Test device for voice wake-up rate capability verification

Abstract

The utility model discloses a test device for voice wake-up rate capability verification, which comprises a computer, a voice player and a voice wake-up rate test sample, a core processing module of the computer comprises a master control MCU (Microprogrammed Control Unit), a voice data storage module and a power supply, the master control MCU of the computer is connected with input equipment consisting of a microphone and a pre-amplifier, and the voice player is connected with the power supply. The main control MCU is further connected with the voice player, linguistic data are played through the voice player, voice interaction with the voice wake-up rate test sample is carried out, the microphone adopts a pre-signal amplification circuit with a decoupling capacitor, the microphone adopts a bias circuit with a resistor R4 to be connected with a power supply MICBIAS, and the power supply MICBIAS is connected with the microphone. Two circuits with a diode D4 and a diode D5 are respectively connected with a digital ground GND, and a circuit with a resistor R12 is connected with an analog ground AGND. According to the utility model, the voice wake-up rate of the test sample can be verified by automatically playing corpora.

Description

Technical Field

[0001] This utility model relates to a test device, and more particularly to a test device for verifying voice wake-up rate capability. Background Technology

[0002] With the rapid development of artificial intelligence technology, more and more smart products are being integrated into people's lives and work. Among them, the application of human-computer voice interaction technology is becoming increasingly widespread. During voice interaction between smart products and users, in order to save power consumption or reduce operational load, they typically enter a sleep state if no corresponding voice signal is received for a predetermined period. Upon receiving a specific voice signal from the user, they switch from sleep to working state; this process is commonly known as voice wake-up. For smart products that can be controlled by voice, the voice wake-up rate has become a key performance parameter for human-computer interaction experience. Therefore, more and more products require targeted voice wake-up rate testing during the design and production process. However, existing technology lacks dedicated voice wake-up rate testing devices, resulting in low efficiency in wake-up rate testing. Utility Model Content

[0003] The purpose of this invention is to provide a test device for verifying voice wake-up rate capability, which can automatically play corpora to verify the voice wake-up rate of test samples.

[0004] The technical solution of this utility model is as follows:

[0005] An experimental device for verifying voice wake-up rate capability includes a computer for controlling the playback of speech data, a voice player for playing the speech data, and a voice wake-up rate test sample. The core processing module of the computer includes a main control MCU, a voice data storage module, and a power supply. The main control MCU of the computer is connected to an input device consisting of a microphone and a preamplifier. The main control MCU is also connected to the voice player. The microphone collects sound signals, which are amplified and conditioned by the preamplifier and then digitized into analog signals by the main control MCU. The speech data is played through the voice player, and voice interaction is performed with the voice wake-up rate test sample. The microphone uses a preamplifier circuit with a decoupling capacitor. The microphone is connected to the power supply MICBIAS using a bias circuit with resistor R4. Two circuits with diodes D4 and D5 are connected to digital ground GND respectively, and a circuit with resistor R12 is connected to analog ground AGND.

[0006] The microphone of this invention employs a word operational amplifier circuit design and a bias circuit to provide a stable MICBIAS voltage. The entire circuit adopts a zoned grounding design, separating the analog ground AGND from the digital ground GND, further improving the system's noise immunity. This operational amplifier circuit design not only improves the microphone signal acquisition quality but also effectively reduces background noise during system operation through a reasonable decoupling capacitor layout, providing a clear audio input signal to the voice wake-up rate test samples.

[0007] This utility model also has the following preferred designs:

[0008] In this invention, a decoupling capacitor C3 is provided between the signal lines MIC- and MICN of the microphone's preamplifier circuit. The decoupling capacitor C3 is positioned close to the microphone interface. It effectively filters out DC bias, allowing only audio signals to pass through, while suppressing high-frequency noise interference. The design parameters of the decoupling capacitor C3 should preferably be type 104, 10% accuracy, and 16V withstand voltage to ensure sufficient safety margin during circuit operation.

[0009] The voice player described in this utility model is a speaker.

[0010] The voice wake-up rate test sample of this utility model is powered by a DC 5V power supply via a USB interface.

[0011] Compared with the prior art, the beneficial effects achieved by this utility model are as follows:

[0012] This invention can automatically play audio corpora to test the voice wake-up rate of test samples, resulting in high testing efficiency and reducing the workload of testing personnel. The operational amplifier circuit design of the microphone in this invention not only improves the quality of microphone signal acquisition but also effectively reduces background noise during system operation through a reasonable decoupling capacitor layout, providing a clear audio input signal to the voice wake-up rate test samples. Attached Figure Description

[0013] Figure 1 A schematic diagram of the working principle of an experimental device for verifying voice wake-up rate capability provided by this utility model;

[0014] Figure 2 This is a module design drawing of this utility model;

[0015] Figure 3 This is a microphone circuit diagram from one embodiment;

[0016] Figure 4 This is a circuit diagram of a main control MCU in one of the embodiments. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this utility model more apparent, exemplary embodiments according to this utility model will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this utility model, and not all embodiments of this utility model. It should be understood that this utility model is not limited to the exemplary embodiments described herein. Based on the embodiments of this utility model described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of this utility model.

[0018] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid confusion with the present invention.

[0019] It should be understood that this invention can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of this invention to those skilled in the art.

