TWM619473U - Voice assistant system - Google Patents

Abstract

A voice assistant system is provided. The voice assistant system includes a microphone module and a signal processor. The microphone module is suitable for being worn on the user, and senses the user's in throat voice through a diaphragm, and generates an analog sound signal in response to the user's in throat voice. The signal processor operates in a keyword detection mode or in a speech reception mode. Power consumption of the signal processor operating in the speech reception mode is greater than power consumption of the signal processor operating in the keyword detection mode. When the signal processor operates in the keyword detection mode, the signal processor performs keyword detection using multiple analog sample voltages of the analog sound signal. In response to detecting a keyword in the keyword detection mode, the signal processor switches from the keyword detection mode to a speech reception mode.

Description

Voice Assistant System

The new creation relates to a voice assistant system, and particularly relates to a voice assistant system with a wireless microphone device.

With the advancement of voice recognition technology, voice assistants have been widely used in the lives of modern people. A voice assistant is a software program running on a terminal device that can communicate with the user by voice to complete tasks assigned by the user, such as information search, electrical control, or other applications that control the terminal device. It is conceivable that if users can use the voice assistant as they like, it can bring great help to life or work. For example, the user can search for information at any time through the voice assistant and obtain the required information in real time. Currently, users all need to clearly and loudly speak voice commands to the radio device in order to smoothly communicate with the voice assistant. However, in some situations where it is necessary to keep quiet, such as a meeting situation or a public environment, it is not suitable for users to speak out voice commands to control the voice assistant in order to avoid disturbing others. In addition, in order for the user to communicate with the voice assistant anytime and anywhere, the user needs to wear a radio device at any time to capture the voice commands issued by the user. Therefore, how to effectively extend the Endurance is also a big test.

In view of this, the present invention provides a voice assistant system, which can greatly save the power consumption of the wireless microphone device and increase the endurance of the wireless microphone device, so that the application range of the voice assistant that receives voice messages through the wireless microphone device can be wider And is not restricted.

The creative embodiment of the present invention proposes a voice assistant system, which includes a microphone module and a signal processor. The microphone module is suitable for being worn on the user, and senses the voice in the user's throat through the diaphragm, and generates an analog sound signal in response to the voice in the user's throat. The diaphragm is connected to the battery and the signal processor. The signal processor operates in a speech radio mode or a keyword detection mode. The power consumption of the signal processor operating in the speech radio mode is higher than the power consumption of the signal processor operating in the keyword detection mode. When the signal processor operates in the keyword detection mode, the signal processor performs keyword detection based on multiple analog sampling voltages of the analog audio signal. In response to the detection of keywords in the keyword detection mode, the signal processor switches from the keyword detection mode to the speech radio mode.

The creative embodiment of the present invention proposes a voice assistant system, which includes a terminal device, a microphone module, and a signal processor. The microphone module is suitable for being worn on the user, and senses the voice in the user's throat through the diaphragm, and generates an analog sound signal in response to the voice in the user's throat. The diaphragm is connected to the battery and the signal processor. The signal processor operates in a speech radio mode or a keyword detection mode. Signal The power consumption of the processor operating in the speech radio mode is higher than the power consumption of the signal processor operating in the keyword detection mode.

When the signal processor operates in the keyword detection mode, the signal processor performs keyword detection based on multiple analog sampling voltages of the analog audio signal. In response to the keyword detection in the keyword detection mode, the signal processor switches from the keyword detection mode to the speech radio mode. After switching to the speech radio mode, the signal processor performs audio processing on the analog audio signal to generate processed digital audio data. The signal processor provides the processed digital audio data to the voice assistant program running on the terminal device.

Based on the above, in the embodiment of the present invention, the signal processor of the voice assistant system can switch between the keyword detection mode and the speech radio mode. When the signal processor of the wireless microphone device operates in the keyword detection mode, the signal processor determines whether the keyword is detected according to the analog audio signal provided by the microphone module when the high power consumption component is disabled. In response to the keyword detection in the keyword detection mode, the signal processor can switch from the keyword detection mode to the speech radio mode to activate the high-power components. Based on this, when the user intends to use the voice assistant to speak a keyword, the wireless microphone device switches from the keyword detection mode to the speech radio mode, so as to use high-power components to perform digital audio on the analog audio signal provided by the microphone module. Processing to prevent high-power components from continuously operating when unnecessary and wasting the power of the wireless microphone device, thereby prolonging the endurance of the wireless microphone device.

