CN219834363U - Radio system in microphone cabin - Google Patents

Abstract

The utility model relates to a sound receiving system in a microphone cabin, which is mainly designed by combining at least two paths of microphone devices, a sound receiving system and a display screen, is arranged in a vehicle to receive sound, and outputs a first sound source sampling signal and a second sound source sampling signal to perform sound source positioning processing and sound source identification content after performing sound source conversion, sound source noise reduction processing and sound source frequency sampling on at least one sound source through at least one processor arranged in the sound receiving system, so that the sound receiving system has the sound receiving efficiency in the cabin, and the sound source positioning and voice identification effects are achieved.

Description

Radio system in microphone cabin

Technical Field

The present utility model relates to an in-cabin sound pickup system, and more particularly to an in-cabin sound pickup system for a vehicle with various forms, which has in-cabin sound pickup performance to achieve sound source positioning and voice recognition.

Background

In addition to the sounds of the running of the vehicle itself, the sounds of the driver and passengers in the cabin of the vehicle are also generated during running of the vehicle, regardless of whether the vehicle is a small car, a medium bus or a large car.

In recent years, many electronic devices such as audio, navigation devices, and car reversing warning devices are installed in a vehicle to help a driver drive or control the vehicle, and some of the auxiliary devices are required to record the sound of the driver in a vehicle cabin and send out a command through the sound to operate the devices (such as audio sound size and channel selection).

However, the voice recorded in the cabin at present is easy to be distorted or is influenced by surrounding environmental sounds to weaken the recognition force, so that the emitted fingers are wrong, and the voice needs to be repeatedly emitted for recognition.

Disclosure of Invention

The utility model mainly aims to provide a sound receiving system in a microphone cabin, which is mainly designed by combining at least two paths of microphone devices, a sound receiving system and a display screen, is arranged in a vehicle to receive sound, and outputs a first sound source sampling signal and a second sound source sampling signal to perform sound source positioning processing and sound source identification content after performing sound source conversion, sound source noise reduction processing and sound source frequency sampling on at least one sound source through at least one processor arranged in the sound receiving system, so that the sound receiving efficiency in the cabin is achieved, the sound source positioning and voice identification effects are achieved, and the overall practicability is further improved.

Another objective of the present utility model is to provide an in-cabin sound receiving system, wherein the sound receiving system has two embodiments, and the first embodiment is that the at least one processor is a Central Processing Unit (CPU), and the sound source signal module, the sound source noise reduction module, the sound source sampling module, the sound source positioning module and the voice recognition module are all disposed in the CPU, so as to have a single chip processing performance. In a second embodiment, the at least one processor includes a Central Processing Unit (CPU) and a Digital Signal Processor (DSP), and the audio signal module and the audio noise reduction module are disposed in the DSP, and the audio sampling module, the audio positioning module and the audio recognition module are disposed in the CPU, so that the modules can be separated into different chips for processing, thereby increasing the processing efficiency and further increasing the overall operability.

Still another objective of the present utility model is to provide an in-cabin sound receiving system, wherein the sound source noise reduction module removes noise through a Voice Activity Detection (VAD), extracts features from a block of the input signal after removing noise, and classifies the block with a classifier to determine whether the block is a voice signal. The sound source positioning module detects and calculates the time when the sound sources of at least two paths of microphone devices enter the processor through a time difference of arrival (TDOA) to determine the sound source direction. The voice recognition module further converts the voice content of the sound file into related words through voice conversion word recognition (STT) to generate the sound source recognition content. Therefore, the efficiency and the efficiency of the in-cabin radio can be improved, and the overall usability is further improved.

For a further understanding of the nature, features, and aspects of the present utility model, reference should be made to the following detailed description of the utility model and to the accompanying drawings, which are provided by way of illustration only and not to limit the utility model.

Drawings

FIG. 1 is a schematic diagram of the main system of the present utility model;

FIG. 2 is a schematic diagram of another system according to the present utility model.

Reference numerals illustrate:

10. microphone device

11. Sound source

20. Radio system

21. Processor and method for controlling the same

211. Central Processing Unit (CPU)

212. Digital Signal Processor (DSP)

22. Sound source signal module

23. Sound source noise reduction module

24. Sound source sampling module

241. The sound source samples the first signal

242. The sound source samples the second signal

25. Sound source positioning module

251. Sound source positioning position

26. Sound gear

27. Voice recognition module

271. Sound source identification content

30. And a display screen.

Detailed Description

Referring to fig. 1-2, which are schematic diagrams of embodiments of the present utility model, an optimal implementation of the in-cabin sound pickup system of the present utility model is applied to various types of vehicles, and has in-cabin sound pickup efficiency, so as to achieve the effects of sound source positioning and voice recognition.