[0020] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0021] To fully understand this utility model, a detailed structure will be presented in the following description to illustrate the technical solution proposed by this utility model. Optional embodiments of this utility model are described in detail below; however, in addition to these detailed descriptions, this utility model may have other embodiments.

[0022] like Figures 1 to 4As shown, an experimental device for verifying voice wake-up rate capability includes a computer for controlling the playback of speech data, a voice player for playing the speech data, and a voice wake-up rate test sample. The core processing module of the computer includes a main control MCU, a voice data storage module, and a power supply. The main control MCU of the computer is connected to an input device consisting of a microphone and a preamplifier. The main control MCU is also connected to the voice player. The microphone collects sound signals. The sound signals are amplified and conditioned by the preamplifier and then digitized into analog signals by the main control MCU. The speech data is played through the voice player, and voice interaction is performed with the voice wake-up rate test sample. The microphone adopts a preamplifier circuit including a decoupling capacitor. The microphone is connected to the power supply MICBIAS by a bias circuit with resistor R4. Two circuits with diodes D4 and D5 are respectively connected to digital ground GND, and a circuit with resistor R12 is connected to analog ground AGND.

[0023] like Figure 3 As shown, in one embodiment, a decoupling capacitor C3 is provided between the signal lines MIC- and MICN of the microphone's preamplifier circuit. The decoupling capacitor C3 is positioned close to the microphone interface. It effectively filters out DC bias, allowing only audio signals to pass through, while suppressing high-frequency noise interference. In this embodiment, the decoupling capacitor C3 is preferably a 100nF capacitor of type 104, 10% accuracy, and 16V withstand voltage, ensuring sufficient safety margin during circuit operation.

[0024] In one embodiment, the voice player is a speaker, used as an output device connected to the computer's main control MCU.

[0025] In one embodiment, the voice wake-up rate test sample is powered by a DC 5V power supply via a USB interface.

[0026] In one embodiment, such as Figure 3 In the microphone circuit shown, the decoupling capacitor C3 (100nF) is located between the MIC- and MICIN+ signal lines, serving to couple signals and suppress noise. This capacitor is placed on the circuit board close to the J4 microphone interface to minimize the signal transmission path and reduce interference.

[0027] In one embodiment, the main control MCU processing section uses a dedicated voice processing MCU chip. The main control MCU is the core processing module, with multiple decoupling capacitors configured around it and an integrated ADC inside.

[0028] like Figure 4The circuit diagram of the main control MCU shown has decoupling capacitors C1 to C5 connected between the various power supply pins (MICBIAS, VCM, AVDD, VDD11, VDD11) of the main control MCU chip and ground. These capacitors are arranged in a "star" configuration, placed around the main control MCU chip, with a distance between them kept within 10mm to ensure a short and direct power decoupling path. In particular, decoupling capacitors C1 and C2, which are connected to the analog power supplies (MICBIAS, VCM), are placed closer to the corresponding pins of the chip to prioritize the power quality of the analog signal processing section.

[0029] Furthermore, capacitors C10 and C11 at both ends of crystal oscillator Y1 are symmetrically arranged, maintaining the shortest possible connection distance with the XIN / XOUT pins of the MCU chip. This design reduces clock signal transmission interference and improves system stability. The decoupling capacitor network of the MCU chip forms a complete power supply filtering system, effectively suppressing the impact of power supply noise on audio signal sampling and processing, ensuring the accuracy and sensitivity of the voice wake-up function.

[0030] In one embodiment, the computer is connected to an external interface module with a USB interface and an expansion interface to facilitate connection with the test sample and output of test data.

[0031] The above are merely specific embodiments of this utility model, but the protection scope of this utility model is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this utility model, and these modifications or substitutions should all be covered within the protection scope of this utility model. Therefore, the protection scope of this utility model should be determined by the scope of the claims.

Claims

1. An experimental device for verifying voice wake-up rate capability, comprising a computer for controlling the playback of speech corpora, characterized in that, It also includes a voice player for playing speech data and a voice wake-up rate test sample. The core processing module of the computer includes a main control MCU, a voice data storage module, and a power supply. The main control MCU of the computer is connected to an input device consisting of a microphone and a preamplifier. The main control MCU is also connected to the voice player. The microphone collects sound signals. The sound signals are amplified and conditioned by the preamplifier and then digitized into analog signals by the main control MCU. The speech data is played through the voice player, and voice interaction is performed with the voice wake-up rate test sample. The microphone adopts a preamplifier circuit with a decoupling capacitor. The microphone adopts a bias circuit with resistor R4 connected to the power supply MICBIAS. Two circuits with diodes D4 and D5 are respectively connected to digital ground GND. A circuit with resistor R12 is connected to analog ground AGND.

2. The test apparatus for voice wake-word rate capability verification of claim 1, wherein: A decoupling capacitor C3 is provided between the signal line MIC- and the signal line MICN of the microphone's preamplifier circuit, and the decoupling capacitor C3 is located close to the microphone interface.

3. The test apparatus for voice wake-word rate capability verification of claim 1, wherein: The voice player is a speaker.

4. The test apparatus for voice wake-word rate capability verification of claim 1, wherein: The voice wake-up rate test sample is powered by a DC 5V power supply via a USB interface.

Images