Wireless communication device and wireless communication system

Abstract

To make it possible to perform noise cancellation so as to effectively output a human uttered voice, compared with the prior art, in a wireless communication device that performs wireless calls.SOLUTION: A wireless communication device of the present invention includes a modulation transmission unit that modulates a radio carrier wave according to an input audio signal and transmits a wireless signal. The wireless communication device includes a first noise cancellation unit that performs audio signal processing so as to cancel noise from the input audio signal and outputs the audio signal to the modulation transmission unit. The first noise cancellation unit performs noise cancellation processing, using a deep learning model unit that is learned using a feature parameter of human voice and that determines whether it is a non-voice period containing noise from the demodulated audio signal.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a wireless communication device for, for example, a specific low-power wireless communication station, and a wireless communication system including a plurality of wireless communication devices. [Background technology]

[0002] For example, in FIGS. 1 and 4 of Patent Document 1, use of a noise cancellation circuit that performs noise cancellation processing on an audio signal from a microphone of a wireless communication device is disclosed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2004-165962 A (Figs. 1 and 4) Summary of the Invention [Problem to be solved by the invention]

[0004] The noise cancellation circuit disclosed in Patent Document 1 only discloses that it "removes noise from the audio signal input from the microphone," but in the prior art, a so-called phase-inversion type noise cancellation circuit that inverts the noise signal outside the microphone and adds it to the audio signal input to the microphone is widely used. In this phase-inversion type noise cancellation circuit, there is a problem that when the noise is loud, even if a person is speaking, the level of the audio signal is suppressed, and noise cancellation cannot be performed to effectively output the human speech.

[0005] The object of the present invention is to solve the above problems and to provide a wireless communication device for wireless calls that can perform noise cancellation to effectively output human speech compared to conventional technology, and a wireless communication system including multiple such wireless communication devices. [Means for solving the problem]

[0006] A wireless communication device according to one aspect of the present invention comprises: A wireless communication device including a modulation transmission unit that modulates a wireless carrier wave in accordance with an input audio signal and transmits a wireless signal, a first noise canceling unit that performs audio signal processing so as to cancel noise from the input audio signal and outputs the processed audio signal to the modulation transmitting unit; The first noise cancellation unit performs noise cancellation processing using a deep learning model unit that is trained using characteristic parameters of human voice and determines whether the demodulated voice signal is a non-voice period containing noise. Effect of the Invention

[0007] Therefore, according to the wireless communication device of the present invention, by providing a noise cancellation circuit using a deep learning model unit instead of a phase inversion type noise cancellation circuit, in a wireless communication device that performs wireless calls, noise cancellation can be performed so as to more effectively output human speech compared to conventional technology. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing an example of the configuration of a wireless device 1 according to an embodiment. [Diagram 2] 2 is a block diagram showing an example of the configuration of a noise canceling unit 13 in FIG. 1. [Diagram 3] A block diagram showing an example configuration of the deep learning model unit 35 in Figure 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments and modifications of the present invention will be described with reference to the drawings. Note that the same or similar components are denoted by the same reference numerals.

[0010] Fig. 1 is a block diagram showing an example of the configuration of a radio device 1 according to an embodiment. In Fig. 1, the radio device 1 is an example of a wireless communication device, and includes a receiving antenna 11, a receiving and demodulating unit 12, a noise canceling unit 13, an audio signal amplifier 14, a speaker 15, a control unit 20, an operation unit 21 including a PTT (Push To Talk) key 21A, a microphone 22, an audio signal amplifier 23, a noise canceling unit 24, a modulation transmitting unit 25, and a transmitting antenna 26.

