Voice processing circuit based on CI1103 voice chip

Abstract

The utility model discloses a voice processing circuit based on a CI1103 voice chip, and the circuit comprises a voice input unit which collects the voice inputted by a microphone; the processing unit is used for receiving the voice signals input by the input unit and comprises a CI1103 voice chip and a preprocessing module, and the preprocessing module is used for inputting the voice signals subjected to echo cancellation and filtering into the CI1103 voice chip again; and the output unit is used for transmitting the voice signal processed by the CI1103 voice chip to a loudspeaker and transmitting the voice signal to a communication interface through a level conversion circuit. The beneficial effects of the utility model are that through the cooperation of the crystal oscillator circuit and the AEC circuit in the preprocessing module, the noise in the voice is effectively filtered, and after the voice passes through the power amplifier, the sound emitted by the loudspeaker is eliminated through echoes; and secondly, through the level conversion circuit, amplification and amplitude limiting of the signals after voice preprocessing are realized, and finally, high and low levels are output, so that the signal waveform of a transmitting section is restored, better tone quality and efficiency are shown, and the man-machine interaction experience is smoother.

Description

TECHNICAL FIELD

[0001] The utility model relates to audio frequency technical field, especially a voice processing circuit based on CI1103 voice chip. BACKGROUND

[0002] With the promotion of computer technology and artificial intelligence technology, speech recognition technology is developing more and more maturely, and speech is not limited to communication between people, but also obtains rapid development in man-machine interaction, and becomes an important way for people to communicate with machines.

[0003] However, at present, the collected voice signal contains much noise, which increases the difficulty of speech recognition, in order to obtain better recognition effect, the collected voice needs to be preprocessed and processed, and then recognized. CONTENT OF THE UTILITY MODEL

[0004] This part aims to outline some aspects of the embodiments of the utility model and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part and the abstract of the specification and the utility model name to avoid obscuring the purpose of this part, the abstract of the specification and the utility model name, and such simplifications or omissions cannot be used to limit the scope of the utility model.

[0005] In view of the above or the problems existing in the prior art, the utility model is proposed.

[0006] Therefore, the purpose of the utility model is to provide a voice processing circuit based on CI1103 voice chip, which can better obtain useful signals by preprocessing and processing the collected voice before recognition.

[0007] To solve the above technical problems, the utility model provides the following technical scheme: a voice processing circuit based on CI1103 voice chip, which comprises a voice input unit, a microphone input voice; a processing unit, which accepts the voice signal input from the input unit, comprises a CI1103 voice chip and a preprocessing module, the preprocessing module inputs the echo-canceled and filtered voice signal to the CI1103 voice chip again; an output unit, which transmits the voice signal processed by the CI1103 voice chip to a loudspeaker, and transmits the voice signal to a communication interface through a level conversion circuit.

[0008] As a preferred scheme of the voice processing circuit based on CI1103 voice chip, the voice input unit is connected with the microphone through MIC+ pin and MIC- pin; the voice input unit is connected with the CI1103 voice chip through MICP terminal, and does filtering processing through MICBIAS bias voltage.

[0009] As a preferred scheme of the speech processing circuit based on the CI1103 voice chip, the pre-processing module comprises a crystal oscillator circuit and an AEC circuit, the crystal oscillator circuit filters noise of the voice signal through a 12.288Mhz crystal oscillator, and the AEC circuit re-inputs the voice signal of the right sound channel to the CI1103 voice chip after power amplification and echo cancellation.

[0010] As a preferred scheme of the speech processing circuit based on the CI1103 voice chip, the processing unit further comprises a power supply module, the power supply module receives a 5V power supply voltage, and is reduced to 3.3V through an LDO and is reduced to 1.2V through a DC / DC chip.

[0011] As a preferred scheme of the speech processing circuit based on the CI1103 voice chip, the 5V power supply voltage is from an external interface.

[0012] As a preferred scheme of the speech processing circuit based on the CI1103 voice chip, the level conversion circuit comprises a triode, a base of the triode is connected to a PWM3_IP_TX pin to receive a high-low level signal, and a collector of the triode is connected to two parallel infrared emitters.

