# US 2018/0322863 A1 · Cepstral variance normalization for audio feature extraction

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

- Number: US 2018/0322863 A1
- Document ID: US20180322863A1
- Status: Published application
- Kind: A1
- Application number: 15/528,068
- Filed: 2014-12-22
- Published: 2018-11-08
- Earliest claimed: 2014-12-22
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: TOBIAS BOCKLET; ADAM MAREK
- Web page: https://patentgrep.com/patent/US20180322863A1

## CPC

- G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit
- G10L 15/20: Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence)
- G10L 17/02: Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
- G10L 17/20: Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions
- G10L 19/008: Multichannel audio signal coding or decoding using interchannel correlation to reduce redundancy, e.g. joint-stereo, intensity-coding or matrixing
- G10L 25/24: the extracted parameters being the cepstrum
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Cepstral variance normalization is described for audio feature extraction. In some embodiments a method includes receiving a sequence of frames of digitized audio from a microphone, determining a feature vector for a first frame of the sequence of frames, the feature vector being determined using an initial mean and an initial variance, updating the initial mean to a current mean using the determined feature vector for the first frame, updating the variance to a current variance using the current mean and the determined feature vector for the first frame, determining a next feature vector for each of subsequent frames of the sequence of frames, after determining a next feature vector for each subsequent frame, updating the current mean to a next current mean and updating the current variance to a next current variance and wherein determining a feature vector for a subsequent frame comprises using the next current mean and the next current variance, and sending the determined feature vectors to a recognition stage of an audio processing pipeline.

## Claims

### Claim 1

A method comprising:
receiving a sequence of frames of digitized audio from a microphone;
determining a feature vector for a first frame of the sequence of frames, the feature vector being determined using an initial mean and an initial variance;
updating the initial mean to a current mean using the determined feature vector for the first frame;
updating the variance to a current variance using the current mean and the determined feature vector for the first frame;
determining a next feature vector for each of subsequent frames of the sequence of frames;
after determining a next feature vector for each subsequent frame, updating the current mean to a next current mean and updating the current variance to a next current variance and wherein determining a feature vector for a subsequent frame comprises using the next current mean and the next current variance; and
sending the determined feature vectors to a recognition stage of an audio processing pipeline.

### Claim 2 (depends on 1)

The method of claim 1, further comprising setting the initial mean and variance to estimated values for the digitized audio.

### Claim 3 (depends on 1, 2)

The method of claim 1 or 2, wherein the initial mean and variance are set based on the feature vector determined for the first frame.

### Claim 4

The method of any one or more of the above claims, wherein determining a feature vector comprises determining a mel-frequency cepstral coefficient.

### Claim 5 (depends on 4)

The method of claim 4, wherein the current mean comprises a cepstral mean and the current variance comprises a cepstral variance.

### Claim 6 (depends on 5)

The method of claim 5, wherein determining a next feature vector comprises determining a next feature vector using cepstral mean substraction and cepstral variance normalization.

### Claim 7

The method of any one or more of the above claims, wherein the digitized audio is speech.

### Claim 8

The method of any one or more of the above claims, wherein the recognition stage comprises a decoder, the method further comprising receiving the determined feature vectors at the decoder and determining at the decoder whether the digitized speech matches an authenticated user.

### Claim 9

The method of any one or more of the above claims, wherein the next current mean is determined after each next feature vector using only the corresponding next feature vector and feature vectors of earlier frames of the sequence of frames.

### Claim 10 (depends on 9)

The method of claim 9, wherein the next current variance is determined after each next feature vector using only the corresponding next current mean.

### Claim 11

A machine-readable medium having instructions thereon that, when executed by the machine, cause the machine to perform operations comprising:
receiving a sequence of frames of digitized audio from a microphone;
determining a feature vector for a first frame of the sequence of frames, the feature vector being determined using an initial mean and an initial variance;
updating the initial mean to a current mean using the determined feature vector for the first frame;
updating the variance to a current variance using the current mean and the determined feature vector for the first frame;
determining a next feature vector for each of subsequent frames of the sequence of frames;
after determining a next feature vector for each subsequent frame, updating the current mean to a next current mean and updating the current variance to a next current variance and wherein determining a feature vector for a subsequent frame comprises using the next current mean and the next current variance; and
sending the determined feature vectors to a recognition stage of an audio processing pipeline.