[0011] Here, the radio 1 according to the embodiment is an example of a radio communication device, for example, a specific low power radio station for a specific low power radio communication system. In this embodiment, the radio 1 is characterized in that, in its transmitting section, instead of a phase inversion type noise canceling circuit, it is provided with a noise canceling section 24 that is particularly effective in reducing noise, for example, in FM (frequency modulation) demodulation or PM (phase modulation) demodulation. Also, in this embodiment, the radio 1 further includes, in its receiving section, a noise canceling section 13 that is particularly effective in reducing noise. Also, a wireless communication system is configured by a plurality of radios 1.

[0012] In Fig. 1, a radio signal received by a receiving antenna 11 is input to a receiving demodulation unit 12. The receiving demodulation unit 12 performs low-noise amplification, low-frequency conversion, intermediate frequency amplification, etc. on the received radio signal, and then demodulates the signal into an audio signal using a predetermined demodulation method, such as FM (frequency modulation) demodulation or PM (phase modulation) demodulation, and outputs the signal to a noise cancellation unit 13. The noise cancellation unit 13 uses a deep learning model unit 35 (Fig. 3) that has been deep-learned using human voice to perform audio signal processing so as to cancel noise by passing the demodulated audio signal only during the audio signal period, and then outputs the processed audio signal to a speaker 15 via an audio signal amplifier 14.

[0013] The microphone 22 converts the input voice into a voice signal and outputs it to a modulation transmission unit 25 via a voice signal amplifier 23 and a noise cancellation unit 24 having a configuration similar to that of the noise cancellation unit 13. When the PTT key 21A is turned on, the control unit 20 operates the modulation transmission unit 25, and the modulation transmission unit 25 modulates a radio carrier wave according to the input voice signal using a predetermined modulation method, and then transmits the radio signal, which is the modulated radio carrier wave, from a transmission antenna 26 after high-frequency conversion and power amplification.

[0014] In this embodiment, the operation of the radio 1 in a simultaneous call system in which the transmission frequency and the reception frequency are different has been described, but the present invention is not limited to this, and when the radio 1 uses the same frequency for the transmission frequency and the reception frequency, the control unit 20 stops the operation of the reception demodulation unit 12 when the PTT key 21A is turned on. That is, in a radio 1 that does not simultaneously perform transmission and reception operations, during reception, the noise cancellation unit 24 may be operated instead of the noise cancellation unit 13 to perform noise cancellation processing during reception.

[0015] Next, with reference to FIG. 2, the configuration and operation of the noise cancellation units 13 and 24 in FIG. 1 using the deep learning model unit 35 will be described below.

[0016] FIG. 2 is a block diagram showing an example of the configuration of the noise canceling units 13 and 24 in FIG.

[0017] Here, the term "phoneme" means a unit of sound that distinguishes one word from another in a particular language, the term "vibration rate" means the number of shifts between 0 and 1 in the digitized vibration data in each second, and the term "vibration count (VC)" means the sum of the values ​​of the digitized vibration data in each frame. Also, the term "vibration pattern" means the data distribution of the sum of the vibration counts calculated for each predetermined number of frames along the time axis. In the deep learning model unit 35, noise cancellation processing is performed taking into account the difference in data distribution of different vibration patterns, i.e., the sum of different vibration counts (VS value), and the vibration rate is similar to the vibration count, but the higher the vibration rate, the higher the vibration count.

[0018] Both the amplitude and vibration rate of the audio signal are observable. A feature of the noise cancellation unit 13, 24 is to detect audio events according to the amplitude and vibration rate of the audio signal. Another feature is to distinguish between voice and non-voice / silence by measuring the sum of vibration count values ​​of the digitized vibration data for a predefined number of frames. Another feature is to classify the input audio signal data stream into different phonemes according to their vibration patterns. Another feature is to correctly distinguish the first activation phoneme from the input audio signal data stream so as to trigger a downstream processing unit, thereby saving computational costs such as power consumption of a computing system including the processing unit.