In order to make the above-mentioned features and advantages of the new creation more obvious and understandable, the following specific examples are given in conjunction with the accompanying drawings to describe in detail as follows.

10: Voice assistant system

100: Wireless microphone device

200: terminal device

300: headphones

110: Microphone module

111: diaphragm

120: signal processor

130: battery

140: wireless transceiver

121: High-power components

122: analog sampling circuit

123: Analog memory

124: Voice recognition circuit

121a: Power amplifier

121b: Analog-to-digital converter

121c: Digital Signal Processor

Fig. 1 is a schematic diagram of a voice assistant system according to an embodiment of the present invention.

Fig. 2 is a schematic diagram of a usage scenario of a voice assistant system according to an embodiment of the new creation.

Fig. 3 is a schematic diagram of a wireless microphone device according to an embodiment of the invention.

Fig. 4 is a schematic diagram of a voice assistant system according to an embodiment of the present invention.

Fig. 5 is a schematic diagram of a usage scenario of a voice assistant system according to an embodiment of the new creation.

Fig. 6 is a schematic diagram of a wireless microphone device according to an embodiment of the invention.

In order to make the content of the new creation easier to understand, the following specific examples are given as examples on which the new creation can indeed be implemented. In addition, wherever possible, elements/components/steps with the same reference numbers in the drawings and embodiments represent the same or similar components.

It should be understood that when an element is referred to as being "directly on" or "directly connected to" another element, there are no intervening elements. As used herein, "connected" can refer to physical and/or electrical connection. Furthermore, "electrical connection" or "coupling" can be binary There are other components between pieces.

Fig. 1 is a schematic diagram of a voice assistant system according to an embodiment of the present invention. Please refer to FIG. 1, the voice assistant system 10 may include a wireless microphone device 100 and a terminal device 200. The terminal device 200 is used to run a voice assistant program, which is, for example, a desktop computer, a notebook computer, a smart phone, a tablet computer, a smart speaker, etc. The present invention is not limited to this. The wireless microphone device 100 can be connected to the terminal device 200 via wireless communication technology.

For example, the wireless microphone device 100 can be connected to the terminal device 200 via wireless communication technologies such as Bluetooth, Wi-Fi, or ZigBee, and the present invention does not limit the types of wireless communication technologies. The wireless microphone device 100 is used to sense the voice in the user's throat, so that the user can use the wireless microphone device 100 to interact with the voice assistant program run by the terminal device 200.

In this embodiment, the wireless microphone device 100 may include a microphone module 110, a signal processor 120, and a battery 130.

The microphone module 110 is suitable for being worn on the user, and generates an analog sound signal in response to the voice in the throat of the user. The sound in the throat is blessed by sound waves that are not heard by others. The microphone module 110 may include a diaphragm 111 for sensing the user’s vocalization, such as a microelectromechanical system (MEMS) microphone, wherein the diaphragm 111 may be a pressure-sensitive membrane, which is used to respond to the sound produced in the larynx. Vibrate. In an embodiment, the wireless microphone device 100 may be a bone-sensitive microphone with a diaphragm that can sense the vibration of the bones or muscles of the head and neck. The microphone module 110 contacts the user's skin and is suitable for being worn on the user's throat or behind the ear. The microphone module 110 can sense the user A sound made at a very low volume. In another embodiment, the microphone module 110 may also include two diaphragms, and the sizes of the two diaphragms are different. The two diaphragms can be respectively used to sense different frequencies of intra-laryngophonic sound, or the two diaphragms can be respectively used to sense the vibrations of bones or muscles of different parts of the head and neck. Among them, those skilled in the art can determine the number of diaphragms in the microphone module 110 according to the design requirements of the voice assistant system 10, and the present invention is not limited to the number of diaphragms mentioned above.

In more detail, FIG. 2 is a schematic diagram of a usage scenario of the voice assistant system according to an embodiment of the new creation. Please refer to FIG. 2, the wireless microphone device 100 can be worn near the mastoid bone behind the ear of the user. When the user makes a sound, the microphone module 110 can generate an analog sound signal based on the vibration of the user's bones or muscles sensed by the diaphragm 111. Therefore, the microphone module 110 in contact with the user's skin senses the user's utterance, and the user can deliver a voice message to the voice assistant program run by the terminal device 200 at a volume that is not clearly heard by others.

