KR100934651B1 - Voice recognition device of automatic washing machine - Google Patents

Abstract

The present invention relates to a voice recognition device of a full-automatic washing machine, which allows a washing machine to be controlled by voice even in ambient noise. The noise generated by the washing machine is removed by an adaptive filter, and when a voice is input, the voice section is detected by a voice section detection algorithm. . The speech is extracted from the detected speech section, and the feature is extracted. The extracted feature is compared with the reference pattern or the probability of occurrence of the reference model is recognized or rejected. By adapting the recognized result to the peripheral device, the automatic washing machine can be controlled by voice recognition to increase convenience and added value.

Washing machine, voice, recognition

Description

Device for recognizing voice in full automation-type washing machine

1 is a perspective view showing an example of a conventional fully automatic washing machine

2 is a block diagram of a general speech recognition system

Figure 3 is a block diagram of a voice recognition device of the automatic washing machine according to the present invention

4 is a block diagram illustrating an adaptive filter of FIG. 3.

* Description of the symbols for the main parts of the drawings *

21: adaptive filter unit 22: speech recognition unit

25: first mixer 26: adaptive filter

27: second mixer 28: voice section detection unit

29: feature extraction unit 30: matching unit

31: recognition result checking unit 32: recognition result performing unit

The present invention relates to voice recognition, and more particularly, to a voice recognition device of a washing machine that can control a washing machine even in ambient noise.                         

At present, there are many attempts to operate electronic products that are used in daily life by voice commands.

In particular, washing machines, dishwashers, and the like provide convenience of life by reducing household labor in modern life. TV, audio, etc., play an important part in leisure, information gathering and education.

In addition, the remote control has appeared to improve the convenience of operation, thereby allowing the user to perform the desired action by sitting in the seat.

However, since this also operates other devices, there is a limit to convenience, and therefore, development of a device capable of recognizing a voice that is most familiar to humans is in progress.

The general operation principle of the speech recognition is as follows.

First, the speech recognition algorithm may be classified into a speech section detection process, a feature extraction process, and a matching process.

That is, as shown in FIG. 2, when a voice signal is input through the microphone 11, the A / D converter 12 converts the voice signal into a digital signal and outputs the digital signal to the voice section detector 13.

The speech section detector 13 divides the digital speech signal into short section signals (ie, frames), and then uses the energy, zero crossing rate, and time length information of each frame to actually input the signals. After detecting only the spoken speech section, the speech signal is output to the feature extractor 14.

The feature extractor 14 extracts the feature of the frame corresponding to the speech section, creates a test pattern of the input speech, and outputs the test pattern to the matcher 15.

The matching unit 15 compares the test pattern with each of the reference patterns stored in the reference data memory 16 and outputs a reference pattern having a feature most similar to the test pattern as a recognized voice.

In this case, when the reference pattern of the voice signal is stored in the reference data memory 16, the feature extractor 14 extracts a feature of a frame corresponding to the voice section to create a reference pattern, and then uses the reference data. In the memory, the voice signal to recognize the operation is repeatedly performed to database the reference pattern in the reference data memory 16.

However, such a conventional speech recognition device is degraded when there is ambient noise.

In particular, the washing machine has a high motor sound when driven and a high noise due to the sound of water during feeding / draining, so that voice recognition may not be easily performed.

Therefore, it is necessary to develop a device capable of speech recognition despite such ambient noise and noise.

An object of the present invention is to provide a voice recognition device for a fully automatic washing machine capable of reliably recognizing voice despite ambient noise generated in a washing machine.

Another object of the present invention is to apply a voice recognition algorithm to a washing machine with a built-in microphone to operate the washing machine by voice.

A feature of the voice recognition device of the automatic washing machine according to the present invention is that the noise signal generated from the washing machine components or the water supply / drainage is adapted to the voice signal input from the microphone built into the washing machine body or the microphone built into the remote controller. An adaptive filter to output an audio signal from which the noise signal is removed; By applying the speech signal of the adaptive filter unit, the speech segment detection algorithm is performed to detect the speech segment, analyze the detected speech signal to extract the features, compare the extracted features with the reference pattern, or calculate the probability of occurrence of the reference model. And a voice recognition unit for recognizing or rejecting an input voice and adapting the extracted feature and recognition result to a recognizer to perform the recognized result to a peripheral device.

