H04M 3/53333 Message receiving aspects

Abstract

A method is provided for discarding an audio message if the audio message meets a predefined discarding condition, which may factor in at least the audio message'"'"'s total length, presence of spoken word(s) in the audio message, presence of tone(s) in the audio message and the presence of click(s) in the audio message. An audio message may be discarded if no spoken words are detected in it and the audio message'"'"'s total length is shorter than a predefined minimal message length, or it contains a tone and the audio message'"'"'s total length minus the tone'"'"'s length is shorter than the predefined minimal message length, or it contains a click sound and the audio message'"'"'s total length minus the click'"'"'s length is shorter than the predefined minimal message length. An audio message may be first stored in a memory buffer and then moved to a legitimate messages pool memory or to a spurious messages pool memory. A messages discriminator and a voicemail system that utilize the messages discrimination method are also provided.

Claims

1. A messages discriminator, comprising:

a controller to determine whether or not an audio message meets a predefined discarding condition;

a legitimate messages pool memory, and

a non-legitimate messages pool memory,

wherein, if the controller determines that the audio message meets the predefined discarding condition, then the controller is to assign a first binary value to a binary flag associated with said audio message to indicate that the audio message is non-legitimate;

wherein, if the controller determines that the audio message does not meet the predefined discarding condition, then the controller is to assign a second binary value to the binary flag associated with said audio message to indicate that the audio message is legitimate;

wherein said predefined discarding condition is defined to be met if no spoken words are detected in said audio message and at least one of the following conditions is met;

a total length of the audio message is shorter than a predefined minimal message length, or said audio message contains a tone, and the total length of the audio message minus a length of the tone is shorter than said predefined minimal message length, or said audio message contains a click sound, and the total length of the audio message minus a length of the click sound is shorter than said predefined minimal message length;

wherein the controller is to discriminate among legitimate and non-legitimate audio messages exclusively based on their original non-translated version as recorded, and without taking into account any translation of said audio messages;

wherein the controller is to determine whether the audio message is either legitimate or non-legitimate based exclusively on an analysis of audio content of the audio message, independently of an identity of a sender of the audio message, independently of audio data of one or more other received audio messages, and without relying on preset information indicated by a recipient of the audio message;

wherein said controller is to store said audio message in said legitimate messages pool memory if said binary flag contains said second binary value

wherein said controller is to store said audio message in said non-legitimate messages pool memory if said binary flag contains said first binary value,

wherein the non-legitimate messages pool memory is to store non-legitimate messages, which are discarded by said controller autonomously without user intervention and are not-yet-deleted by a user.

2. The messages discriminator according to claim 1, wherein the predefined discarding condition takes into account at least:

a total length of the audio message;

presence of one or more spoken words in said audio message;

presence of one or more tones in said audio message; and

presence of one or more clicks in said audio message.

3. The messages discriminator according to claim 1, wherein the controller is to render accessible to a user both messages stored in the legitimate messages pool memory and messages stored in the non-legitimate messages pool memory, by using two distinct access codes.

4. The messages discriminator according to claim 1, further comprising:

a buffer memory for storing an incoming audio message,

wherein the controller is to move said audio message from said buffer memory to the legitimate messages pool memory or to the non-legitimate messages pool memory, based on a determination whether or not the incoming audio message meets the predefined discarding condition.

5. A voicemail system, comprising:

a messages discriminator to selectively discard one or more audio messages,

the message discriminator comprising;

a controller to determine whether or not an audio message meets a predefined discarding condition;

a legitimate messages pool memory, and

a non-legitimate messages pool memory,

wherein, if the controller determines that the audio message meets the predefined discarding condition, then the controller is to assign a first binary value to a binary flag associated with said audio message to indicate that the audio message is non-legitimate;

wherein, if the controller determines that the audio message does not meet the predefined discarding condition, then the controller is to assign a second binary value to the binary flag associated with said audio message to indicate that the audio message is legitimate;

wherein said predefined discarding condition is defined to be met if no spoken words are detected in said audio message and at least one of the following conditions is met;

a total length of the audio message is shorter than a predefined minimal message length, or said audio message contains a tone, and the total length of the audio message minus a length of the tone is shorter than said predefined minimal message length, or said audio message contains a click sound, and the total length of the audio message minus a length of the click sound is shorter than said predefined minimal message length;