[0019] In FIG. 2, the noise canceling units 13 and 24 perform noise canceling processing using voice event detection, and include a voice signal preprocessing unit 38, an AD converter 39, and a voice signal processing unit 30. Here, the voice signal preprocessing unit 38 performs voice signal preprocessing on the analog voice signal, including high-pass filtering, low-pass filtering, amplification, or a combination thereof, and outputs the processed analog voice signal to the AD converter 39. That is, the voice signal preprocessing unit 38 passes only a predetermined bandwidth within a predetermined level range of the human voice signal for the voice signal from the microphone 22. Next, the AD converter 39 AD-converts the analog voice signal into a digital voice signal according to a predetermined reference voltage Vref and an allowable voltage Vadm (<Vref), and outputs it to the input interface 36 of the voice signal processing unit 30.

[0020] In this embodiment, in the AD converter 39, the allowable voltage Vadm smaller than the reference voltage Vref is used in combination with the reference voltage Vref to form a first threshold voltage Vth1 (=Vref+Vadm) and a second threshold voltage Vth2 (=Vref-Vadm). Based on the first threshold voltage Vth1 and the second threshold voltage Vth2, the AD converter 39 does not perform AD conversion on noise equal to or greater than the first threshold voltage Vth1 or equal to or less than the second threshold voltage Vth2, but performs AD conversion on the audio signal in between, thereby removing noise and interference from the input analog audio signal. Here, for example, if Vref=1.0V and Vadm=0.01V, it can be understood that the number of vibrations in the vibration data is small in a quiet environment and the number of vibrations in the vibration data is large in a voice environment. In this embodiment, the "frame size" means the number of sampling points corresponding to the digitized vibration data in each frame, and the "phoneme window Tw" means the time for collecting the audio feature of each phoneme. In a preferred embodiment, the duration Tf of each frame is, for example, 0.1 to 1 millisecond (ms), and the phoneme window Tw is, for example, about 0.3 seconds. In a further preferred embodiment, the number of sampling points corresponding to the digitized vibration data in each frame is, for example, in the range of 1 to 16.

[0021] When analyzing audio signals, short-term analysis methods are usually adopted since most audio signals are stable in a short period of time. For example, assuming that the sampling frequency fs used in the AD converter 39 is 16000 and the duration Tf of each frame is 1 ms, the frame size is fs x 1 / 1000 = 16 sample points.

[0022] In FIG. 2, the audio signal processing unit 30 is, for example, a computer device. (1) A CPU (Central Processing Unit) 31 that executes predetermined audio signal processing such as noise cancellation; (2) a ROM (Read Only Memory) 32 for storing an operating system for executing the basic processing of the CPU 31, a program for the audio signal processing, and data necessary for executing the program; (3) a RAM (Read Access Memory) 33 for storing data being processed when an operating system for executing the basic processing of the CPU 31 and the program for processing the audio signal are executed; (4) a non-volatile EEPROM (Electrically Erasable Programmable Memory) 34 for storing setting data, etc., which are necessary for executing the audio signal processing, as described later; (5) A deep learning model unit 35, which is composed of, for example, a neural network, removes noise from voice signal data input through deep learning based on human voice signal data, and extracts and outputs only the voice signal; (6) an input interface 36 that performs a predetermined signal conversion process on the audio signal data input from the AD converter 39 to convert the data into a signal specification value for a subsequent stage and outputs the signal to the CPU 31; (7) an output interface 37 that performs a predetermined signal conversion process for converting the voice signal data from which noise has been removed by the deep learning model unit 35 into a signal specification value of a subsequent stage, and outputs the data to the wireless device 1 via the terminal T12, the audio line L2, etc.; The present invention is configured to include the following components:

[0023] Here, the EEPROM 34 stores, for example, a series of vibration count values ​​VC, a sum of vibration count values ​​VS, a sum of vibration count values ​​VSf, a sum of vibration count values ​​VSp (described later), and audio feature values ​​of all feature vectors. Note that the EEPROM 34 may be a storage device such as an external memory. The audio event detection method applied to the audio signal processing unit 30 is executed by the CPU 31 during run-time to capture audio events. Audio event detection is performed assuming fs=16000, Tf=1 ms, and Tw=0.3 s.

