Speech recognition system and radio equipment

Abstract

The utility model discloses a voice recognition system and radio equipment, relates to the technical field of voice recognition, and discloses a voice recognition system, which comprises a main control chip and a CAT1 chip which are connected with each other, and the main control chip is also connected with peripheral equipment; the main control chip is used for receiving voice input by the peripheral equipment, generating a corresponding audio stream and sending the audio stream to the CAT1 chip; the CAT1 chip is used for performing voice recognition on the audio stream to obtain a voice recognition signal and feeding back the voice recognition signal to the main control chip; and the main control chip is also used for analyzing the voice recognition signal to obtain a voice command signal and executing the voice command signal.

Description

Technical Field

[0001] The utility model relates to the technical field of speech recognition, in particular to a speech recognition system and a sound collection device. Background Art

[0002] In the current application of speech recognition technology, most devices rely on high-performance chips to achieve accurate and fast speech recognition functions. First of all, high-performance chips consume a large amount of energy, which is a heavy burden for devices that need to run for a long time or rely on battery power. Secondly, due to the complexity of high-performance chips, the overall volume and weight of the devices also increase, limiting their application in portable or miniaturized devices.

[0003] The CAT1 chip, as a medium and low rate communication chip, has the advantages of low power consumption and high stability, and is widely used in Internet of Things devices. Applying it to speech recognition technology and using its functions more in the aspect of recognition operation can free up more CPU computing power for the main control chip to support other functions, effectively solving the above problems. Summary of the Utility Model

[0004] The main purpose of the utility model is to provide a speech recognition system and a sound collection device, aiming to solve the technical problem that high-performance chips are complex and have limited application scenarios.

[0005] To achieve the above purpose, the utility model proposes a speech recognition system, which includes:

[0006] A main control chip and a CAT1 chip connected to each other, and the main control chip is also connected to peripheral devices;

[0007] The main control chip is used to receive the voice input by the peripheral device to generate a corresponding audio stream, and send the audio stream to the CAT1 chip;

[0008] The CAT1 chip is used to perform speech recognition on the audio stream to obtain a speech recognition signal, and feedback the speech recognition signal to the main control chip;

[0009] The main control chip is also used to parse the speech recognition signal to obtain a speech command signal and execute the speech command signal.

[0010] Optionally, the main control chip includes:

[0011] An acquisition module, a generation module, an analysis module and an execution module;

[0012] The acquisition module is connected to the generation module; the generation module is connected to the CAT1 chip; the analysis module is respectively connected to the CAT1 chip and the execution module;

[0013] The acquisition module is used to acquire the voice input by the peripheral device;

[0014] The generation module is used to generate a corresponding audio stream from the voice;

[0015] The parsing module is used to parse the voice recognition signal to obtain the voice command signal;

[0016] The execution module is used to execute the voice command signal.

[0017] Optionally, the CAT1 chip includes:

[0018] An identification module and a feedback module;

[0019] The identification module is respectively connected to the generation module and the feedback module; the feedback module is connected to the parsing module;

[0020] The identification module is used to perform voice recognition on the audio stream to obtain the voice recognition signal;

[0021] The feedback module is used to feedback the voice recognition signal to the main control chip.

[0022] Optionally, the acquisition module includes; a microphone and an analog-to-digital converter;

[0023] The microphone is connected to the analog-to-digital converter; the analog-to-digital converter is connected to the generation module;

[0024] The microphone is used to convert the sound signal into an analog electrical signal;

[0025] The analog-to-digital converter is used to convert the analog electrical signal into a digital audio signal.

[0026] Optionally, the generation module includes;

[0027] A digital audio processor and an audio stream generator;

[0028] The digital audio processor is connected to the audio stream generator; the audio stream generator is connected to the identification module;

[0029] The digital audio processor is used to receive and decode the digital audio signal;

[0030] The audio stream generator is used to package the decoded digital audio signal into a continuous audio stream.