[0013] As a preferred scheme of the speech processing circuit based on the CI1103 voice chip, the level conversion circuit further comprises an infrared receiving module, the infrared receiving module receives an infrared signal emitted by the infrared emitter, and restores a signal waveform of the emission section and transmits the signal waveform to the single-chip microcomputer through a PWM4_IP_RX pin.

[0014] As a preferred scheme of the speech processing circuit based on the CI1103 voice chip, the CI1103 voice chip externally expands an SPI Flash, and the SPI Flash stores a model library and a feature extraction parameter generated in a voice training stage.

[0015] The utility model discloses a microphone, through the cooperation of the crystal oscillator circuit and the AEC circuit in the pre-processing module, realizes the effective filtration of the noise in the voice, then after the power amplifier, the echo is eliminated by the sound emitted by the loudspeaker, secondly through the level conversion circuit, realizes the amplification, limiting of the signal after the pre-processing of the voice, finally outputs high-low level, restores the signal waveform of the emission section, and exhibits better sound quality and efficiency, so that the human-computer interaction experience is more smooth. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical scheme of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the premise of not deviating from the concept of the present application.

[0017] Fig. 1 It is a whole interaction diagram of the voice processing circuit based on CI1103 voice chip.

[0018] Fig. 2 It is a port interaction diagram of the voice processing circuit based on CI1103 voice chip.

[0019] Fig. 3 It is a microphone input bias circuit diagram of the voice processing circuit based on CI1103 voice chip.

[0020] Fig. 4 It is a 5V to 3.3V circuit schematic diagram of the voice processing circuit based on CI1103 voice chip.

[0021] Fig. 5 It is a 5V to 1.2V circuit schematic diagram of the voice processing circuit based on CI1103 voice chip.

[0022] Fig. 6 It is an infrared transceiver circuit schematic diagram of the voice processing circuit based on CI1103 voice chip. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned purpose, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0024] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced without the specific details, other than those described herein, and it is understood that the present application is not limited to the particular details described herein. In other instances, well-known methods, procedures and components have not been described in detail so as not to unnecessarily obscure aspects of the present application.

[0025] Secondly, the "one embodiment" or "embodiment" referred to herein can include specific features, structures or characteristics contained in at least one implementation of the present application. In this specification, "in one embodiment" appearing in different places does not refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments.

[0026] Embodiment 1

[0027] Reference Figs. 1-2For the first embodiment of the utility model, the embodiment provides a voice processing circuit based on CI1103 voice chip, which comprises a voice input unit 100, which collects voice input by a microphone; a processing unit 200, which accepts voice signals input from the input unit 100, comprising CI1103 voice chip 201 and pre-processing module 202, the pre-processing module 202 inputs the echo-canceled and filtered voice signal to CI1103 voice chip 201 again; an output unit 300, which transmits the voice signal processed by CI1103 voice chip 201 to a loudspeaker 301, and transmits the voice signal to a communication interface through a level conversion circuit 302.

[0028] In the periphery of CI1103 voice chip 201, a single microphone input and a single loudspeaker output are arranged, the collected voice signal is transmitted to CI1103 voice chip 201 through the input unit 100; the voice signal is further filtered by the pre-processing module 202, then passes through a power amplifier, and is subjected to echo cancellation, thereby eliminating the sound emitted by the loudspeaker and the echo picked up by the microphone again, and is input to CI1103 voice chip 201; the signal is amplified, limited in amplitude, and finally output as high or low level by the level conversion circuit 302, so that the signal waveform of the transmitting section is restored, and finally transmitted to the single-chip microcomputer.

[0029] In addition, the periphery of CI1103 voice chip 201 is further provided with an upgrade & debugging circuit and an analog circuit.

[0030] Embodiment 2

[0031] Reference Fig. 3 For the second embodiment of the utility model, different from the previous embodiment, the embodiment provides a voice processing circuit based on CI1103 voice chip, which comprises a voice input unit 100 connected with a microphone through a MIC+ pin and a MIC- pin; the voice input unit 100 is connected with CI1103 voice chip 201 through a MICP terminal, and is subjected to filtering processing through MICBIAS bias voltage.