The battery 130 is coupled to the microphone module 110 and the signal processor 120 and is used as a power source for the wireless microphone device 100. In other words, the battery 130 can provide power to the microphone module 110 and the signal processor 120.

The signal processor 120 can be switched to operate in a speech radio mode or a keyword detection mode. The power consumption of the signal processor 120 operating in the speech radio mode is higher than the power consumption of the signal processor operating in the keyword detection mode. In other words, the signal processor 120 can be operated in a speech receiving mode with higher power consumption or in a keyword detection mode with lower power consumption. In one embodiment, the signal processor 120 includes a high power consumption component 121 and receives the analog audio signal generated by the microphone module 110. When the signal processor 120 When operating in the keyword detection mode, the high power consumption component 121 is disabled and stops operating. When the signal processor 120 is operating in the speech radio mode, the high power consumption component 121 is enabled to perform audio processing on the analog audio signal provided by the microphone module 110. In an embodiment, the high power consumption component 121 may include an analog-to-digital converter, a digital signal processor, a power amplifier, or a combination thereof.

Therefore, when the signal processor 120 is operating in the keyword detection mode, the high power consumption component 121 used to perform audio processing on the analog audio signal provided by the microphone module 110 does not consume the power of the battery 130. It should be noted that the signal processor 120 determines whether to switch from the keyword detection mode to the speech radio mode according to whether the user utters the keyword. Therefore, when the user does not speak the keyword, the signal processor 120 will maintain the operation in the keyword detection mode with lower power consumption. When the user utters a keyword, the signal processor 120 will switch to operate in a speech radio mode with higher power consumption. Corresponding to different voice assistant programs, the above-mentioned keywords are, for example, Alexa, Cortana, Hey Siri, OK Google, or other custom keywords, etc., and the creation of the new model is not limited to this.

In one embodiment, when the signal processor 120 is operating in the keyword detection mode, the signal processor 120 can perform keyword detection based on multiple analog sample voltages of the analog audio signal based on an artificial neural network (ANN) . In detail, the signal processor 120 can perform analog signal sampling on the analog audio signal to obtain multiple analog sample voltages. In one embodiment, the signal processor 120 may include an analog artificial intelligence (AI) circuit that implements an artificial neural network, and the artificial neural network is configured to receive multiple analog sample voltages for keyword detection. Measurement. Compared with the digital AI circuit, the analog AI circuit that can realize the analog multiplier and adder has lower power consumption. In other words, the signal processor 120 can continuously detect whether the user utters the keyword by providing multiple analog sampling voltages to the analog AI circuit in the keyword detection mode.

Therefore, in response to detecting the keyword in the keyword detection mode, the signal processor 120 can switch from the keyword detection mode to the speech radio mode to activate the high power consumption element 121. After switching to the speech radio mode, the signal processor 120 can use the high-power component 121 to perform audio processing on the analog audio signal to generate processed digital audio data. The wireless microphone device 100 provides the processed digital audio data to the voice assistant program run by the terminal device 200, so that the voice assistant program can perform related functions based on the processed digital audio data, such as information search, electrical control, or other control of the terminal device 200 Applications and more.

On the other hand, in response to no keywords being detected in the keyword detection mode, the signal processor 120 maintains the operation in the keyword detection mode to disable the high power consumption component 121. In other words, if the user does not say the keyword, the signal processor 120 can maintain the operation in the keyword detection mode for a long time to save power consumption. That is to say, when the user wearing the wireless microphone device 100 does not want to use the voice assistant, the user does not speak the keyword and controls the signal processor 120 of the wireless microphone device 100 to keep operating in the keyword detection mode. middle. When the user wants to use the voice assistant, the user can speak keywords at a very low volume and control the signal processor 120 of the wireless microphone device 100 to switch to operate in the speech radio mode, so that the signal processor 120 operates in the speech radio mode Available for microphone module 110 The analog audio signal is converted from analog to digital and processed with digital audio. In other words, the high-power component 121 is enabled to operate only when the user sends a voice message to the voice assistant, and is disabled for the rest of the time. Therefore, the power consumption of the wireless microphone device 100 in the voice assistant system 10 can be greatly reduced, so that the user can wear the wireless microphone device 100 for a long time without charging the wireless microphone device 100 frequently.