[0031] Optionally, the identification module includes;

[0032] A filter and a first decoder;

[0033] The filter is connected to the first decoder; the first decoder is connected to the feedback module;

[0034] The filter is used to remove unnecessary frequency components in the audio stream to obtain a filtered audio stream;

[0035] The first decoder is used to decode the filtered audio stream to obtain the speech recognition signal and transmit the speech recognition signal to the feedback module.

[0036] Optionally, the feedback module includes;

[0037] A first controller;

[0038] The first controller is connected to the parsing module;

[0039] The first controller is used to pack the speech recognition signal after receiving it and transmit the packed speech recognition signal to the parsing module.

[0040] Optionally, the parsing module includes;

[0041] A second decoder;

[0042] The second decoder is connected to the execution module;

[0043] The second decoder is used to parse the speech recognition signal to obtain the speech command signal.

[0044] Optionally, the execution module includes;

[0045] A second controller;

[0046] The second controller is connected to the peripheral device;

[0047] The second controller is used to execute the speech command signal.

[0048] The present utility model also provides a sound receiving device, and the sound receiving device includes the speech recognition system described above.

[0049] One or more technical solutions provided by the present utility model have at least the following technical effects:

[0050] The present utility model discloses a voice recognition system and a sound collection device, relating to the technical field of voice recognition. A voice recognition system is disclosed, including: a main control chip and a CAT1 chip connected to each other, and the main control chip is further connected to a peripheral device; the main control chip is configured to receive voice input by the peripheral device to generate a corresponding audio stream, and send the audio stream to the CAT1 chip; the CAT1 chip is configured to perform voice recognition on the audio stream to obtain a voice recognition signal, and feedback the voice recognition signal to the main control chip; the main control chip is further configured to parse the voice recognition signal to obtain a voice command signal, and execute the voice command signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present utility model, and are used together with the specification to explain the principles of the present utility model.

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present utility model or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a first structural schematic diagram of an embodiment of the voice recognition system of the present utility model;

[0054] Figure 2 It is a second structural schematic diagram of an embodiment of the voice recognition system of the present utility model;

[0055] Figure 3 It is a third structural schematic diagram of an embodiment of the voice recognition system of the present utility model.

[0056] Explanation of the reference numerals in the drawings:

[0057] 1. Main control chip; 2. CAT1 chip; 3. Peripheral device; 11. Acquisition module; 12. Generation module; 13. Parsing module; 14. Execution module; 21. Recognition module; 22. Feedback module; 111. Microphone; 112. Analog-to-digital converter; 121. Digital audio processor; 122. Audio stream generator; 131. Second decoder; 141. Second controller; 211. Filter; 212. First decoder; 221. First controller.

[0058] The realization of the purpose, functional features and advantages of the present utility model will be further described with reference to the embodiments and the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] Next, the technical solutions in the embodiments of the present utility model will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present utility model. Obviously, the described embodiments are only a part of the embodiments of the present utility model, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present utility model without making creative efforts belong to the scope of protection of the present utility model.

[0060] It should be noted that if there are directional indications (such as up, down, left, right, front, back,...) involved in the embodiments of the present utility model, then the directional indications are only used to explain the relative positional relationship and movement conditions between components in a certain specific posture. If this specific posture changes, then the directional indications will also change accordingly.

[0061] In addition, if there are descriptions such as "first", "second", etc. involved in the embodiments of the present utility model, then the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second" may explicitly or implicitly include at least one such feature. In addition, if "and / or" or "and / or" appears throughout the text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, or solution B, or the solution where A and B are satisfied simultaneously. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present utility model.

[0062] The present utility model proposes a voice recognition system.

[0063] Refer to Figure 1 , Figure 1 which is the first structural schematic diagram of the embodiment of the voice recognition system of the present utility model.

