Method and device for processing a sound signal

Patent metadata

Field	Value
Publication number	US-2016163335-A1
Application number	US-201514959580-A
Country	US
Kind code	A1
Filing date	Dec 4, 2015
Priority date	Dec 4, 2014
Publication date	Jun 9, 2016
Grant date	—

Abstract

A method of processing a sound signal is disclosed. The method of processing a sound signal includes receiving a sound signal from the outside of a device, converting the sound signal into a first frequency domain signal, determining whether or not the sound signal is a voice signal using the first frequency domain signal acquired through the conversion, converting the first frequency domain signal into a second frequency domain signal based on the determination, and recognizing the sound signal using the second frequency domain signal acquired through the conversion.

First claim

What is claimed is:

1 . A method of processing a sound signal, the method comprising:
receiving, by a device, a sound signal from an external source; converting the sound signal into a first frequency domain signal in a first frequency domain, and determining whether or not the sound signal is a voice signal using the first frequency domain signal; converting the first frequency domain signal into a second frequency domain signal in a second frequency domain based on a result of the determining; and analyzing the sound signal using the second frequency domain signal.

2 . The method of claim 1 , wherein the converting the first frequency domain signal into the second frequency domain signal based on the result of the determining comprises determining that the sound signal is a voice signal.

3 . The method of claim 1 , wherein the converting the first frequency domain signal into the second frequency domain signal based on the result of the determining comprises using at least one method selected from upsampling, downsampling, interpolation, mirroring, and phase shifting.

4 . The method of claim 1 , wherein the first frequency domain includes at least one selected from a discrete Fourier transform (DFT) domain, a discrete cosine transform (DCT) domain, a discrete sine transform (DST) domain, and a modified discrete cosine transform (MDCT) domain.

5 . The method of claim 1 , wherein the second frequency domain includes at least one selected from a discrete Fourier transform (DFT) domain, a discrete cosine transform (DCT) domain, a discrete sine transform (DST) domain, and a modified discrete cosine transform (MDCT) domain.

6 . The method of claim 1 , wherein the converting the first frequency domain signal into the second frequency domain signal based on the result of the determining comprises:
storing the first frequency domain signal in an internal memory included in the device; and converting the stored first frequency domain signal into the second frequency domain signal.

7 . The method of claim 1 , wherein the converting the first frequency domain signal into the second frequency domain signal based on the result of the determining comprises:
performing noise filtering on the first frequency domain signal; and converting the noise-filtered first frequency domain signal into the second frequency domain.

8 . The method of claim 1 , wherein the analyzing the sound signal using the second frequency domain signal comprises using an external memory located outside of the device.

9 . A device comprising:
a signal receiver configured to receive a sound signal from an external sound source; a voice signal determiner configured to convert the sound signal into a first frequency domain signal in a first frequency domain, and determine whether or not the sound signal is a voice signal using the first frequency domain signal; a frequency converter configured to convert the first frequency domain signal into a second frequency domain signal in a second frequency domain based on a result of the determining; and a signal recognizer configured to analyze the sound signal using the second frequency domain signal.

10 . The device of claim 9 , wherein the frequency converter is further configured to convert the first frequency domain signal into the second frequency domain signal when the voice signal determiner determines that the sound signal is a voice signal.

11 . The device of claim 9 , wherein the frequency converter is further configured to convert the first frequency domain signal into the second frequency domain signal using at least one method selected from upsampling, downsampling, interpolation, mirroring, and phase shifting.

12 . The device of claim 9 , wherein the first frequency domain includes at least one selected from a discrete Fourier transform (DFT) domain, a discrete cosine transform (DCT) domain, a discrete sine transform (DST) domain, and a modified discrete cosine transform (MDCT) domain.

13 . The device of claim 9 , wherein the second frequency domain includes at least one selected from a discrete Fourier transform (DFT) domain, a discrete cosine transform (DCT) domain, a discrete sine transform (DST) domain, and a modified discrete cosine transform (MDCT) domain.

14 . The device of claim 9 , wherein the frequency converter is further configured to store the first frequency domain signal in an internal memory included in the device, and convert the stored first frequency domain signal into the second frequency domain signal.

15 . The device of claim 9 , wherein the frequency converter is further configured to perform noise filtering on the first frequency domain signal, and convert the noise-filtered first frequency domain signal into the second frequency domain.

16 . The device of claim 9 , wherein the signal recognizer is further configured to use an external memory located outside of the device.

17 . A non-transitory computer-readable recording medium storing a program for implementing the method of claim 1 .

18 . The method of claim 1 , wherein the analyzing the sound signal using the second frequency domain signal comprises:
extracting features from the second frequency domain signal; comparing the extracted features from the second frequency domain signal with a vocal database; and transmitting a voice recognition result based on a result of the comparing.

19 . The method of claim 1 , wherein the converting the first frequency domain signal into the second frequency domain signal comprises converting the first frequency domain signal directly into the second frequency domain signal without an intermediate process of converting the first frequency domain signal into a time domain signal.

20 . The method of claim 1 , wherein:
the converting the sound signal into the first frequency domain signal comprises converting the sound signal into the first frequency domain signal in units of a first preset time length, the converting the first frequency domain signal into the second frequency domain signal comprises converting the first frequency domain signal into the second frequency domain signal in units of a second preset time length, and
the second preset time length is shorter than the first preset time length.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Jo Seok-Hwan
• Kim Do-Hyung
• Kim Jae-Hyun
• Lee Shi-Hwa

Classifications

• G10L25/93 Primary

  Discriminating between voiced and unvoiced parts of speech signals (G10L25/90 takes precedence) · CPC title

• G10L15/285

  Memory allocation or algorithm optimisation to reduce hardware requirements · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L21/0208

  Noise filtering · CPC title

• G10L15/20

  Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence) · CPC title