Fig. 3 is a schematic diagram of a wireless microphone device according to an embodiment of the invention. 3, the wireless microphone device 100 may include a microphone module 110, a signal processor 120, a battery 130, and a wireless transceiver 140.

Compared with the embodiment of FIG. 1, in this embodiment, the wireless microphone device 100 may further include a wireless transceiver 140. The wireless transceiver 140 is coupled to the signal processor 120 and establishes a wireless communication link with the terminal device 200. Specifically, the wireless transceiver 140 can be used to transmit data to or receive data from the terminal device 200. The wireless transceiver 140 may include an antenna or other communication-related circuits, such as a Bluetooth transceiver, but the invention is not limited to this. Here, the wireless transceiver 140 can transmit the processed digital audio data generated by the signal processor 120 operating in the speech radio mode to the terminal device 200, so that the voice assistant program run by the terminal device 200 can be based on the processed digital audio data Perform voice recognition to obtain the voice message issued by the user.

In addition, in this embodiment, the signal processor 120 may include an analog sampling circuit 122, an analog memory 123, and a voice recognition circuit 124.

In one embodiment, the analog sampling circuit 122 may include one or more analogs Sampling and holding circuit (analog sampling-and-hold circuit). The analog sampling circuit 122 can sample and hold the analog audio signal according to the sampling frequency, thereby outputting multiple analog sampling voltages that have been sampled and held. In one embodiment, the diaphragm of the microphone module 110 can sense the user's bone or muscle vibration, so that the microphone module 110 outputs analog sound signals to the signal processor 120 accordingly. The analog sampling circuit 122 is coupled to the microphone module 110. The analog sampling circuit 122 receives the analog audio signal generated by the microphone module 110, and samples the analog audio signal to generate a plurality of analog sampling voltages. In one embodiment, the analog sampling circuit 122 may sample the analog audio signal at a sampling frequency of 16 kHz, for example.

The analog memory 123 is coupled to the analog sampling circuit 122 and records multiple analog sampling voltages from the analog sampling circuit 122. In one embodiment, the analog memory 123 may be a charge coupled device (CCD) memory. The analog memory 123 can be a three-phase CCD memory or a four-phase CCD memory, which is not limited by the present invention. In detail, the analog memory 123 can respectively convert multiple analog sampling voltages into corresponding charges, so as to record the respective charges of the multiple analog sampling voltages. Based on the charge transfer effect generated by applying multiple clock signals to multiple gate electrodes on the CCD memory, the analog memory 123 can temporarily store multiple analog sampling voltages in accordance with the sampling order.

Alternatively, in an embodiment, the analog memory 123 may be a phase-change memory (PCM). In detail, multiple analog sampling voltages can be converted into current pulses with corresponding pulse widths, and these current pulses can be applied to the electrodes of multiple memory cells in the analog memory 123, so that each The phase change material in the memory cell undergoes a physical phase change and has a corresponding resistance state. By converting multiple analog sampling voltages into resistance states corresponding to multiple memory cells in the phase change memory, the analog memory 123 can record multiple analog sampling voltages.

In one embodiment, the analog memory 123 can record multiple analog sampling voltages acquired during a predetermined sampling period. The above-mentioned preset sampling period is, for example, 250 ms, but the present invention does not limit this.

The voice recognition circuit 124 is coupled to the analog memory 123. The voice recognition circuit 124 can obtain multiple analog sampling voltages corresponding to a predetermined sampling period from the analog memory 123. The voice recognition circuit 124 can perform feature extraction on these analog sample voltages based on an artificial neural network to determine whether a keyword is detected. It can be seen that the artificial neural network includes multiple neurons arranged in multiple layers, and these neurons perform multiplication and addition operations respectively according to the weight information, and the output of these layers can be regarded as the feature vector extracted. In one embodiment, the speech recognition circuit 124 may include an analog AI circuit that implements an analog multiplier and adder, which can perform analog AI operations on multiple analog sample voltages according to an artificial neural network to perform feature extraction on these analog sample voltages. . Finally, the speech recognition circuit 124 can perform a classification operation based on the feature vectors of these analog sample voltages to determine whether a keyword is detected.