[0032] In the system, a capacitive single microphone single microphone input mode is adopted, generally having two terminals of MICP terminal and MICBIAS terminal, after the microphone collects voice signals, the voice signals are transmitted to the MICP terminal through the MIC+ pin and the MIC- pin, the MICP terminal transmits the voice signals captured by the microphone to an audio processing system or an amplifier, and performs A / D conversion, and saves in the corresponding register, at the same time, the MICBIAS terminal removes or reduces the frequency components in the voice signals that are not needed through microphone bias voltage, while retaining or enhancing the frequency components that are needed, converts the sound signals into electric signals.

[0033] Embodiment 3

[0034] With reference to Fig. 2 , the third embodiment of the utility model, unlike the last embodiment, provides a voice processing circuit based on CI1103 voice chip, which includes a preprocessing module 202, including crystal oscillator circuit 202a and AEC circuit 202b, the crystal oscillator circuit 202a filters noise of the voice signal through 12.288Mhz crystal oscillator;AEC circuit 202b passes the voice signal of the right sound channel through the power amplifier and the echo cancellation, and re-enters the CI1103 voice chip 201.

[0035] The crystal oscillator circuit 202a uses 12.288Mhz crystal oscillator, when the voice signal passes through the crystal oscillator circuit 202a, the noise in the signal will be filtered, at this time, the filtered voice signal returns to the CI1103 voice chip 201 again, after the filtered voice signal passes through the power amplifier, the audio signal is amplified to a level sufficient to drive the loudspeaker, and is provided to MIC_R through the combination with the AEC circuit 202b, in this process, the AEC circuit 202b eliminates the sound emitted by the loudspeaker, and the echo picked up by the microphone again, and inputs to the CI1103 voice chip 201.

[0036] Embodiment 4

[0037] With reference to Figs. 4-5 , the fourth embodiment of the utility model, unlike the last embodiment, provides a voice processing circuit based on CI1103 voice chip, which includes a processing unit 200, including a power supply module 203, the power supply module 203 accepts 5V power supply voltage, and is reduced to 3.3V through LDOU4, and is reduced to 1.2V through DC / DC chip U3.

[0038] 5V power supply voltage comes from the external interface.

[0039] CI1103 voice chip 201 needs 3.3V and 1.2V two groups of voltage, which can be selected directly external input, also can pass through voltage conversion.When the input voltage is 3.3V, select LDO chip RY6212, not only low noise, clean power supply and low cost;When the input voltage is 1.2V, because LDO will be because the pressure drop is larger, and the loss is very large efficiency, select DC / DC chip RY3408, voltage conversion efficiency is higher.

[0040] Embodiment 5

[0041] With reference to Fig. 6The fifth embodiment of the utility model differs from the previous embodiment in that the embodiment provides a voice processing circuit based on a CI1103 voice chip, which comprises a level conversion circuit 302, including a triode 302a, the base of the triode 302a is connected to a PWM3_IP_TX pin to receive high and low level signals, and the collector of the triode 302a is connected to two parallel infrared emitters.

[0042] The level conversion circuit 302 further comprises an infrared receiving module 302b, which receives the infrared signals emitted by the infrared emitters and restores the signal waveform of the emission section through a PWM4_IP_RX pin to a single-chip microcomputer.

[0043] The infrared emitter is an IR33C, and the infrared receiving module 302b is an HS0038G. The infrared emitter IR33C is controlled by a PWM3_IR_TX pin, and when the PWM3_IR_TX pin receives a high level of 3.3V, the infrared emitter starts to work and emits infrared light around; when the PWM3_IR_TX pin is at a low level, the emission is stopped. When the internal circuit of the infrared receiving module 302b starts to work, the infrared diode first monitors the infrared signals emitted by the remote controller, and then sends the signals to a band-pass filter after amplification and limiting processing, and then enters a comparator through a demodulation circuit and an integration circuit. The comparator outputs high and low levels, thereby restoring the signal waveform of the emission section through a PWM4_IP_RX pin to a single-chip microcomputer.

[0044] In summary, the utility model selects a CI1103 voice chip and designs a circuit based on the voice module of the CI1103 chip. First, the overall hardware design of the chip is studied, which leads to some key peripheral circuits, and the microphone input circuit, voltage conversion circuit and infrared transceiver circuit are analyzed in detail. A non-specific person voice recognition system is designed, which can improve the signal quality through the preprocessing of the CI1103 voice chip and better obtain useful signals, so that the human-computer interaction experience is more smooth.

