# US 2012/0232890 A1 · Apparatus and method for discriminating speech, and computer readable medium

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

- Number: US 2012/0232890 A1
- Document ID: US20120232890A1
- Status: Published application
- Kind: A1
- Application number: 13/232,469
- Filed: 2011-09-14
- Published: 2012-09-13
- Earliest claimed: 2011-03-11
- Assignees: Kabushiki Kaisha Toshiba
- Inventors: Kaoru Suzuki; Masaru Sakai; Yusuke Kida
- Web page: https://patentgrep.com/patent/US20120232890A1

## CPC

- 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 25/18: the extracted parameters being spectral information of each sub-band
- G10L 2021/02082: {the noise being echo, reverberation of the speech}
- H04M 9/082: {using echo cancellers (echo cancellers per se H04B3/23)}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

According to one embodiment, an apparatus for discriminating speech/non-speech of a first acoustic signal includes a weight assignment unit, a feature extraction unit, and a speech/non-speech discrimination unit. The first acoustic signal includes a user's speech and a reproduced sound. The reproduced sound is a system sound having a plurality of channels reproduced from a plurality of speakers. The weight assignment unit is configured to assign a weight to each frequency band based on the system sound. The feature extraction unit is configured to extract a feature from a second acoustic signal based on the weight of each frequency band. The second acoustic signal is the first acoustic signal in which the reproduced sound is suppressed. The speech/non-speech discrimination unit is configured to discriminate speech/non-speech of the first acoustic signal based on the feature.

## Claims

### Claim 1

An apparatus for discriminating speech/non-speech of a first acoustic signal including a user's speech and a reproduced sound, the reproduced sound being a system sound having a plurality of channels reproduced from a plurality of speakers, comprising:
a weight assignment unit configured to assign a weight to each frequency band based on the system sound;
a feature extraction unit configured to extract a feature from a second acoustic signal based on the weight of each frequency band, the second acoustic signal being the first acoustic signal in which the reproduced sound is suppressed; and
a speech/non-speech discrimination unit configured to discriminate speech/non-speech of the first acoustic signal based on the feature.

### Claim 2 (depends on 1)

The apparatus according to claim 1, further comprising:
an echo canceller configured to generate the second acoustic signal by suppressing the reproduced sound included in the first acoustic signal;
wherein the feature extraction unit extracts the feature from the second acoustic signal generated by the echo canceller.

### Claim 3 (depends on 1)

The apparatus according to claim 1, further comprising:
a monophonization unit configured to generate a third acoustic signal by monophonizing the system sound;
wherein the weight assignment unit assigns the weight to each frequency band based on the third acoustic signal.

### Claim 4 (depends on 3)

The apparatus according to claim 3, wherein
the weight assignment unit assigns a predetermined weight to a frequency band in which a frequency spectrum of the third acoustic signal is larger than a first threshold, and
the feature extraction unit extracts the feature by excluding frequency spectrums of the frequency band to which the predetermined weight is assigned.

### Claim 5 (depends on 3)

The apparatus according to claim 3, wherein
the weight assignment unit assigns a predetermined weight to a frequency band in which a frequency spectrum of the third acoustic signal is larger than a first threshold and a frequency spectrum of the second acoustic signal is smaller than a second threshold, and
the feature extraction unit extracts the feature by excluding frequency spectrums of the frequency band to which the predetermined weight is assigned.

### Claim 6 (depends on 3)

The apparatus according to claim 3, wherein
the weight assignment unit assigns a weight to each frequency band so that the weight is smaller when a frequency spectrum of the third acoustic signal is larger, and
the feature extraction unit makes a degree which a frequency spectrum of a frequency band contributes to the feature be smaller when the weight assigned to the frequency band is smaller.

### Claim 7 (depends on 1)

The apparatus according to claim 1, wherein
the weight assignment unit assigns the weight to each frequency band, based on a frequency spectrum of each channel composing the system sound.

### Claim 8 (depends on 7)

The apparatus according to claim 7, wherein
the weight assignment unit assigns a predetermined weight to a frequency band in which a frequency spectrum of one of the plurality of channels is larger than a first threshold and a frequency spectrum of the second acoustic signal is smaller than a second threshold, and
the feature extraction unit extracts the feature by excluding frequency spectrums of the frequency band to which the predetermined weight is assigned.

### Claim 9

A method for discriminating speech/non-speech of a first acoustic signal including a user's speech and a reproduced sound, the reproduced sound being a system sound having a plurality of channels reproduced from a plurality of speakers, comprising:
assigning a weight to each frequency band based on the system sound;
extracting a feature from a second acoustic signal based on the weight of each frequency band, the second acoustic signal being the first acoustic signal in which the reproduced sound is suppressed; and
discriminating speech/non-speech of the first acoustic signal based on the feature.

### Claim 10

A computer readable medium for causing a computer to perform a method for discriminating speech/non-speech of a first acoustic signal including a user's speech and a reproduced sound, the reproduced sound being a system sound having a plurality of channels reproduced from a plurality of speakers, the method comprising:
assigning a weight to each frequency band based on the system sound;
extracting a feature from a second acoustic signal based on the weight of each frequency band, the second acoustic signal being the first acoustic signal in which the reproduced sound is suppressed; and
discriminating speech/non-speech of the first acoustic signal based on the feature.