In one embodiment, the keyword may be composed of multiple syllables, and these syllables include at least a first syllable and a second syllable. The voice recognition circuit 124 can determine whether the first sampled voltages of the plurality of analog sampled voltages match the first syllable of the keyword based on the artificial neural network. The first sampling voltage is analogously taken during a preset sampling period The analog memory 123 can simultaneously temporarily store multiple sampling voltages generated by analog sampling in a preset sampling period. For example, based on the fact that it takes about 1/4 second for a person to speak a syllable, it can be assumed that the preset sampling period is 250ms. Assuming that the sampling frequency is 16k HZ (that is, 16k analog sampling voltages are sampled in one second), the first sampling voltage temporarily stored in the analog memory 123 corresponding to the preset sampling period is 4k. First, the first sampled voltage is input to the voice recognition circuit 124, and the voice recognition circuit 124 can determine whether the multiple first sampled voltages match the first syllable of the keyword.

Then, in response to the decision based on the artificial neural network that the first sampled voltage of the multiple analog sampled voltages matches the first syllable of the keyword, the speech recognition circuit 124 can determine the multiple second ones of the analog sampled voltages based on the artificial neural network. Whether the sampling voltage matches the second syllable of the keyword. Conversely, in response to the decision based on the artificial neural network that the first sampled voltage of the multiple analog sampled voltages does not match the first syllable of the keyword, the speech recognition circuit 124 will again determine the multiple of the analog sampled voltages based on the artificial neural network. Whether the second sampling voltage matches the first syllable of the keyword.

In one embodiment, the speech recognition circuit 124 uses the first neural network weight data to determine whether the first sampled voltage among the plurality of analog sampled voltages matches the first syllable of the keyword. In addition, the speech recognition circuit 124 uses the second neural network weight data to determine whether the second sampling voltage of the plurality of analog sampling voltages matches the second syllable of the keyword. That is, corresponding to the first syllable and the second syllable of different pronunciations, the speech recognition circuit 124 can use different trained neural network weight data to make a judgment.

In other words, when the voice recognition circuit 124 determines that multiple first sampled voltages When it matches the first syllable of the keyword, the speech recognition circuit 124 will continue to determine whether other subsequent sampled voltages match the second syllable of the keyword. Otherwise, the speech recognition circuit 124 will continue to determine whether the analog sampling voltage temporarily stored in the analog memory 123 matches the first syllable of the keyword. In other words, in one embodiment, when the voice recognition circuit 124 determines that the analog sampling voltage matches multiple syllables of the keyword in a specific order based on the artificial neural network, the voice recognition circuit 124 determines that the keyword is detected.

For example, taking the keyword "ok! google" as an example, this keyword would include 4 syllables "o", "k", "goo", and "gle". The speech recognition circuit 124 may first determine whether the first to i-th analog sampled voltages match the first syllable "o" of the keyword according to the first neural network weight data corresponding to "o". If so, the speech recognition circuit 124 can determine whether the (i+1)th to 2ith analog sampling voltages match the second syllable "k" of the keyword according to the second neural network weight data corresponding to "k". If not, the speech recognition circuit 124 can again determine whether the (i+1)th to 2ith analog sampling voltages match the first syllable of the keyword "o" according to the first neural network weight data corresponding to "o". .

If the voice recognition circuit 124 determines that the (i+1)th to 2ith analog sampling voltages do not match the second syllable "k" of the keyword, the speech recognition circuit 124 can again rely on the first neural network corresponding to "o" The weight data is used to determine whether the (2i+1)th to 3ith analog sampling voltages match the first syllable "o" of the keyword. If the speech recognition circuit 124 determines that the (i+1)th to 2ith analog sampling voltages match the second syllable "k" of the keyword, the speech recognition circuit 124 can then base on the third neural network weight corresponding to "goo" Data to determine whether the analog sampling voltage from the (2i+1)th to the 3ith The third syllable of the key word "goo".

If the voice recognition circuit 124 determines that the (2i+1)th to 3ith analog sampling voltages do not match the third syllable "goo" of the keyword, the voice recognition circuit 124 can again rely on the first neural network corresponding to "o" The weight data is used to determine whether the (3i+1)th to 4ith analog sampling voltages match the first syllable "o" of the keyword. If the speech recognition circuit 124 determines that the (2i+1)th to 3ith analog sample voltages match the third syllable of the keyword "goo", the speech recognition circuit 124 can then base on the fourth neural network weight corresponding to "gle" The data is used to determine whether the analog sampling voltage from the (3i+1)th to the 4ith matches the fourth syllable "gle" of the keyword.