According to another aspect of the present invention, an adaptive filter unit includes: a first mixer configured to add a noise signal generated from a washing machine and a voice signal input from a microphone to output a mixed voice signal; A second mixer for subtracting the speech signal mixed with the noise applied from the first mixer and the filtered signal applied from the following adaptive filter and outputting the speech signal from which the noise is removed; And an adaptive filter for filtering and outputting an applied noise signal and feeding back a speech signal from which the noise output from the second mixer is removed to adjust a coefficient of the filter.

Another feature of the present invention is to use the characteristics of the voice signal input from the microphone and the noise signal generated in the washing machine and the coefficient change of the adaptive filter when detecting the voice section in the voice recognition unit.

Referring to the accompanying drawings, the voice recognition device of the automatic washing machine according to the present invention having the features as described above is as follows.

First, the concept of the present invention forms an adaptive filter using various components of the automatic washing machine or noise (noise) generated during supply / drainage as a reference signal to remove the noise generated in the washing machine. It is to enable speech recognition.

FIG. 3 is a block diagram illustrating a speech recognition device of the automatic washing machine according to the present invention. As shown in FIG. 3, the adaptive filter unit 21 and the speech recognition unit 22 may be largely divided.

As shown in FIG. 4, the adaptive filter unit 21 adds the noise generated by the automatic washing machine and the voice signal input from the microphone provided in the washing machine main body or a microphone provided separately from the washing machine to output a mixed voice signal. A second mixer which subtracts the voice signal mixed with the noise applied from the first mixer 25 and the first mixer 25 and the filtered signal applied from the adaptive filter 26 to output the voice signal from which the noise is removed ( 27) and an adaptive filter 26 which filters and outputs the applied noise and feeds back the speech signal from which the noise output from the second mixer 27 is removed to adjust the coefficient of the filter.

Here, the noise refers to a signal of the noise generated from the parts of the washing machine to be controlled and the sound generated during the supply / drainage, the voice signal input from the microphone is a voice signal including an external noise signal and a noise signal generated from the washing machine Means.

The voice recognition unit 22 extracts the voice signal section from the signal applied through the microphone by using the coefficient change of the adaptive filter 26 and the voice signal and noise input through the washing machine main body or a microphone separately provided. A speech section extractor 28, a feature extractor 29 extracting a parameter representing a characteristic from the detected speech signal, and a speech inputted by comparing the extracted parameter with a reference pattern or calculating a probability of occurrence of the reference model A matching unit 30 for recognizing the identification, a recognition result unit 31 for rejecting recognition if the similarity or probability of occurrence of the recognized result is below a predetermined level, a recognition result performing unit 32 for performing the recognized result, It is composed of a recognizer adaptation unit 33 for adapting the speech recognition device to the characteristics of the speaker or the use environment using the extracted features and recognition results.

The operation of the present invention configured as described above will be described with reference to FIGS. 2 and 3.

First, in order to recognize a voice in a washing machine, a sound signal (noise) generated in the washing machine must be removed from the voice signal applied from the microphone.

To do this, the adaptive filter coefficients should be adjusted to minimize the difference between the generated signal of the washing machine and the voice signal applied from the microphone.

That is, the noise generated in the washing machine and the voice signal input from the microphone are added by the first mixer 25 to output the mixed voice signal, and the adaptive filter 26 filters the noise signal.                     

The output signal of the adaptive filter 26 and the output signal of the first mixer 25 are applied to the second mixer 27 to output an audio signal from which noise is removed.

The speech signal from which the noise is removed is fed back to the adaptive filter 26 to adjust the coefficients of the adaptive filter.

In this way, the speech signal from which the noise output from the adaptive filter unit 21 is removed is applied to the speech section detecting section 28 to detect only the section actually spoken, i.e., the speech section.