[0045] It is important to note that the construction and arrangements of the application shown in the various exemplary embodiments are illustrative only. Although only a few embodiments have been described in detail in this disclosure, those skilled in the art who review this disclosure will readily appreciate that many modifications can be made to the embodiments without departing from the novel teachings and advantages of the subject matter described herein. For example, elements described as integrated in a single unit can be separated, elements described as separate can be integrated, and the position, number, shape, and arrangements of elements can be varied. Accordingly, all such modifications are intended to be included within the scope of the present inventive subject matter. The order or sequence of any process or method steps can be varied or re-sequenced without departing from the general nature of the claims. Any "means plus function" clauses are intended to cover the structures described herein as performing the recited functionality and not only structural equivalents but also equivalent structures. Other substitutions, modifications, changes, and omissions can be made in the design, operating conditions, and arrangement of the exemplary embodiments without departing from the scope of the present inventive subject matter. Accordingly, the present inventive subject matter is not limited to the particular embodiments described and illustrated herein, but extends to equivalents of which the foregoing describes are intended to cover.

[0046] Furthermore, in order to provide a concise description of the exemplary embodiments, not all features of an actual implementation can be described (i.e., those pertaining to the

[0047] It is understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions can be made. Such development efforts can inevitably lead to a number of substitutions, modifications, changes, and omissions of parts illustrated as having a specific configuration. Such are the natural consequences of research and development efforts, and

[0048] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application, and although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and all should be included in the scope of the claims of the present application.

Claims

1. A voice processing circuit based on a CI1103 voice chip, characterized by: The application relates to a voice input device, which comprises the following parts: a voice input unit (100) for collecting microphone input voice; a processing unit (200) for accepting voice signals input from the input unit (100), which comprises a CI1103 voice chip (201) and a preprocessing module (202), wherein the preprocessing module (202) inputs the echo-canceled and filtered voice signals to the CI1103 voice chip (201) again; an output unit (300) for transmitting the voice signals processed by the CI1103 voice chip (201) to a loudspeaker (301) and transmitting the voice signals to a communication interface through a level conversion circuit (302).

2. The CI 1103 voice chip based voice processing circuit of claim 1, wherein: The voice input unit (100) is connected with a microphone through a MIC+ pin and a MIC- pin; the voice input unit (100) is connected with the CI1103 voice chip (201) through a MICP terminal and is subjected to filtering treatment through a MICBIAS bias voltage.

3. The CI 1103 voice chip based voice processing circuit of claim 2, wherein: The preprocessing module (202) comprises a crystal oscillator circuit (202a) and an AEC circuit (202b), the crystal oscillator circuit (202a) filters noise of the voice signals through a 12.288Mhz crystal oscillator, and the AEC circuit (202b) inputs the voice signals of a right sound channel to the CI1103 voice chip (201) again after the voice signals are subjected to power amplifier treatment and echo cancellation.

4. The CI 1103 voice chip based voice processing circuit of claim 3, wherein: The processing unit (200) further comprises a power supply module (203), which accepts a 5V power supply voltage, reduces the voltage to 3.3V through an LDO (U4) and reduces the voltage to 1.2V through a DC / DC chip (U3).

5. The CI 1103 voice chip based voice processing circuit of claim 4, wherein: The 5V power supply voltage is from an external interface.

6. The CI 1103 voice chip based voice processing circuit of claim 5, wherein: The level conversion circuit (302) comprises a triode (302a), the base of the triode (302a) is connected with a PWM3_IP_TX pin to receive high-low level signals, and the collector of the triode (302a) is connected with two parallel infrared emitters.

7. The CI 1103 voice chip based voice processing circuit of claim 6, wherein: The level conversion circuit (302) further comprises an infrared receiving module (302b), which receives infrared signals emitted by the infrared emitters and restores the waveforms of the signals of the emitting section and transmits the signals to a single-chip microcomputer through a PWM4_IP_RX pin.

8. The CI 1103 voice chip based voice processing circuit of claim 7, wherein: The SPIFlash externally expanded from the CI1103 voice chip (201) stores a model library and feature extraction parameters generated in a voice training stage.

Images