If the speech recognition circuit 124 determines that the (3i+1)th to 4ith analog sampling voltages do not match the fourth syllable "gle" of the keyword, the speech recognition circuit 124 can again rely on the first neural network corresponding to "o" The weight data is used to determine whether the (4i+1)th to 5ith analog sampling voltages match the first syllable "o" of the keyword. If the voice recognition circuit 124 determines that the (3i+1)th to 4ith analog sample voltages match the fourth syllable of the keyword "gle", the voice recognition circuit 124 may determine that the keyword "ok! google" is detected.

In one embodiment, if the voice recognition circuit 124 determines that the keyword is not detected, the signal processor 120 can maintain the operation in the keyword detection mode. In contrast, if the voice recognition circuit 124 determines that a keyword is detected, the signal processor 120 can switch from the keyword detection mode to the speech radio mode to enable the high power consumption component 121.

For example, in one embodiment, the voice recognition circuit 124 can provide a notification signal to the power control circuit in the signal processor 120 so that the power control circuit can decide whether to supply power from the battery 130 to the high power consumption component 121. It can be seen that the class The ratio sampling circuit 122, the analog memory 123, and the voice recognition circuit 124 can continuously detect whether the user utters a keyword in the keyword detection mode. When the voice recognition circuit 124 determines that the keyword is detected, the wireless microphone device 100 uses the high-power component 121 to process the analog audio signal and transmit the processed digital audio data to the terminal device 200.

Fig. 4 is a schematic diagram of a voice assistant system according to an embodiment of the present invention. Fig. 5 is a schematic diagram of a usage scenario of a voice assistant system according to an embodiment of the new creation. Referring to FIGS. 4 and 5, in addition to the wireless microphone device 100 and the terminal device 200 similar to the embodiment of FIG. 1, the voice assistant system 10 may further include a headset 300. The earphone 300 is suitable for being worn on the ear of a user and can play audio data from the terminal device 200.

In one embodiment, when the user does not intend to use the voice assistant program, even if the user keeps talking, the signal processor 120 of the wireless microphone device 100 still operates in the keyword detection mode without wasting power. Perform digital audio processing and transmit data to the terminal device 200. When the user wants to use the voice assistant program to search for data, the user can speak the key words at a very low volume. In response to the detection of the keyword, the signal processor 120 operating in the keyword detection mode in the wireless microphone device 100 can be switched to operate in the speech radio mode to activate the high power consumption component 121.

Then, the user can speak the question at a very low volume. At this time, the high-power component 121 has been activated to perform audio processing on the analog audio signal to generate processed digital audio data. The processed digital audio data can be sent to the terminal device 200, As a result, the voice assistant of the terminal device 200 can perform voice recognition and perform information search based on the processed digital audio data. Finally, the terminal device 200 can return the answer to the user's question to the earphone 300, and the earphone 300 can play the answer to the user. In this case, the user can use the voice assistant to query data without disturbing others or even without being aware of them.

Fig. 6 is a schematic diagram of a wireless microphone device according to an embodiment of the invention. Referring to FIG. 6, compared with the embodiment in FIG. 3, in this embodiment, the high power consumption component 121 may include a power amplifier 121a, an analog-to-digital converter 121b, and a digital signal processor 121c. The power amplifier 121a, the analog-to-digital converter 121b, and the digital signal processor 121c are used to generate processed digital audio data according to the analog audio signal provided by the microphone module 110.

Compared with the analog sampling circuit 122, the analog memory 123, and the speech recognition circuit 124, the operation of the power amplifier 121a, the analog-to-digital converter 121b, and the digital signal processor 121c requires relatively high power consumption. However, since the power amplifier 121a, the analog-to-digital converter 121b, and the digital signal processor 121c of the creative embodiment of the present invention can only be activated in the speech radio mode, the endurance of the wireless microphone device 100 can be greatly improved.