[0064] In this embodiment, considering that most devices in the prior art rely on high-performance chips to implement the voice recognition function, and since the required running time and power supply of high-performance devices are a heavy burden for many devices, the present utility model adds a CAT1 chip to solve this problem. The voice recognition system includes: a main control chip 1 and a CAT1 chip 2 connected to each other, and the main control chip 1 is also connected to a peripheral device 3;

[0065] The main control chip 1 is configured to receive the voice input by the peripheral device 3 to generate a corresponding audio stream, and send the audio stream to the CAT1 chip 2;

[0066] The CAT1 chip 2 is used to perform speech recognition on the audio stream to obtain a speech recognition signal, and feedback the speech recognition signal to the main control chip 1;

[0067] The main control chip 1 is further configured to parse the speech recognition signal to obtain a speech command signal and execute the speech command signal.

[0068] It should be noted that the main control chip can be STMicroelectronics, or Microchip, etc., and this embodiment does not limit this;

[0069] It should be noted that the CAT1 chip can be ASR1606, or V8850, etc., and this embodiment does not limit this;

[0070] It should be noted that the peripheral device can be MIC hardware, camera, T card, etc., and this embodiment does not limit this.

[0071] In specific implementation, the peripheral device 3 first reads the speech input by the user and transmits the speech to the main control chip 1. After receiving the speech, the main control chip 1 generates the corresponding audio stream and transmits the audio stream to the CAT1 chip 2. After receiving the audio stream, the CAT1 chip 2 performs speech recognition on it to obtain the speech recognition signal, and feedbacks the speech recognition signal to the main control chip 1. After receiving the speech recognition signal, the main control chip 1 parses it to obtain the speech command signal, and finally executes the instruction of the speech command signal.

[0072] In this embodiment, the main control chip 1 is used to produce the audio stream and execute the speech command signal, giving more space to the CAT1 chip 2 for recognizing the audio stream. Through the combination of the main control chip 1 and the CAT1 chip 2, the entire speech recognition process is completed more efficiently.

[0073] Reference Figure 2 , Figure 2 is the second structural schematic diagram of the embodiment of the speech recognition system of the present invention.

[0074] Since the addition of the CAT1 chip 2 provides more CPU computing power space for the main control chip 1, the main control chip 1 needs to perform more tasks. The main control chip 1 includes: a collection module 11, a generation module 12, an analysis module 13, and an execution module 14;

[0075] The acquisition module 11 is connected to the generation module 12; the generation module 12 is connected to the CAT1 chip 2; the parsing module 13 is respectively connected to the CAT1 chip 1 and the execution module 14;

[0076] The acquisition module 11 is configured to acquire the voice input by the peripheral device;

[0077] The generation module 12 is configured to generate a corresponding audio stream from the voice;

[0078] The parsing module 13 is configured to parse the voice recognition signal to obtain the voice command signal;

[0079] The execution module 14 is configured to execute the voice command signal.

[0080] In a specific implementation, the acquisition module 11 first acquires and processes the voice input by the peripheral device, and transmits the acquired voice to the generation module 12. The generation module 12 will process the acquired voice again and generate the corresponding audio stream, and then transmit the audio stream to the CAT1 chip 2 for recognition work. After the CAT1 chip 2 completes the recognition, the generated voice recognition signal is transmitted to the parsing module 13. The parsing module 13 parses the voice recognition signal to obtain the voice command signal, and transmits the voice command signal to the execution module 14 for execution.

[0081] In this embodiment, by adding the work of parsing and execution to the main control chip 1, the workload of the main control chip 1 is increased, thereby giving the CAT1 chip 2 more voice recognition operation space, and maximizing the application of the CPU computing power of the main control chip 1 and the CAT1 chip 2.

[0082] Reference Figure 2 , Figure 2 is the second structural schematic diagram of the embodiment of the voice recognition system of the present utility model.

[0083] Since the main control chip 1 supports the CPU computing power to other functions, the CAT1 chip 2 can better exert its computing power to support the recognition work of the audio stream. The CAT1 chip includes: a recognition module 21 and a feedback module 22;

[0084] The recognition module 21 is respectively connected to the generation module 12 and the feedback module 22; the feedback module 22 is connected to the parsing module 13;

[0085] The recognition module 21 is configured to perform voice recognition on the audio stream to obtain a voice recognition signal;

[0086] The feedback module 22 is configured to feed back the voice recognition signal to the main control chip.

