# US 2019/0096424 A1 · System and method for cluster-based audio event detection

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

- Number: US 2019/0096424 A1
- Document ID: US20190096424A1
- Status: Published application
- Kind: A1
- Application number: 16/200,283
- Filed: 2018-11-26
- Published: 2019-03-28
- Earliest claimed: 2016-06-28
- Assignees: Pindrop Security, Inc.
- Applicants: Pindrop Security, Inc.
- Inventors: Elie KHOURY; Matthew GARLAND
- Web page: https://patentgrep.com/patent/US20190096424A1

## CPC

- G10L 25/45: characterised by the type of analysis window
- G10L 25/27: characterised by the analysis technique
- G10L 25/51: for comparison or discrimination
- 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)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Methods, systems, and apparatuses for audio event detection, where the determination of a type of sound data is made at the cluster level rather than at the frame level. The techniques provided are thus more robust to the local behavior of features of an audio signal or audio recording. The audio event detection is performed by using Gaussian mixture models (GMMs) to classify each cluster or by extracting an i-vector from each cluster. Each cluster may be classified based on an i-vector classification using a support vector machine or probabilistic linear discriminant analysis. The audio event detection significantly reduces potential smoothing error and avoids any dependency on accurate window-size tuning. Segmentation may be performed using a generalized likelihood ratio and a Bayesian information criterion, and the segments may be clustered using hierarchical agglomerative clustering. Audio frames may be clustered using K-means and GMMs.

## Claims

### Claim 1

A computer-implemented method for audio event detection, comprising:
partitioning, by a computer, an audio signal into a plurality of audio frames;
clustering, by the computer, the plurality of audio frames into a plurality of clusters containing audio frames having similar features; and
detecting, by the computer utilizing a supervised classifier, an audio event in at least one cluster of the plurality of clusters.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the computer utilizes K-means to partition the audio signal into the plurality of audio frames.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the computer utilizes at least one Gaussian mixture model to cluster the plurality of audio frames to the plurality of clusters.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
extracting, by the computer, an i-vector for the at least one cluster; and
detecting, by the computer, the audio event in the at least one cluster based upon the extracted i-vector.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the supervised classifier utilizes probabilistic linear discriminant analysis.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the supervised classifier utilizes a support vector machine.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the supervised classifier utilizes a Gaussian mixture model.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, further comprising:
generating, by the computer, a plurality of segments from the audio signal using generalized likelihood ratio and Bayesian information criterion.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, further comprising:
detecting, by the computer, a set of candidates for segment boundaries utilizing the general likelihood ratio; and
filtering out, by the computer, at least one of the candidates utilizing the Bayesian information criterion.

### Claim 10 (depends on 8)

The computer-implemented method of claim 8, further comprising:
clustering, by the computer, the plurality of segments utilizing hierarchical agglomerative clustering.

### Claim 11

A system comprising:
a non-transitory storage medium storing a plurality of computer program instructions;
a processor electrically coupled to the non-transitory storage medium and configured to execute the plurality of computer program instructions to:
partition an audio signal into a plurality of audio frames;
cluster the plurality of audio frames into a plurality of clusters containing audio frames having similar features; and
detect utilizing a supervised classifier, an audio event in at least one cluster of the plurality of clusters.

### Claim 12 (depends on 11)

The system of claim 11, wherein the computer utilizes K-means to partition the audio signal into the plurality of audio frames.

### Claim 13 (depends on 11)

The system of claim 11, wherein the computer utilizes at least one Gaussian mixture model to cluster the plurality of audio frames to the plurality of clusters.

### Claim 14 (depends on 11)

The system of claim 11, wherein the processor is configured to further execute the plurality of computer program instructions to:
extract an i-vector for the at least one cluster; and
detect the audio event in the at least one cluster based upon the extracted i-vector.

### Claim 15 (depends on 11)

The system of claim 11, wherein the supervised classifier utilizes probabilistic linear discriminant analysis.

### Claim 16 (depends on 11)

The system of claim 11, wherein the supervised classifier utilizes a support vector machine.

### Claim 17 (depends on 11)

The system of claim 11, wherein the supervised classifier utilizes a Gaussian mixture model.

### Claim 18 (depends on 11)

The system of claim 11, wherein the processor is configured to further execute the plurality of computer program instructions to:
generate a plurality of segments from the audio signal using generalized likelihood ratio and Bayesian information criterion.

### Claim 19 (depends on 18)

The system of claim 18, wherein the processor is configured to further execute the plurality of computer program instructions to:
detect a set of candidates for segment boundaries utilizing the general likelihood ratio; and
filter out at least one of the candidates utilizing the Bayesian information criterion.

### Claim 20 (depends on 18)

The system of claim 18, wherein the processor is configured to further execute the plurality of computer program instructions to:
cluster the plurality of segments utilizing hierarchical agglomerative clustering.