In summary, in the creative embodiment of the present invention, the wireless microphone device can maintain operation in the keyword detection mode when the user does not speak the keyword, and use the analog circuit with lower power consumption to detect the usage. Whether the person said the key words. In response to the user uttering a keyword, the wireless microphone device switches to operate in the speech radio mode to enable high-power components. Then, the wireless microphone device can use high-power The consumer performs digital audio processing to generate processed audio data, and then sends the processed audio data to the terminal device. Based on this, the high-power components will only be activated when needed to consume power, so that the wireless microphone device will not quickly use up the battery power, thereby greatly extending the endurance of the wireless microphone device. In this way, the application range of the voice assistant program used with the wireless microphone device can be more unrestricted, and the user can use the voice assistant more freely.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the new creation, not to limit it; although the new creation is described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand : It can still modify the technical solutions recorded in the foregoing embodiments, or equivalently replace some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the various embodiments of the invention The scope of the technical solution.

10: Voice assistant system

100: Wireless microphone device

200: terminal device

110: Microphone module

111: diaphragm

120: signal processor

130: battery

121: High-power components

Claims (34)

A voice assistant system includes: a microphone module adapted to be worn on a user, and through a diaphragm to sense the voice in the user’s throat, and to respond to the user’s throat Internal sound generation generates an analog sound signal; and a signal processor operating in a speech radio mode or a keyword detection mode, wherein the power consumption of the signal processor operating in the speech radio mode is higher than that of the signal processing The power consumption of the device operating in the keyword detection mode, wherein, when the signal processor is operating in the keyword detection mode, the signal processor performs keywords based on multiple analog sample voltages of the analog audio signal The detection is in response to detecting a keyword in the keyword detection mode, and the signal processor switches from the keyword detection mode to the speech radio mode. The voice assistant system according to claim 1, wherein the microphone module is in contact with the skin of the user and is suitable for being worn on the throat or behind the ear of the user. The voice assistant system according to claim 1, wherein the voice in the throat is a sound wave that cannot be heard by others. The voice assistant system according to claim 1, wherein the signal processor is based on an artificial neural network to perform the keyword detection based on a plurality of analog sampling voltages of the analog audio signal. The voice assistant system according to claim 1, wherein the signal processor includes a high power consumption component, and the signal processor switches from the keyword detection mode to the speech radio mode to activate the high power consumption element. The voice assistant system according to claim 5, wherein in response to the keyword detection mode not detecting the keyword, the signal processor maintains operation in the keyword detection mode and disables the high Power components. The voice assistant system according to claim 5, wherein after switching to the speech radio mode, the signal processor uses the high-power component to perform audio processing on the analog sound signal to generate processed digital audio data . The voice assistant system according to claim 5, wherein the high power consumption component includes an analog-to-digital converter, a digital signal processor, a power amplifier, or a combination thereof. The voice assistant system according to claim 1, further comprising: a wireless transceiver, coupled to the signal processor, to establish a wireless communication link with a terminal device to connect the signal operating in the speech radio mode The processed digital audio data generated by the processor is transmitted to the terminal device. The voice assistant system according to claim 1, wherein the signal processor includes: a voice recognition circuit that performs feature extraction on the analog sampled voltage based on an artificial neural network to determine whether the key is detected word. The voice assistant system according to claim 10, wherein the signal processor further includes: An analog sampling circuit is coupled to the microphone module to sample the analog audio signal to generate a plurality of analog sampling voltages; and an analog memory is coupled to the analog sampling circuit to record the analog sampling voltage. The voice assistant system according to claim 11, wherein the analog memory includes a charge coupled device (CCD) memory or a phase-change memory (PCM). The voice assistant system according to claim 10, wherein the voice recognition circuit determines whether multiple first sample voltages in the analog sample voltage match the first syllable of the keyword based on the artificial neural network, wherein , In response to determining based on the artificial neural network that the first sampled voltage in the analog sampled voltage matches the first syllable of the keyword, the speech recognition circuit determines the first syllable based on the artificial neural network Whether the multiple second sampling voltages in the analog sampling voltage match the second syllable of the keyword. The voice assistant system according to claim 13, wherein the voice recognition circuit uses the first neural network weight data to determine whether the first sampled voltage in the analog sampled voltage matches the first sampled voltage of the keyword And use the second neural network weight data to determine whether the second sampled voltage in the analog sampled voltage matches