KR20180125395A - Environment classification hearing aid and environment classification method using thereof - Google Patents

Abstract

The present invention relates to an environment classification hearing aid to classify in which environment did an external sound input to a hearing aid input, and an environment classification method using the same. The environment classification hearing aid comprises a plurality of DSPs for analyzing an environment of an external sound, and processing a voice signal included in the external sound according to the analyzed environment. The environment classification hearing aid is operated by at least one of a first mode extracting a first feature point from a digital signal of the plurality of DSPs and a second mode for extracting a second feature point from the digital signal to analyze the environment of the external sound again when the environment of the external sound is analyzed through the first mode.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a hearing aid,

The present invention relates to an environment classifying hearing aid and an environmental classifying method using the same, and more particularly, to an environment classifying hearing aid for classifying an external sound inputted into a hearing aid and an environment classifying method using the same.

Generally, a hearing aid is a device for amplifying sound by being attached to the ear of a patient diagnosed with hearing loss. The hearing aid is composed of a microphone for receiving sound, an amplifier for amplifying sound, and a receiver for outputting amplified sound. Artificially deforms the acoustic signal so that the acoustic signal input to the organism can be input to the brain to the same degree as a normal person.

Currently available hearing aids are classified into analog type and digital type hearing aids. The dual analogue type hearing aids have the disadvantage that the analog circuit included in the hearing aid can not amplify the functionality of the digital circuit because of the flexibility and reliability of the digital circuit.

Therefore, in order to solve the problems of the conventional analog type hearing aid, development of a digital hearing aid capable of realizing a complicated signal processing algorithm, which has an improved performance than the flexibility and reliability of an analog circuit, has been actively developed.

Conventionally developed digital hearing aids may classify an environment in which an external sound is generated in order to remove noise in a process of processing sound generated from the outside and outputting the sound to a user of the hearing aid. Therefore, in order to more effectively remove the noise from the sound output to the hearing aid user, a method of effectively classifying the environmental sound, which is the noise heard from the external environment, and removing the noise according to the kind of the environment sound is required.

In general, the process of classifying the environment performed in a digital hearing aid is processed by a DSP (Digital Signal Processor). To classify the environment more precisely, a large amount of arithmetic processing is required, and accordingly, a plurality of DSPs must be operated. For example, if the DSP for performing the basic operation of the hearing aid such as noise elimination or WDRC (Wide Dynamic Range Compression) amplification and the DSP for detecting and classifying environmental changes are operated separately, Two or more DSPs must be operated together.

And, when a plurality of DSPs operate together for environment calculation processing, the power consumption of the hearing aid increases. On the other hand, the size of the hearing aid is limited due to the comfort and portability required of the hearing aid, which limits the energy that can be stored in the hearing aid.

Therefore, there is a need for a method that can reduce the power consumption while efficiently performing the environmental classification function of the hearing aid.

SUMMARY OF THE INVENTION It is an object of the present invention to reduce the amount of power consumed while performing an environmental classification function of a hearing aid more efficiently.

Another object of the present invention is to reduce the amount of power consumed by the DSP by selectively changing the DSP structure of the hearing aid according to the environment classification algorithm.

According to an aspect of the present invention, there is provided an environment classifying hearing aid comprising: a microphone for inputting an external sound; A plurality of DSPs for analyzing the environment of the external sound and processing voice signals included in the external sound according to the analyzed environment; A receiver for converting a digital signal processed by the DSP into a voice signal and outputting the converted digital signal to a user; At least some of the plurality of DSPs processing a voice signal from the external sound and extracting a first feature point from the digital signal to analyze the environment of the external sound; And a second mode for analyzing the environment of the external sound by extracting a second characteristic point from the digital signal when the environment of the external sound is analyzed through the first mode; Lt; RTI ID = 0.0 > mode. ≪ / RTI >

The DSP includes a DSP core that decodes an instruction to process an operation; A memory unit for storing instructions and data necessary for arithmetic processing of the DSP core; . ≪ / RTI >

The DSP core includes: a decoding unit decoding the instruction; An operation unit for processing an operation according to the decoded instruction; A register unit for storing intermediate processing results generated in the operation processing of the operation unit; . ≪ / RTI >

A DSP for operating the first mode includes a simple command processor for extracting the first feature point; As shown in FIG.