### Claim 12 (depends on 11)

The medium of claim 11, wherein determining a feature vector comprises determining a mel-frequency cepstral coefficient.

### Claim 13 (depends on 12)

The medium of claim 12, wherein the current mean comprises a cepstral mean and the current variance comprises a cepstral variance.

### Claim 14 (depends on 13)

The medium of claim 13, wherein determining a next feature vector comprises determining a next feature vector using cepstral mean substraction and cepstral variance normalization.

### Claim 15 (depends on 11, 12, 13, 14)

The medium of any one or more of claims 11-14, wherein the next current mean is determined after each next feature vector using only the corresponding next feature vector and feature vectors of earlier frames of the sequence of frames.

### Claim 16 (depends on 15)

The medium of claim 15, wherein the next current variance is determined after each next feature vector using only the corresponding next current mean.

### Claim 17

An apparatus comprising:
a feature extractor to receive a sequence of frames of digitized audio from a microphone through an analog to digital converter, to determine a feature vector for a first frame of the sequence of frames, the feature vector being determined using an initial mean and an initial variance, to update the initial mean to a current mean using the determined feature vector for the first frame, to update the variance to a current variance using the current mean and the determined feature vector for the first frame, to determine a next feature vector for each of subsequent frames of the sequence of frames, to update the current mean to a next current mean and update the current variance to a next current variance after determining a next feature vector for each subsequent frame, wherein determining a feature vector for a subsequent frame comprises using the next current mean and the next current variance; and
a recognition stage to recognize the extracted feature vectors.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the digitized audio is speech.

### Claim 19 (depends on 17, 18)

The apparatus of claim 17 or 18, wherein the recognition stage comprises a decoder, the decoder receiving the determined feature vectors and determining whether the digitized speech matches an authenticated user.

### Claim 20 (depends on 17, 18)

The apparatus of claim 17, 18, or 19, wherein the next current mean is determined after each next feature vector using only the corresponding next feature vector and feature vectors of earlier frames of the sequence of frames.

### Claim 21

An apparatus comprising:
means for receiving a sequence of frames of digitized audio from a microphone;
means for determining a feature vector for a first frame of the sequence of frames, the feature vector being determined using an initial mean and an initial variance;
means for updating the initial mean to a current mean using the determined feature vector for the first frame;
means for updating the variance to a current variance using the current mean and the determined feature vector for the first frame;
means for determining a next feature vector for each of subsequent frames of the sequence of frames, for updating the current mean to a next current mean and updating the current variance to a next current variance after determining a next feature vector for each subsequent frame and wherein determining a feature vector for a subsequent frame comprises using the next current mean and the next current variance; and
means for sending the determined feature vectors to a recognition stage of an audio processing pipeline.

### Claim 22 (depends on 21)

The apparatus of claim 21, wherein the initial mean and variance are set based on the feature vector determined for the first frame.

### Claim 23 (depends on 21, 22)

The apparatus of claim 21 or 22, wherein determining a feature vector comprises determining a mel-frequency cepstral coefficient.

### Claim 24 (depends on 23)

The apparatus of claim 23, wherein the current mean comprises a cepstral mean and the current variance comprises a cepstral variance.

### Claim 25 (depends on 24)

The apparatus of claim 24, wherein determining a next feature vector comprises determining a next feature vector using cepstral mean substraction and cepstral variance normalization.

### Claim 26 (depends on 21, 22, 23, 24, 25)

The apparatus of any one or more of claims 21-25, wherein the recognition stage comprises means for decoding, the means for decoding determining whether the digitized speech matches an authenticated user.