the second syllable of the keyword. The voice assistant system according to claim 10, wherein when the voice recognition circuit determines based on the artificial neural network that the analog sampling voltage is in accordance with a If the specific sequence matches the multiple syllables of the keyword, the speech recognition circuit determines that the keyword is detected. The voice assistant system according to claim 1, wherein the diaphragm is a pressure-sensitive membrane, and is used to generate vibration in response to sound produced in the throat. The voice assistant system according to claim 1, further comprising another diaphragm, and the diaphragm is different in size from the another diaphragm. A voice assistant system includes: a terminal device; a microphone module, suitable for being worn on a user, and through a diaphragm to sense the voice in the throat of the user, and respond to the user The voice in the throat generates an analog sound signal; and a signal processor operating in a speech radio mode or a keyword detection mode, wherein the power consumption of the signal processor operating in the speech radio mode is higher than The power consumption of the signal processor operating in the keyword detection mode, wherein, when the signal processor operates in the keyword detection mode, the signal processor is based on multiple analog samples of the analog audio signal The voltage performs keyword detection, in response to detecting a keyword in the keyword detection mode, the signal processor switches from the keyword detection mode to the speech radio mode, and then switches to the speech radio mode After that, the signal processor performs audio processing on the analog audio signal to generate processed digital audio data, wherein the signal processor provides the processed digital audio data to all A voice assistant program run by the terminal device. The voice assistant system according to claim 18, wherein the microphone module is in contact with the skin of the user and is suitable for being worn on the throat or behind the ears of the user. The voice assistant system according to claim 18, wherein the voice in the throat is a blessing of sound waves that cannot be heard by others. The voice assistant system according to claim 18, wherein the signal processor is based on an artificial neural network to perform the keyword detection based on multiple analog sample voltages of the analog sound signal. The voice assistant system according to claim 18, wherein the signal processor includes a high power consumption component, and the signal processor switches from the keyword detection mode to the speech radio mode to activate the high power consumption element. The voice assistant system according to claim 22, wherein in response to the keyword detection mode not detecting the keyword, the signal processor maintains operation in the keyword detection mode and disables the high Power components. The voice assistant system according to claim 22, wherein after switching to the speech radio mode, the signal processor uses the high power consumption component to perform the audio processing on the analog sound signal. The voice assistant system according to claim 22, wherein the high power consumption component includes an analog-to-digital converter, a digital signal processor, a power amplifier, or a combination thereof. The voice assistant system according to claim 18, which further includes a wireless transceiver, the wireless transceiver is coupled to the signal processor and establishes a wireless communication link with the terminal device, so as to operate on the speech radio The processed digital audio data generated by the signal processor in the mode is transmitted to the terminal device. The voice assistant system according to claim 18, wherein the signal processor includes: a voice recognition circuit that performs feature extraction on the analog sampled voltage based on an artificial neural network to determine whether the key is detected word. The voice assistant system according to claim 27, wherein the signal processor further includes: an analog sampling circuit, coupled to the microphone module, to sample the analog sound signal to generate a plurality of analog sampling voltages; and an analog A memory, coupled to the analog sampling circuit, records the analog sampling voltage. The voice assistant system according to claim 28, wherein the analog memory includes a charge coupled device (CCD) memory or a phase-change memory (PCM). The voice assistant system according to claim 27, wherein the voice recognition circuit determines whether a plurality of first sampled voltages in the analog sampled voltage match the first syllable of the keyword based on the artificial neural network, wherein , In response to determining based on the artificial neural network that the first sampled voltage in the analog sampled voltage matches the first syllable of the keyword, the language The sound recognition circuit determines whether multiple second sample voltages in the analog sample voltage match the second syllable of the keyword based on the artificial neural network. The voice assistant system according to claim 30, wherein the voice recognition circuit uses the first neural network weight data to determine whether the first sampling voltage in the analog sampling voltage matches the first sampling voltage of the keyword And use the second neural network weight data to determine whether the second sampled voltage in the analog sampled voltage matches the second syllable of the keyword. The voice assistant system according to claim 27, wherein when the voice recognition circuit determines based on the artificial neural network that the analog sampling voltage matches the multiple syllables of the keyword in a specific order, the voice recognition circuit It is determined that the keyword is detected. The voice assistant system according to claim 18, wherein the diaphragm is a pressure-sensitive membrane, and is used to generate vibration in response to sound produced in the throat. The voice assistant system according to claim 18 further includes another diaphragm, and the size of the diaphragm is different from the another diaphragm.

Images