Wherein the simple instruction processing unit comprises: a command buffer for indicating a simple instruction for extracting the first feature point using at least a part of the register files included in the register unit; And an arithmetic operation unit that processes the arithmetic unit in accordance with an instruction of the instruction buffer using at least a part of the arithmetic units included in the arithmetic unit; . ≪ / RTI >

The DSP core of the DSP in which the second mode is operated includes a loop buffer for processing repeated instructions used when extracting the second characteristic point using at least a part of register files included in the register unit; As shown in FIG.

Wherein the first feature point corresponds to at least one of a ZCR (zero crossing rate) and a power spectrum, and the second feature point corresponds to at least one of a Mel-Scale Frequency Cepstrum Coefficient (MFCC), a spectral entropy, have.

The DSP may analyze the environment of the external sound by extracting the first feature point through the first mode, comparing the previously stored environment information with the distance value, and measuring the similarity.

The DSP may extract the second feature point through the second mode and then analyze the environment of the external sound by measuring the similarity through pre-stored environment information and log-raycyle hood based on GMM (Gaussian Mixture Model) .

Wherein the second mode is a mode in which when the environment of the external sound analyzed by the DSP is different from the environment of the external sound analyzed through the first mode and the environment of the external sound analyzed through the first mode, .

The second mode may be operated in a DSP different from the DSP in which the first mode is operated.

When the environment analysis of the external sound through the second mode is terminated, the DSP in which the second mode is operated may be changed to the idle state.

According to another aspect of the present invention, there is provided a method for classifying an environment of an external sound inputted to a hearing aid by a plurality of DSPs of a hearing aid, the method comprising the steps of: ; Operating in a first mode to extract first feature points of the external sound; Analyzing the environment of the external sound through the first feature point; Extracting a second feature point of the external sound by operating in a second mode if the environment of the external sound does not match the environment; And re-analyzing the environment of the external sound through the second feature point; And information on the environment of the external sound analyzed again through the second feature point may be reflected in the speech signal processing step.

The first mode may be operated by one of the plurality of DSPs, and the second mode may be operated by another one of the plurality of DSPs.

Further comprising: after re-analyzing the environment of the external sound through the second feature point, changing the DSP in which the second mode is operated to an idle state; As shown in FIG.

The step of processing the voice signal for the external sound and the step of extracting the first feature point of the external sound by operating in the first mode may be performed in parallel with the DSP operated in the first mode.

The environment classification hearing aid and the environment classification method according to the embodiment of the present invention can reduce the amount of power consumed while performing the environment classification function more efficiently.

In addition, the environment classifying hearing aid and the environment classifying method according to the embodiment of the present invention can selectively change the DSP structure of the hearing aid according to the environment classifying algorithm, thereby reducing the amount of power consumed in the DSP.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.
1 is a view for explaining an environment classifying hearing aid according to an embodiment of the present invention.
FIGS. 2 to 4 are views for explaining an embodiment in which the structure of the DSP can be modified in FIG.
5 is a view for explaining an environmental classification method according to another embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments will be described in detail below with reference to the accompanying drawings.

The following examples are provided to aid in a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, this is merely an example and the present invention is not limited thereto.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. The following terms are defined in consideration of the functions of the present invention, and may be changed according to the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification. The terms used in the detailed description are intended only to describe embodiments of the invention and should in no way be limiting. Unless specifically stated otherwise, the singular form of a term includes plural forms of meaning. In this description, the expressions " comprising " or " comprising " are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, Should not be construed to preclude the presence or possibility of other features, numbers, steps, operations, elements, portions or combinations thereof.

It is also to be understood that the terms first, second, etc. may be used to describe various components, but the components are not limited by the terms, and the terms may be used to distinguish one component from another .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining an environment classifying hearing aid according to an embodiment of the present invention.

1, an environment classifying hearing aid according to an embodiment of the present invention includes a general processor 10, a microphone 20, a general memory 30, a receiver 40, and a plurality of DSPs 50 and 51 . And the above-described configurations can be connected to each other via a bus to exchange signals.

The general purpose processor 10 can operate or convert a plurality of DSPs 50 and 51 included in the environment classifying hearing aid into an idle state and can set a parameter value between the plurality of DSPs 50 and 51 or a result value As shown in FIG.

