# US 2012/0250830 A1 · Conference signal anomaly detection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0250830 A1
- Document ID: US20120250830A1
- Status: Published application
- Kind: A1
- Application number: 13/075,130
- Filed: 2011-03-29
- Published: 2012-10-04
- Earliest claimed: 2011-03-29
- Assignees: Microsoft Corporation
- Inventors: Warren M. Lam; Hosam A. Khalil; Vinod Prakash; Sang K. Choe; Hong Wang Sodoma
- Web page: https://patentgrep.com/patent/US20120250830A1

## CPC

- H04M 3/56: Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities (video conference systems H04N7/15)
- H04M 3/2227: {Quality of service monitoring}
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

Detecting at least one of an echo detector and a noise detector based on analysis of audio streams transmitted to and received from each endpoint of a conference. When certain characteristics of the respective audio streams for a given endpoint are classified as significant against certain criteria, a determination is made as to whether that endpoint is a source of echo and/or noise. Subsequent actions are taken to alert users and/or prevent broadcast of impaired signals.

## Claims

### Claim 1

A method for detecting an anomaly in a teleconference communication signal, the method comprising:
receiving, at a computing device, a first signal comprising audio generated by a first endpoint of a plurality of endpoints connected to a teleconference;
receiving a second signal comprising a summation of audio generated by each of the plurality of endpoints other than the first endpoint;
generating a first data sequence comprising a number of zero-crossings per unit time of the first signal;
generating a second data sequence comprising a number of zero-crossings per unit time of the second signal;
calculating an inner product between the first and second data sequences;
comparing a maximum value of the inner product to a first threshold value; and
sending an alert notifying at least one of the plurality of endpoints that the first endpoint is a source of echo upon the maximum value of the inner product exceeding the first threshold value.

### Claim 2 (depends on 1)

The method of claim 1, wherein the inner product is defined by a cross-correlation function:
c
Xmit
,
Recv

[
n
]
=
∑
k
=
0
K
-
1

ZCR
Xmit

[
k
]

ZCR
Recv

[
n
+
k
]
.

### Claim 3 (depends on 2)

The method of claim 2, further comprising normalizing the cross-correlation function to bound the inner product between −1 and 1.

### Claim 4 (depends on 2)

The method of claim 2, further comprising calculating the inner product over a finite integer value n corresponding to a plurality of time delayed versions of the first and second data sequences.

### Claim 5 (depends on 1)

The method of claim 1, further comprising pre-processing the first and second signal prior to generating the first and second data sequence.

### Claim 6 (depends on 5)

The method of claim 5, further comprising level shifting the first and second signal to zero DC voltage offset.

### Claim 7 (depends on 5)

The method of claim 5, further comprising sampling at least one of the first and second signals to a common sample rate.

### Claim 8 (depends on 5)

The method of claim 5, further comprising one of: decoding the first signal to a non-network transmission format prior to generating the first data sequence; and generating the first data sequence directly from the first signal in a network transmission format.

### Claim 9 (depends on 1)

The method of claim 1, further comprising encoding the second signal to a network transmission format and transferring the second signal to each of the plurality of teleconference endpoints.

### Claim 10 (depends on 1)

The method of claim 1, further comprising generating a third data sequence comprising an RMS noise value of the first signal per unit time.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
estimating a noise power of the first signal based on the third data sequence;
comparing the noise power to a second threshold value; and
sending a noise alert notifying at least one of the plurality of endpoints that the first endpoint is a source of noise upon the noise power exceeding the second threshold value.