[0024] Specifically, the CPU 31 calculates the sum of the vibration data values ​​of the current frame to be processed (i.e., within 1 ms) to obtain a vibration count value VC, and then stores the VC value of the current frame at time Tj in the EEPROM 34. Here, the vibration count values ​​VC of x frames are added together to obtain a sum VS of the vibration count values ​​of the current frame at time Tj. The x frames include the current frame. In one embodiment, the CPU 31 adds the vibration count value VC of the current frame at time Tj to the sum VSp of the vibration count values ​​of the (x-1) frames immediately preceding it to obtain the sum VS (=VC+VSp) of the vibration count values ​​of the x frames at time Tj.

[0025] In a modified example, the CPU 31 adds the vibration count value VC of the current frame at the time Tj, the sum of the vibration count values ​​of the immediately following y frames VSf, and the sum of the vibration count values ​​of the immediately preceding (xy-1) frames VSp to obtain the sum of the vibration count values ​​of the x frames at the time Tj (=VC+VSf+VSp), where y is equal to or greater than zero. The CPU 31 stores the values ​​of VS, VSf, and VSp in the EEPROM 34. In a preferred embodiment, the duration (x×Tf) of x frames (phoneme window Tw) is about 0.3 seconds. In a more preferred embodiment, the number of sampling points corresponding to the digitized vibration data of x frames is in the range of x to 16x.

[0026] Generally, for voice signal data, the vibration patterns of the vibration count value VC are similar for the same phoneme, but the vibration patterns of the VS value are completely different for different phonemes. Therefore, the vibration patterns of the vibration count value VC can be used to distinguish phonemes. In particular, it is known that the frequency distribution of the vibration count value VC is completely different between, for example, a chicken or a cat's cry and a human voice, and most of the vibration count values ​​VC of the human voice are distributed below 40.

[0027] In the training phase, the CPU 31 of the speech signal processing unit 30 first executes a predetermined speech signal data collection method multiple times to collect multiple feature vectors for multiple phonemes, and adds labels corresponding to the multiple feature vectors to form multiple labeled training examples. Then, the multiple labeled training examples for different phonemes including the activation phoneme are applied to training the deep learning model unit 35. Finally, the trained deep learning model unit 35 (which constitutes a predictive model of the speech signal data) is created to classify whether the input speech signal data stream includes the activation phoneme. When a predetermined phoneme is designated as the activation phoneme of the speech signal processing unit 30, the deep learning model unit 35 is trained with multiple labeled training examples for different phonemes including at least the designated phoneme.

[0028] That is, in the training phase, the set of labeled training examples is used to train the deep learning model unit 35 so that the deep learning model unit 35 recognizes a given activation phoneme, for j=0-299, based on three speech features (e.g., (VSj, TDj, TGj)) of each frame of the labeled training examples. At the end of the training phase, the trained deep learning model unit 35 provides a trained score corresponding to the activation phoneme, which is then used as a criterion for classifying an input stream of speech signal data at run-time. Here, VSj, TDj, and TGj are defined as follows: (1)VSj: the sum of vibration counts of frame j (VS value); (2) TDj: the time period of the sum of non-zero vibration count values ​​(VS values) in frame j; and (3) TGj; the time gap between the sums of non-zero vibration count values ​​(VS values) in frame j.

[0029] To train the deep learning model unit 35, various machine learning techniques related to supervised learning can be used, such as support vector machine (SVM) methods, random forest methods, convolutional neural network methods, etc. In supervised learning, a function calculator (i.e., the deep learning model unit 35) is created using a number of labeled training examples, each of which consists of an input feature vector and a labeled output. When trained, the deep learning model unit 35 can be applied to new unlabeled examples to generate a corresponding score or prediction value.

[0030] FIG. 3 is a block diagram showing an example of a detailed configuration of the deep learning model unit 35 in FIG.