The microphone 20 can receive an external sound input from the outside of the environment classifying hearing aid and convert it into a digital signal. To this end, the microphone 20 may include a signal conversion device such as an A / D converter.

The general purpose memory 30 may be a storage device for storing data used for arithmetic processing and the like of an internal apparatus of an environment classifying hearing aid such as a general-purpose processor 10, a microphone 20 and a receiver 40. [

The receiver 40 can convert a digital signal from which a noise is removed from a speech signal through a plurality of DSPs 50 and 51 into a sound so that the user of the environmental classification hearing aid can recognize the sound through hearing.

The plurality of DSPs 50 and 51 may analyze the environment of the external sound and process the voice signal included in the external sound according to the analyzed environment.

Wherein at least some of the plurality of DSPs include a first mode in which at least some of the plurality of DSPs extract a first feature point from the digital signal to analyze the environment of the external sound and analyze the environment of the external sound, And a second mode for analyzing the environment of the external sound by extracting a second characteristic point from the digital signal when the environment of the external sound is analyzed through the mode.

Here, the environment of the external sound refers to a place where a hearing aid receives external sound, and various places such as a cafe, a street, a movie theater, and a construction site can be exemplified. The sound from this environment is mixed with the voice of the other party that the hearing aid user wants to hear, which causes noise. Therefore, it is important to analyze how the external sound belongs to the environment and to vary the noise removal method according to the environment.

The number of DSPs included in an environmental classification hearing aid may vary depending on the intention of the hearing aid designer or the hearing aid production environment.

FIGS. 2 to 4 are views for explaining an embodiment in which the structure of the DSP can be modified in FIG.

2 is a diagram for explaining a general operation mode of a DSP according to an embodiment of the present invention. Referring to FIG. 2, the DSP may include a DSP core 100 and a memory unit 110 in a general operation mode.

The DSP core 100 can decode the received instruction and load the related data from the memory unit 110 and calculate and output the result.

For this purpose, the DSP core 100 includes a decoding unit 101 for decoding an instruction, an operation unit 103 for performing an operation according to the decoded instruction, and an operation unit 103 for storing an intermediate process result generated in the operation process of the operation unit 103 And a register unit 102.

The memory unit 110 may store instructions and data necessary for the arithmetic processing of the DSP core 100. In more detail, the memory unit 110 may include an instruction memory 111 for storing instructions and stored data, and a data memory 112 for storing data necessary for the operation of the operation unit 103.

The decoding unit 101 decodes a digital signal received from other components of the hearing aid, such as the general-purpose processor 10 and the microphone 20, by using a command. The decoding unit 101 may access the instruction memory 111 to load necessary data in the decoding process of the instruction of the decoding unit 101. [

The register unit 102 may store the intermediate processing result generated in the operation processing of the operation unit 103 or temporarily store the data for updating the operation processed value. The register unit 102 may include a plurality of register files R0, R1, R2, ..., R15. In FIG. 2, the register unit 102 is configured to include 16 register files (R0, R1, R2, ..., R15). However, the number of register files included in the register unit 102 may vary depending on the design of the DSP core 100 or the mode of the DSP.

The arithmetic unit 103 can perform arithmetic operation between the data loaded from the data memory 112 and output the result of the arithmetic operation according to a given instruction. The arithmetic unit 103 is an ALU (Arithmetic Logic Unit), and can be configured to include a plurality of arithmetic units. Here, the arithmetic unit may be a MAC (Multiplier Accumulator) unit capable of performing an addition operation and a multiplication operation between two pieces of data.

FIG. 3 is a view for explaining a first mode of a DSP according to an embodiment of the present invention, and FIG. 4 is a diagram for explaining a second mode of a DSP according to an embodiment of the present invention. In the description of FIG. 3 and FIG. 4, the description of the configuration or effect overlapping with the general operation mode of the DSP of FIG. 2 will be omitted.

The first mode may be a mode for processing a speech signal from an external sound and extracting a first feature point from the digital signal to decompose the environment of the external sound. The second mode may be a mode for analyzing the environment of the external sound by extracting the second characteristic point from the digital signal when the environment of the external sound is analyzed through the first mode.

The plurality of DSPs included in the environment classification hearing aid can be converted into at least one of the above-mentioned general operation mode, first mode and second mode according to the judgment of the general purpose processor.