[0087] In a specific implementation, after receiving the audio stream, the recognition module 21 performs voice recognition operations on it to obtain the voice recognition signal, and transmits the voice recognition signal to the feedback module 22. After receiving the voice recognition signal, the feedback module 22 feeds back the voice recognition signal to the main control chip 1 for subsequent operations.

[0088] In this embodiment, by concentrating the CPU computing power of the CAT1 chip 2 on the recognition of the audio stream, the computing efficiency is greatly improved, and the CPU computing power space of the main control chip 1 is increased.

[0089] Reference Figure 3 , Figure 3 is the third structural schematic diagram of the embodiment of the voice recognition system of the present invention.

[0090] When the peripheral device 3 obtains the voice input by the user, the main control chip 1 needs to collect and process the input voice. The collection module includes a microphone 111 and an analog-to-digital converter 112;

[0091] The microphone 111 is connected to the analog-to-digital converter 112; the analog-to-digital converter 112 is connected to the generation module 12;

[0092] The microphone 111 is configured to convert the sound signal into an analog electrical signal;

[0093] The analog-to-digital converter 112 is configured to convert the analog electrical signal into a digital audio signal.

[0094] It should be noted that the microphone 111 can be an external microphone or an internal microphone, etc., and this embodiment does not limit this;

[0095] It should be noted that the analog-to-digital converter can be a direct ADC or an indirect ADC, etc., and this embodiment does not limit this.

[0096] In a specific implementation, when the peripheral device 3 obtains the user's voice, the microphone 111 in the collection module 12 converts the sound signal in the voice into the analog electrical signal and gives it to the analog-to-digital converter 112, and the analog-to-digital converter 112 then converts the analog electrical signal into the digital audio signal.

[0097] In this embodiment, the collection module 11 quickly converts the user's voice into the digital audio signal that can be internally processed through the cooperation of the microphone 111 and the analog-to-digital converter 112.

[0098] Reference Figure 3 , Figure 3 is the third structural schematic diagram of the embodiment of the voice recognition system of the present utility model.

[0099] Since the CAT1 chip 2 can only identify and process the audio stream, the main control chip 1 also needs to further process the obtained digital audio signal to generate the audio stream. The generation module 12 includes a digital audio processor 121 and an audio stream generator 122;

[0100] The digital audio processor 121 is connected to the audio stream generator 122; the audio stream generator 122 is connected to the recognition module 21;

[0101] The digital audio processor 121 is configured to receive and decode the digital audio signal;

[0102] The audio stream generator 122 is configured to pack the decoded digital audio signal into a continuous audio stream.

[0103] It should be noted that the digital audio processor 121 can be a simple speaker processor or a multi-functional digital audio processor, etc., and this embodiment does not limit this;

[0104] It should be noted that the audio stream generator can be an audio DSP or a reverberator, etc., and this embodiment does not limit this.

[0105] In specific implementation, when the digital audio processor 121 receives the digital audio signal, it decodes it and transmits it to the audio stream generator 122, and the audio stream generator 122 packs the decoded digital audio signal into a continuous audio stream.

[0106] In this embodiment, the digital audio processor 121 and the audio stream generator 122 process the digital audio signal to obtain the audio stream. At this time, the first-stage work of the main control chip 1 is completed.

[0107] Reference Figure 3 , Figure 3 is the third structural schematic diagram of the embodiment of the voice recognition system of the present utility model.

[0108] After the first-stage work of the main control chip 1 is completed, the CAT1 chip 2 needs to identify and process the obtained audio stream. The recognition module 21 includes a filter 211 and a first decoder 212;

[0109] The filter 211 is connected to the first decoder 212; the first decoder 212 is connected to the feedback module 22;

[0110] The filter 211 is configured to remove unnecessary frequency components from the audio stream to obtain a filtered audio stream;

[0111] The first decoder 212 is configured to decode the filtered audio stream to obtain the speech recognition signal and transmit the speech recognition signal to the feedback module 22.