[0031] The deep learning model unit 35 is implemented using a neural network, for example, as shown in FIG. 3. Here, the neural network includes one input layer 41, at least one and preferably multiple hidden layers 42, and one output layer 43. The input layer 41 includes three input neurons 51, 52, and 53, each of which corresponds to three audio feature values ​​(i.e., VSj, TDj, and TGj) of each frame of the feature vector. The hidden layer 42 includes neurons 61-74 having weighting coefficients associated with each input neuron 51, 52, and 53 and biasing coefficients for each neuron. By changing the weighting coefficients and biasing coefficients for each neuron 61-74 of the hidden layer 42 through cycles of a learning phase, the neural network can be trained to report a predicted value for a given type of input. The output layer 43 includes one output neuron 81 that provides a predicted value corresponding to a phoneme (specifically, indicating whether it is a speech period or a noisy non-speech period).

[0032] As described above, in the noise cancellation units 13 and 24, the deep learning model unit 35 learns using the characteristic parameters of human voice and judges whether or not the input voice signal is a non-voice period containing noise. Then, the CPU 31 of the voice signal processing unit 30 performs noise cancellation processing so as not to pass the non-voice period containing noise from the input voice signal based on the judgment of the deep learning model unit 35, and outputs the voice signal after the noise cancellation processing. Here, the deep learning model unit 35 is configured by the neural network of FIG. 3, which receives the characteristic parameters of human voice as input and outputs the judgment result of judging whether or not the input voice signal is a non-voice period containing noise.

[0033] As described above, in this embodiment, the wireless device 1 has a noise canceling unit 24 in its transmission section, which is particularly effective in reducing noise in, for example, FM (frequency modulation) demodulation or PM (phase modulation) demodulation, instead of a phase inversion type noise canceling circuit. This allows a wireless communication device that performs wireless calls to perform noise cancellation so as to output human speech more effectively than the prior art. By providing the noise canceling unit 24 on the transmission side, noise can be effectively removed from audio signals in circuits and devices (e.g., wireless relay devices, etc.) subsequent to the transmission side.

[0034] In this embodiment, the wireless device 1 further includes a noise canceling unit 13 that is particularly effective in reducing noise in the receiving section. This allows the wireless communication device that performs wireless communication to perform noise cancellation so as to effectively output human speech compared to the conventional technology. When FM or PM is used as the modulation method, the demodulated audio signal is passed through the noise canceling unit 13 before being output to the speaker 15, so that white noise when the signal is close to no signal disappears, and the received audio continues to maintain a clear voice even when the communication limit distance is approached. Furthermore, by performing noise cancellation using the noise canceling unit 13 that uses the deep learning model unit 35 instead of the conventional noise squelch circuit, the output of noise in the no-signal state is stopped (or reduced), and the output of the audio signal that can be received is not stopped. Therefore, the audio signal received up to the limit of the communication distance can be output, and the communication distance can be extended compared to the noise squelch circuit.

[0035] (Modification) In the above embodiment, the wireless device 1 includes the noise canceling unit 24. However, the present invention is not limited to this, and the wireless device 1 does not necessarily need to include the noise canceling unit 24. [Industrial Applicability]

[0036] As described above in detail, according to the wireless communication device of the present invention, instead of a phase inversion type noise cancellation circuit, noise cancellation is performed using a noise cancellation unit 13 that utilizes a deep learning model unit 35 on the transmitting side of the radio set 1, or even on the receiving side, thereby making it possible to perform noise cancellation in a wireless communication device that performs wireless calls so as to more effectively output human speech sounds compared to conventional technology. [Explanation of symbols]