3, in the first mode, the DSP core 200 is different from the DSP core 100 of FIG. 2 in that some arithmetic units of the arithmetic unit 203 and some of the register files of the register unit 202 are connected to the simple instruction processing unit 210). ≪ / RTI >

More specifically, in the first mode of the DSP, the simplified instruction processing unit 210 for extracting the first feature point in the DSP extracts the first feature point using at least a part of the register files included in the register unit 202 And a command buffer 211 for indicating a command. The simplified instruction processing unit 210 may include a simple arithmetic operation unit 212 for performing an arithmetic operation in accordance with an instruction of the instruction buffer 211 by using at least some of the arithmetic units included in the arithmetic unit 203. [

In other words, unlike the DSP general operation mode of FIG. 2, the register file and the arithmetic unit can be separated from the DSP core 200 in the DSP first mode of FIG. Here, separating the register file and the arithmetic unit from each other does not mean that the register file and the arithmetic unit are physically separated from each other, but may be used differently from the DSP core 200 in order to process a separate operation.

In the first mode, the simplified instruction processing unit 210 can process an operation in parallel with the DSP core 200 through the instruction buffer 211 and the simple operation unit 212. [ While the DSP core 200 performs the algorithm for processing the voice signal from the external sound, the simplified command processing unit 210 may extract the first feature point included in the external sound.

In this way, it is possible to operate the arithmetic units in a state other than the idle state in the first mode than in the general operation mode in Fig. This allows the DSP to process more computations for the same amount of time than in the normal mode of operation. Therefore, there is an effect that the efficiency of the arithmetic processing process for the external sound is increased.

Since some arithmetic units of the arithmetic units are used for other arithmetic operations, the arithmetic operations to be processed in the simple instruction processor 210 need to be arithmetic operations with a small amount of computation. Accordingly, the first feature point extracted through the simple instruction processing unit 210 may be a feature point extracted by simple iterative calculation.

In the first mode, the memory unit 220 may include a command memory 221 and a data memory 222 as in a normal operation mode.

The instruction buffer 211 of the simple instruction processing unit 210 may repeatedly perform an operation on the data stored in the memory in the form of a vector or an array. That is, the simple command processing unit 210 can repeatedly calculate a plurality of data with one command. Therefore, the simple arithmetic operation unit 212 can directly load and store data from the data memory 222 of the memory unit 220, and can process the arithmetic operation according to the instruction as soon as the data is applied without the need for a separate register file.

In the case of extracting the first feature point by the above-described method, it is not necessary to additionally operate a separate DSP or to add additional hardware to the DSP in order to extract the first feature point, so that the power consumption by the DSP can be reduced .

The first determination of the environment of the currently input external sound is possible through the extraction of the first feature point. It is possible to preferentially judge whether or not the environment already recognized by the environment classification hearing aid is identical to the environment of the external sound currently input through the first feature point. As a result of determining the environment of the external sound through the extraction of the first feature point, if the already recognized environment and the newly recognized environment are not different from each other, the environment classification can be terminated without operating the additional DSP.

If it is determined that the already recognized environment is different from the newly recognized environment as a result of the extraction of the first feature point, an additional DSP may be operated to extract the second feature point of the currently inputted external sound. At this time, the DSP which is in the idle state under the control of the general-purpose processor 10 may be additionally operated as the second mode.

In addition, when the environment is recognized and classified last for a predetermined time or more from the current time, it is necessary to newly recognize and classify the environment, so that the additional DSP can be operated. At this time, the predetermined time may be set differently according to the intention of the hearing aid designer.

Here, the first characteristic point may be a relatively simple calculation process such as ZCR (Zero Crossing Rate), which is an added value of how the negative and positive numbers change between adjacent samples, and power spectrum, which is obtained by measuring power per band. The DSP operating according to the first mode may extract the first feature point and compare the extracted feature point with the previously extracted feature point to determine whether the environment changes.

When the first feature points are extracted through the first mode, the DSP compares the previously stored environment information with the distance values of the first feature points to measure the similarity degree. If the difference in the degree of similarity exceeds a predetermined range, And then proceeds to the second feature point extraction step.