wherein the controller is to discriminate among legitimate and non-legitimate audio messages exclusively based on their original non-translated version as recorded, and without taking into account any translation of said audio messages;

wherein the controller is to determine whether the audio message is either legitimate or non-legitimate based exclusively on an analysis of audio content of the audio message, independently of an identity of a sender of the audio message, independently of audio data of one or more other received audio messages, and without relying on preset information indicated by a recipient of the audio message;

wherein said controller is to store said audio message in said legitimate messages pool memory if said binary flag contains said second binary value

wherein said controller is to store said audio message in said non-legitimate messages pool memory is said binary flag contains said first binary value,

wherein the non-legitimate messages pool memory is to store non-legitimate messages, which are discarded by said controller autonomously without user intervention and are not-yet-deleted by a user.

6. The voicemail system according to claim 5, wherein the predefined discarding condition takes into account at least:

a total length of the audio message;

presence of one or more spoken words in said audio message;

presence of one or more tones in said audio message; and

presence of one or more clicks in said audio message.

7. The voicemail system according to claim 5, wherein the controller is to render accessible to a user both messages stored in the legitimate messages pool memory and messages stored in the non-legitimate messages pool memory, by using two distinct access codes.

8. The voicemail system according to claim 5, further comprising:

a buffer memory for storing an incoming audio message,

wherein the controller is to move said audio message from said buffer memory to the legitimate messages pool memory or to the non-legitimate messages pool memory, based on a determination whether or not the incoming audio message meets the predefined discarding condition.

9. A method of handling audio messages, the method comprising:

determining whether or not an audio message meets a predefined discarding condition;

if said audio message does not meet the predefined discarding condition, storing said audio message in a legitimate messages pool memory;

if said audio message meets said predefined discarding condition, storing said audio message in a non-legitimate messages pool memory,

wherein, if it is determined that the audio message meets the predefined discarding condition, then the method comprises assigning a first binary value to a binary flag associated with said audio message to indicate that the audio message is non-legitimate;

wherein, if it is determined that the audio message does not meet the predefined discarding condition, then the method comprises assigning a second binary value to the binary flag associated with said audio message to indicate that the audio message is legitimate;

wherein said predefined discarding condition is defined to be met if no spoken words are detected in said audio message and at least one of the following conditions is met;

a total length of the audio message is shorter than a predefined minimal message length, or said audio message contains a tone, and the total length of the audio message minus a length of the tone is shorter than said predefined minimal message length, or said audio message contains a click sound, and the total length of the audio message minus a length of the click sound is shorter than said predefined minimal message length;

wherein the method comprises discriminating among legitimate and non-legitimate audio messages exclusively based on their original non-translated version as recorded, and without taking into account any translation of said audio messages;

wherein the method comprises determining whether the audio message is either legitimate or non-legitimate based exclusively on an analysis of audio content of the audio message, independently of an identity of a sender of the audio message, independently of audio data of one or more other received audio messages, and without relying on preset information indicated by a recipient of the audio message;

wherein the method comprises storing said audio message in said legitimate messages pool memory if said binary flag contains said second binary value;

wherein the method comprises storing said audio message in said non-legitimate messages pool memory if said binary flag contains said first binary value;

wherein storing the audio message in the non-legitimate messages pool memory comprises storing an audio message which is autonomously discarded by a controller without user intervention and is not-yet-deleted by a user,

wherein the method is to be performed by a voice messaging system comprising said controller.

10. The method according to claim 9, wherein the predefined discarding condition takes into account at least:

a total length of the audio message;

presence of one or more spoken words in said audio message;

presence of one or more tones in said audio message; and

presence of one or more clicks in said audio message.

11. The method according to claim 9, comprising:

rendering accessible to a user messages stored in the legitimate messages pool memory and messages stored in the non-legitimate messages pool memory, using two distinct access codes.

12. The method according to 9, comprising:

storing the audio message in a memory buffer; and

moving the audio message to the legitimate messages pool memory or to the non-legitimate messages pool memory, based on a determination whether or not the audio message meets the predefined discarding condition.