[0037] 1 Radio 11 Receiving antenna 12 Reception demodulation section 13 Noise Cancellation Section 14 Audio signal amplifier 15 Speaker 20 Control section 21 Control section 21A PTT key 22 Microphone 23 Audio signal amplifier 24 Noise Cancellation Section 25 Modulation transmitter 26 Transmitting Antenna 30 Audio signal processing section 31 CPU 32 ROM 33 RAM 34 EEPROM 35 Deep Learning Model Division 36 Input Interface 37 Output Interface 38 Audio signal pre-processing unit 39 AD converter 41 Input Layer 42 Middle Class 43 Output layer 51-81 Neurons

Claims

1. A wireless communication device including a modulation transmission unit that modulates a wireless carrier wave in accordance with an input audio signal and transmits a wireless signal, a first noise canceling unit that performs audio signal processing so as to cancel noise from the input audio signal and outputs the processed audio signal to the modulation transmitting unit; The first noise cancellation unit is a wireless communication device that performs noise cancellation processing using a deep learning model unit that is trained using characteristic parameters of human voice, which are vibration frequencies calculated for each predetermined number of frames along the time axis in the input audio signal, and determines whether the input audio signal is a non-voice period containing noise based on a vibration pattern that represents a data distribution of the sum of the vibration frequencies.

2. The wireless communication device according to claim 1 , wherein the modulation transmission unit modulates a wireless carrier wave according to an input audio signal by a frequency modulation method or a phase modulation method.

3. The first noise cancellation unit includes an audio signal processing unit that performs a noise cancellation process based on the determination of the deep learning model unit so as not to pass a non-voice period including noise from the input audio signal, and outputs the audio signal after the noise cancellation process.

3. A wireless communication device according to claim 1 or 2.

4. The first noise cancellation unit includes:

4. The wireless communication device according to claim 3, further comprising an audio signal pre-processing unit provided in front of the audio signal processing unit, which passes only the input audio signal within a predetermined level range of human audio signals and a predetermined bandwidth.

5. The deep learning model unit is configured with a predetermined neural network that inputs characteristic parameters of human voice and outputs a judgment result of whether the input voice signal is a non-voice period containing noise or not. The wireless communication device described in any one of claims 1 to 4.

6. The wireless communication device includes: a receiving and demodulating unit that demodulates a received wireless signal into an audio signal; a second noise canceling unit that performs audio signal processing so as to cancel noise from the demodulated audio signal and outputs the audio signal after the audio signal processing, The wireless communication device according to claim 1 or 2, wherein the second noise cancellation unit performs noise cancellation processing using a deep learning model unit that is trained using characteristic parameters of human voice and determines whether the demodulated voice signal is a non-voice period containing noise.

7. The wireless communication device according to claim 6 , wherein the receiving and demodulating unit demodulates the received wireless signal using a frequency modulation method or a phase modulation method.

8. The second noise cancellation unit includes an audio signal processing unit that performs a noise cancellation process based on the determination of the deep learning model unit so as to pass the audio signal only during an audio signal period from the demodulated audio signal, and outputs the audio signal after the noise cancellation process.

8. A wireless communication device according to claim 6 or 7.

9. The second noise cancellation unit includes: The wireless communication device according to claim 8, further comprising an audio signal pre-processing unit provided in front of the audio signal processing unit, which passes only the input audio signal within a predetermined level range of human audio signals and a predetermined bandwidth.

10. The deep learning model unit is configured with a predetermined neural network that inputs characteristic parameters of human voice and outputs a judgment result of whether or not the input voice signal is a non-voice period containing noise. The wireless communication device described in any one of claims 6 to 9.

11. A wireless communication device that does not simultaneously perform transmission and reception operations, and during reception, the wireless communication device described in any one of claims 6 to 10, operates the first noise cancellation unit instead of the second noise cancellation unit to perform noise cancellation processing during reception.

12. The wireless communication device according to any one of claims 1 to 11, wherein the wireless communication device is a specific low-power wireless station that is a wireless communication device for a specific low-power wireless communication system.

13. A wireless communication system comprising a plurality of wireless communication devices according to any one of claims 1 to 12.

Images