Here, the environment information may indicate a first feature point extracted for a previous external sound. And the distance value may mean a distance value of a vector between minutiae points described by Euclidian distance or cosine distance.

Referring to FIG. 4, it can be seen that, in the second mode, some of the register files of the register portion 202 are used as the loop buffer 304, unlike the DSP core 300 of the DSP core 100 of FIG.

The loop buffer 304 can be utilized for extracting the second feature point. Since the second feature point has more complex characteristics than the first feature point, more computation is required for extracting the feature points. The commands used to extract feature points for environmental classification are often repeated commands. Although the operation based on such a repeat instruction is simple, it increases the overall calculation amount by repeatedly executing the instruction. In addition, the DSP core continuously accesses the memory area, which causes an increase in power consumption.

The loop buffer 304 can reduce the access frequency of the DSP core 300 to the instruction memory 311 of the memory unit 310 by processing the repeated instruction used in extracting the second feature point. That is, the frequency of access to the memory unit 310 of the DSP core 300 can be reduced by utilizing a part of the register file constituting the register unit as the loop buffer 304.

Here, the second characteristic point may correspond to at least one of a Mel-Scale Frequency Cepstrum Coefficient (MFCC) for a power spectral density of a predetermined section, a spectral entropy for a smoothness of a power spectrum, and ZCR.

The DSP can extract the second feature point of the current environment and analyze the environment of the external sound by measuring the similarity through log-likelihood based on GMM (Gaussian Mixture Model).

The DSP operating in the first mode and the second mode may be different DSPs. The DSP operating in the first mode is performing the voice signal processing through the DSP core 200 and at the same time the other DSP is operated in the second mode to extract the second characteristic points and analyze the environment. The result of the environmental analysis of the DSP operating in the second mode may be transmitted to the DSP operating in the first mode and used for voice signal processing.

When the DSP operating in the first mode extracts the first feature point and it is determined that the pre-stored environment information and the environment of the currently input external sound are different from each other, a DSP different from the DSP operating in the first mode may be operated. That is, the DSP operating in the second mode can be changed from the idle state to the second mode according to the extraction result of the first feature point.

When extraction of the second feature point of the DSP operating in the second mode is completed, the DSP operating in the second mode is changed to the idle mode again, thereby saving power consumption.

5 is a view for explaining an environmental classification method according to another embodiment of the present invention.

Referring to FIG. 5, the environmental classification method includes a voice signal processing step S110, a first feature point extraction step S120, an external sound environment analysis step S130 using a first feature point, a second feature point extraction step (S160), and an external sound environment analysis step (S170) using the second characteristic point.

When the external sound is input through the microphone of the environment classification hearing aid (S100), the DSP can operate in the first mode. The voice signal processing step S110 and the first feature point extracting step S120 may be performed on the DSP operating in the first mode. The speech signal processing step S110 and the first feature point extracting step S120 may be performed in parallel in the same DSP as described above.

The voice signal processing step (S110) is a step for the DSP to recognize and process the voice signal included in the external sound. When the second feature point is extracted as described later, the information about the recognized environment is reflected .

The first feature point extracting step (S120) may mean that the DSP operates in the first mode and extracts the first feature point from the external sound.

When the first feature point is extracted, the DSP operating in the first mode compares the existing environment information with the newly extracted first feature point to determine whether the environment is changed (S130). If the difference in similarity between the existing environmental information and the first feature point is less than a predetermined value, the DSP determines that the environment is maintained (S140). If the difference in similarity between the existing environment information and the first feature point exceeds a predetermined value, it is determined that the environment has changed and another DSP in the idle state can be operated (S150).

The DSP, which is operated by changing from the idle state to the second mode, can extract the second feature point from the external sound (S160). The DSP operating in the second mode can classify the surroundings of the environment of the external sound through the extracted second feature points. The information related to this can be transmitted to the DSP of the first mode which is reflected in the algorithm and performs the preceding speech signal processing step. Then, by extracting the second feature point, the DSP whose operation in the second mode is ended is changed to the idle state again, thereby reducing power consumption (S180).

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments described in the present invention are not intended to limit the technical spirit of the present invention but to illustrate the present invention. The scope of protection of the present invention should be construed by the following claims, and all technical ideas within the scope of equivalents thereof should be construed as being included in the scope of the present invention.