[0112] It should be noted that the filter 211 can be a low-pass filter or a high-pass filter, etc., and this embodiment does not limit this;

[0113] It should be noted that the first decoder 212 can be a professional audio decoder or an embedded decoder, etc., and this embodiment does not limit this.

[0114] In a specific implementation, when the recognition module 21 receives the audio stream, the filter 211 first filters the audio stream to obtain the filtered audio stream, and then transmits the filtered audio stream to the first decoder 212 for decoding to obtain the speech recognition signal, and transmits the speech recognition signal to the feedback module.

[0115] In this embodiment, the filter 211 and the first decoder 212 in the recognition module 21 efficiently process the audio stream to obtain the speech recognition signal, preparing for the second-stage work of the main control chip 1.

[0116] Reference Figure 3 , Figure 3 is the third structural schematic diagram of the embodiment of the speech recognition system of the present utility model.

[0117] The first-stage work of the CAT1 chip 2 is to perform recognition processing on the audio stream. After completion, the second-stage work is carried out, the recognized audio stream is packaged, and it is fed back and transmitted to the main control chip 1 to support the main control chip 1 to carry out the second-stage work. The feedback module 22 includes: a first controller 221;

[0118] The first controller 221 is connected to the parsing module 13;

[0119] The first controller 221 is configured to package the speech recognition signal after receiving it and transmit the packaged speech recognition signal to the parsing module.

[0120] It should be noted that the first controller 221 can be an intelligent voice controller or an embedded voice recognition controller, and this embodiment does not limit this.

[0121] In specific implementation, after receiving the voice recognition signal, the first controller 221 packs it and transmits the packed voice recognition signal to the parsing module 13. At this time, the second-stage work of the CAT1 chip 2 is completed.

[0122] In this embodiment, the task of the CAT1 chip 2 ends during the entire voice recognition process. The first controller 221 packs the voice recognition signal and feeds it back to the main control chip 1, saving a large amount of CPU computing power space for the main control chip 1 throughout the process.

[0123] Reference Figure 3 , Figure 3 is the third structural schematic diagram of the voice recognition system embodiment of the present utility model.

[0124] After the work of the CAT1 chip 2 ends, the main control chip 1 starts the second-stage work and needs to parse the packed voice recognition signal. The parsing module 13 includes: a second decoder 131;

[0125] The second decoder 131 is connected to the execution module 14;

[0126] The second decoder 131 is used to parse the voice recognition signal to obtain the voice command signal.

[0127] It should be noted that the first decoder 131 can be a professional audio decoder or an embedded decoder, and this embodiment does not limit this.

[0128] In specific implementation, after receiving the voice recognition signal, the second decoder 131 decodes it to obtain the finally required voice command signal, which is the finally required command signal obtained from the voice input by the user.

[0129] In this embodiment, the second decoder 131 decodes the voice recognition signal to obtain the voice command signal. Due to the addition of the CAT1 chip 2, the audio stream in the whole process is processed, saving a large amount of space for the CPU computing power of the main control chip 1. Therefore, the second decoder 131 has a very high efficiency when decoding the voice recognition signal.

[0130] Reference Figure 3 , Figure 3 is the third structural schematic diagram of the voice recognition system embodiment of the present utility model.

[0131] After obtaining the voice command signal, only the main control chip 1 needs to perform the last step. The execution module 14 includes: a second controller 141;

[0132] The second controller 141 is connected to the peripheral device;

[0133] The second controller 141 is used to execute the voice command signal.

[0134] It should be noted that the second controller 141 can be an intelligent voice controller or an embedded voice recognition controller, and this embodiment does not limit this.

[0135] In specific implementation, after receiving the voice command signal, the second controller 141 directly executes the command content.