Here, the voice section is detected using the coefficient change of the adaptive filter and the characteristics of the voice signal input from the microphone and the noise signal generated in the washing machine.

The reason for using them is that in the case of the adaptive filter, the filter coefficient is very severely changed when the main signal input from the reference signal and the microphone are significantly different.

That is, while the voice is input, the filter coefficient change is remarkably different from other intervals.

Therefore, if the coefficient variation is continuously monitored, a large portion of the variation can be extracted as the voice interval.

Here, each coefficient change amount measures the average coefficient change amount of a short segment.

In addition to the filter coefficient variation, the speech section is extracted by using the spectrum information and the energy information of the reference signal and the main signal together.

Next, the feature extractor 29 extracts a feature of the detected speech section signal, and usually uses a parameter representing spectrum information.                     

The matching unit 30 recognizes the input voice by comparing the extracted parameter with a reference pattern or by calculating a probability of occurrence of the reference model.

That is, the voice most similar to the input voice is searched among the registered voices. After all the similarities of the registered words are all calculated, the most similar registered words are extracted.

As an example of measuring similarity, a dynamic time warping (DTW) algorithm or a hidden markov model (HMM) probability value may be used.

The matching unit 30 of the present invention may use a two-stage recognition method to improve the performance of the voice recognition device.

Two-stage recognition is divided into a key word recognition process and a command recognition process. The key word recognition process recognizes whether a single word is uttered.

That is, there is only one vocabulary to be recognized, and 'recognition' or 'rejection' is determined by the recognition result checking process, and the recognition rate is improved by minimizing the recognition word.

The device to be controlled operates in the keyword recognition mode as an initial state, and when it is determined as 'recognition', sets the device to be controlled to the command recognition mode and limits the noise generated by the device to a predetermined level or less.

In addition, the command recognition process recognizes a command of the device, performs a recognition result, and sets the device to a keyword recognition mode in its original state.

Then, if the similarity between the most similar registered words and the input voice is rejected by the predetermined rule, the recognition result confirming unit 31 sees that the voice not registered is input and accepts the voice again.

In this case, a simple similarity may be measured and used, or various types of filter models may be used.

This applies to both keyword recognition and command recognition.

If the recognition process is successful, the recognition result execution unit 32 executes a command according to the result.

On the other hand, the recognizer adaptor 33 adapts the speech recognition apparatus to the characteristics of the speaker or the use environment by using the extracted features and recognition results.

This can be done as a training course before the actual use of the device or during the actual use.

Voice recognition device of the automatic washing machine according to the present invention has the following effects.

First, by controlling the automatic washing machine by voice recognition, its convenience and added value can be increased.

Second, by solving the noise problem that was the biggest problem in applying the speech recognition function to the automatic washing machine, it is possible to enable speech recognition in spite of the noise generated in the washing machine.

Claims (3)

An adaptive filter that outputs a voice signal from which the noise signal is removed by adapting a noise signal generated from a washing machine component or a noise signal generated from a water supply / drainage to a voice signal input from a microphone built in a washing machine body or a microphone built in a remote controller. Wealth, The speech signal is applied to the adaptive filter unit to perform a speech section detection algorithm to detect a speech section, analyze the detected speech signal to extract a feature, and compare the extracted feature with a reference pattern or calculate a probability of occurrence of a reference model. And a voice recognition unit configured to recognize or reject the input voice and to adapt the extracted feature and the recognition result to a recognizer to perform the recognized result on the peripheral device. The method of claim 1, The adaptive filter unit, A first mixer for adding a noise signal generated from a washing machine and a voice signal input from a microphone to output a voice signal mixed with noise; A second mixer for subtracting the speech signal mixed with the noise applied from the first mixer and the filtered signal applied from the following adaptive filter and outputting the speech signal from which the noise is removed; And an adaptive filter for filtering and outputting an applied noise signal and feeding back a noise signal from which the noise output from the second mixer is removed to adjust coefficients of the filter. The method of claim 1, The voice signal input from the microphone built in the washing machine body or the microphone built in the remote controller provided separately is a voice signal including an external noise signal and a noise signal generated by the washing machine.

Images