10: general purpose processor 20: microphone
30: general purpose memory 40: receiver
50, 51: DSP

Claims (16)

A microphone to which an external sound is input;
A plurality of DSPs for analyzing the environment of the external sound and processing voice signals included in the external sound according to the analyzed environment; And
A receiver for converting a digital signal processed by the DSP into a voice signal and outputting the converted digital signal to a user; Lt; / RTI >
At least some of the plurality of DSPs
A first mode for processing a speech signal from the external sound and extracting a first feature point from the digital signal to analyze the environment of the external sound; And
A second mode for analyzing the environment of the external sound by extracting a second characteristic point from the digital signal when the environment of the external sound is analyzed through the first mode; Wherein the at least one of the at least one mode and the at least one mode is selected from the group consisting of: 2. The apparatus of claim 1, wherein the DSP
A DSP core decoding an instruction to process an operation; And
A memory unit for storing instructions and data necessary for arithmetic processing of the DSP core; And an environmental classification hearing aid. 3. The system of claim 2, wherein the DSP core
A decoding unit decoding the instruction;
An operation unit for processing an operation according to the decoded instruction;
A register unit for storing intermediate processing results generated in the operation processing of the operation unit; And an environmental classification hearing aid. 4. The method of claim 3, wherein the DSP in which the first mode is operated comprises:
A simple command processing unit for extracting the first feature point; Further comprising: an environmental classification hearing aid. 5. The apparatus of claim 4, wherein the simple command processing unit
A command buffer for indicating a simple command for extracting the first characteristic point using at least a part of the register files included in the register unit; And
A simple arithmetic operation unit for performing an arithmetic operation corresponding to an instruction of the instruction buffer using at least a part of arithmetic units included in the arithmetic unit; And an environmental classification hearing aid. 4. The method of claim 3, wherein the DSP core of the DSP in which the second mode is operating
A loop buffer for processing an iteration instruction used when extracting the second feature point using at least a part of the register files included in the register unit; Further comprising: an environmental classification hearing aid. The method according to claim 1,
The first feature point corresponds to at least one of ZCR (zero crossing rate) and power spectrum,
Wherein the second feature point corresponds to at least one of MFCC (Mel-Scale Frequency Cepstrum Coefficient), spectral entropy, and ZCR. 2. The apparatus of claim 1, wherein the DSP
Wherein the environment analyzing unit analyzes the environment of the external sound by extracting the first feature point through the first mode, comparing the previously stored environment information with the distance value, and measuring the similarity. 2. The apparatus of claim 1, wherein the DSP
Extracting the second feature point through the second mode, and analyzing the environment of the external sound by measuring the similarity through pre-stored environment information and a log-likelihood based on GMM (Gaussian Mixture Model) Classification hearing aids. 2. The method of claim 1,
Wherein the DSP is operated when the environment of the external sound analyzed in the environment analysis of the external sound through the first mode and the environment of the external sound analyzed through the first mode do not coincide with each other Environmental Classification Hearing Aids. 2. The method of claim 1,
Wherein the first mode is operated in a DSP different from the DSP in which the first mode is operated. 12. The method of claim 11,
Wherein when the environment analysis of the external sound through the second mode is terminated, the DSP in which the second mode is operated is changed to an idle state. A method for classifying an environment of an external sound inputted to a hearing aid by a plurality of DSPs of a hearing aid,
Processing a voice signal for the external sound;
Operating in a first mode to extract first feature points of the external sound;
Analyzing the environment of the external sound through the first feature point;
Extracting a second feature point of the external sound by operating in a second mode if the environment of the external sound does not match the environment; And
Analyzing the environment of the external sound again through the second feature point; Lt; / RTI >
Wherein the information about the environment of the external sound analyzed again through the second feature point is reflected in the speech signal processing step. 14. The method of claim 13,
Wherein the first mode is operated by one of the plurality of DSPs,
Wherein the second mode is operated by another one of the plurality of DSPs. 14. The method of claim 13,
Further comprising: after re-analyzing the environment of the external sound through the second feature point, changing the DSP in which the second mode is operated to an idle state; Further comprising the steps of: 14. The method of claim 13, wherein the step of processing the sound signal for the external sound and the step of extracting the first feature point of the external sound by operating in the first mode
And the DSP operating in the first mode is performed in parallel.

Images