[0136] In this embodiment, through the cooperation of other modules in the main control chip 1 and the CAT1 chip 2, the entire voice recognition process can be efficiently executed. This is due to the help of the CAT1 chip 2 in the audio stream recognition process, enabling the entire main control chip 1 to be more efficient in the operation process in other aspects.

[0137] In addition, to achieve the above object, the present utility model also proposes a sound receiving device, and the sound receiving device includes the voice recognition system as described above. Other embodiments or specific implementation manners of the sound receiving device of the present utility model can refer to the embodiments of the above voice recognition system, and will not be elaborated here.

[0138] The above are only exemplary embodiments of the present utility model, and do not limit the patent scope of the present utility model accordingly. All equivalent structural transformations made under the technical concept of the present utility model by using the content of the specification and drawings of the present utility model, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present utility model.

Claims

1. A voice recognition system, characterized in that, The voice recognition system includes: A main control chip and a CAT1 chip that are interconnected, and the main control chip is also connected to peripheral devices; The main control chip is used to receive the voice input by the peripheral device to generate a corresponding audio stream, and send the audio stream to the CAT1 chip; The CAT1 chip is used to perform voice recognition on the audio stream to obtain a voice recognition signal, and feedback the voice recognition signal to the main control chip; The main control chip is also used to parse the voice recognition signal to obtain a voice command signal, and execute the voice command signal.

2. The voice recognition system according to claim 1, wherein The main control chip includes: An acquisition module, a generation module, an analysis module, and an execution module; The acquisition module is connected to the generation module; the generation module is connected to the CAT1 chip; the analysis module is respectively connected to the CAT1 chip and the execution module; The acquisition module is used to acquire the voice input by the peripheral device; The generation module is used to generate a corresponding audio stream from the voice; The analysis module is used to parse the voice recognition signal to obtain the voice command signal; The execution module is used to execute the voice command signal.

3. The voice recognition system according to claim 2, characterized in that, The CAT1 chip includes: A recognition module and a feedback module; The recognition module is respectively connected to the generation module and the feedback module; the feedback module is connected to the analysis module; The recognition module is used to perform voice recognition on the audio stream to obtain the voice recognition signal; The feedback module is used to feedback the voice recognition signal to the main control chip.

4. The voice recognition system according to claim 3, wherein, The acquisition module includes; A microphone and an analog-to-digital converter; The microphone is connected to the analog-to-digital converter; the analog-to-digital converter is connected to the generation module; The microphone is used to convert the sound signal into an analog electrical signal; The analog-to-digital converter is used to convert the analog electrical signal into a digital audio signal.

5. The speech recognition system according to claim 4, characterized in that, The generation module includes; A digital audio processor and an audio stream generator; The digital audio processor is connected to the audio stream generator; The audio stream generator is connected to the recognition module; The digital audio processor is used to receive and decode the digital audio signal; The audio stream generator is used to pack the decoded digital audio signal into a continuous audio stream.

6. The voice recognition system according to claim 5, characterized in that, The recognition module includes; A filter and a first decoder; The filter is connected to the first decoder; the first decoder is connected to the feedback module; The filter is used to remove the unnecessary frequency components in the audio stream to obtain a filtered audio stream; The first decoder is used to decode the filtered audio stream to obtain the voice recognition signal, and transmit the voice recognition signal to the feedback module.

7. The voice recognition system according to claim 6, characterized in that, The feedback module includes; A first controller; The first controller is connected to the analysis module; The first controller is used to pack the voice recognition signal after receiving it, and transmit the packed voice recognition signal to the analysis module.

8. The voice recognition system according to claim 7, wherein The analysis module includes; A second decoder; The second decoder is connected to the execution module; The second decoder is configured to parse the speech recognition signal to obtain the speech command signal.

9. The voice recognition system according to claim 8, wherein The execution module includes; A second controller; The second controller is connected to the peripheral device; The second controller is configured to execute the speech command signal.

10. A radio device, characterized in that, The sound collection device includes the speech recognition system according to any one of claims 1 to 9.

Images