### Claim 12

A computing device, comprising:
a processing unit; and
a system memory connected to the processing unit, the system memory including instructions that, when executed by the processing unit, cause the processing unit to implement a detection module configured to detect an anomaly in a communication signal of a teleconference, wherein the detection module comprises:
a first module configured to implement signal processing of a first signal comprising audio generated by a first endpoint of a plurality of endpoints connected to the teleconference and a second signal comprising a summation of audio generated by each of the plurality of endpoints other than the first endpoint, wherein the signal processing includes level shifting the first and second signal to zero DC voltage offset and sampling at least one of the first and second signal to a common sample rate;
a second module configured to generate a first data sequence comprising a number of zero-crossings per unit time of the first signal and generate a second data sequence comprising a number zero-crossings per unit time of the second signal; and
a correlation module configured to calculate an inner product between the first and second data sequences, compare a maximum value of the inner product to a threshold value, and notify at least one of the plurality of endpoints that the first endpoint is a source of echo upon the maximum value exceeding the threshold value.

### Claim 13 (depends on 12)

The computing device of claim 12, wherein the inner product is defined by a cross-correlation function:
c
Xmit
,
Recv

[
n
]
=
∑
k
=
0
K
-
1

ZCR
Xmit

[
k
]

ZCR
Recv

[
n
+
k
]
.

### Claim 14 (depends on 13)

The computing device of claim 13, wherein the cross-correlation function is normalized bounding the inner product between −1 and 1.

### Claim 15 (depends on 13)

The computing device of claim 13, wherein the correlation module is configured to calculate the inner product over a finite integer value n corresponding to a plurality of time delayed versions of the first and second data sequences.

### Claim 16 (depends on 12)

The computing device of claim 12, wherein the first module is further configured to receive an endpoint-specific signal comprising audio generated by a second endpoint of the plurality of endpoints; the second module is further configured to generate an endpoint-specific sequence comprising a number of zero-crossings per unit time of the endpoint-specific signal; and the correlation module is further configured to calculate a second inner product between the endpoint-specific and second data sequences and compare a maximum value of the calculated second inner product to the threshold value.

### Claim 17 (depends on 16)

The computing device of claim 16, wherein the correlation module is further configured to notify at least one of the plurality of endpoints that the second endpoint is a source of echo upon the maximum value of the calculated second inner product exceeding the threshold value.

### Claim 18 (depends on 12)

The computing device of claim 12, further comprising a third module configured to generate a third data sequence comprising an RMS noise value of the first signal per unit time.

### Claim 19 (depends on 18)

The computing device of claim 18, wherein the third module is further configured to estimate a noise power based on the third data sequence, compare the noise power to a second threshold value, and send a noise alert notifying at least one of the plurality of endpoints that the first endpoint is a source of noise upon the noise power exceeding the second threshold value.

### Claim 20

A computer readable storage medium having computer-executable instructions that, when executed by a computing device, cause the computing device to perform steps comprising:
receiving a first signal comprising audio generated by a first endpoint of a plurality of endpoints connected to a teleconference;
receiving a second signal comprising a summation of audio generated by each of the plurality of endpoints other than the first endpoint;
processing the first and second signal comprising level shifting the first and second signal to zero DC voltage offset and sampling at least one of the first and second signal to a common sample rate;
generating a first data sequence comprising a number of zero-crossings per unit time of the first signal;
generating a second data sequence comprising a number of zero-crossings per unit time of the second signal; generating a third data sequence comprising an RMS noise value of the first signal per unit time;
calculating an inner product between the first and second data sequences over a finite integer value n corresponding to a plurality of time delayed versions of the first and second data sequences, wherein the inner product is defined by a normalized cross-correlation function bound between −1 and 1:
c
Xmit
,
Recv

[
n
]
=
∑
k
=
0
K
-
1

ZCR
Xmit

[
k
]

ZCR
Recv

[
n
+
k
]
;
comparing a maximum value of the inner product to a threshold value;
notifying at least one of the plurality of endpoints that the first endpoint is a source of echo upon the maximum value exceeding the threshold value;
estimating a noise power based on the third data sequence;
comparing the noise power to a second threshold value; and
sending a noise alert notifying at least one of the plurality of endpoints that the first endpoint is a source of noise upon the noise power exceeding the second threshold value.