The microphone cabin sound receiving system of the present utility model is mainly designed by combining at least two microphone devices 10, a sound receiving system 20 and a display screen 30 (as shown in fig. 1 and 2), wherein the at least two microphone devices 10, the sound receiving system 20 and the display screen 30 are respectively installed in a cabin (not shown) of a vehicle, wherein the vehicle is a small-sized vehicle, a medium-sized bus, a large-sized vehicle (buses, tourist buses, etc.), a rapid transit vehicle, a railway vehicle, a high-speed railway vehicle, an electric vehicle or an electric bus, etc., in addition, the at least two microphone devices 10 are installed in cooperation with the cabin design of different vehicles (can be three-way microphone devices 10, four-way microphone devices 10, etc.) and are installed at different positions according to the cabin of different vehicles, such as the front of the cabin, the rear of the cabin, the upper part of the cabin, etc., so as to facilitate at least one sound source 11, the at least one sound source 11 can be mainly sound or the sound from the human cabin, and the present utility model can be recognized by the human being.

In addition, a circuit board (not shown) is disposed in the sound receiving system 20, the circuit board is composed of a plurality of electronic components, the circuit board is connected to the at least two microphone devices 10, and at least one processor 21 is disposed on the circuit board, the at least one processor 21 is provided with a sound source signal module 22, a sound source noise reduction module 23, a sound source sampling module 24, a sound source positioning module 25 and a voice recognition module 27 (as shown in fig. 1 and 2), wherein the sound receiving system 20 has two embodiments, the first embodiment is that the at least one processor 21 is a Central Processing Unit (CPU) 211, and the sound source signal module 22, the sound source noise reduction module 23, the sound source sampling module 24, the sound source positioning module 25 and the voice recognition module 27 are all disposed in the Central Processing Unit (CPU) 211 (as shown in fig. 1) to have the performance of single chip processing. In addition, the second embodiment is that the at least one processor 21 includes a Central Processing Unit (CPU) 211 and a Digital Signal Processor (DSP) 212 (as shown in fig. 2), the audio signal module 22 and the audio noise reduction module 23 are disposed in the DSP 212, and the audio sampling module 24, the audio positioning module 25 and the voice recognition module 27 are disposed in the CPU 211, so that the modules can be separated into different chips for processing, thereby increasing the processing efficiency.

When the at least two microphone devices 10 transmit the at least one recorded sound source 11 to the at least one processor 21 on the circuit board (as shown in fig. 1 and 2), the at least one processor 21 converts the at least one recorded sound source 11 into a digital signal by the sound source signal module 22, so that the subsequent sound source 11 can process the digital signal. After the audio signal module 22 performs audio conversion, the at least one audio 11 is transmitted to the audio noise reduction module 23 for audio noise reduction, and the audio noise reduction module 23 performs noise removal through a Voice Activity Detection (VAD), extracts features from a block of the input signal after the noise removal, and classifies the block by using a classifier to determine whether the block is a voice signal. After the sound source noise reduction processing is performed by the sound source noise reduction module 23, the at least one sound source 11 is transmitted to the sound source sampling module 24 for performing sound source frequency sampling, wherein the sound source sampling module 24 takes out one of the signals at 44.1KHz or 48KHz through a sampling frequency (a process of converting the signals from the analog signal in the continuous time domain to the discrete signal in the discrete time domain), and according to the sampling theorem, the sound wave at the frequency must be recorded by using twice the sampling frequency, wherein half of the frequency at 44.1KHz is 22.05KHz, that is, the highest frequency which can be represented by the CD is 22.05KHz. The human auditory system can hear in the frequency range of about 15-20khz, with a sampling frequency of 44.1khz being satisfactory for most purposes.

When the audio sampling module 24 performs audio frequency sampling, and outputs an audio sampling first signal 241 and an audio sampling second signal 242 (as shown in fig. 1 and 2), the audio sampling first signal 241 and the audio sampling second signal 242 may be the same signal (e.g. 44.1 KHz), or may be different signals (e.g. the audio sampling first signal 241 is 44.1KHz, the audio sampling second signal 242 is 48 KHz), and the audio sampling first signal 241 is transmitted to the audio positioning module 25 for audio positioning processing, and generates an audio positioning position 251, wherein the audio positioning module 25 detects and calculates the time when the audio 11 of at least two microphone apparatuses 10 enters the processor 21 by a time difference of arrival (TDOA) to determine the audio azimuth. In addition, the audio sample second signal 242 is transferred to a sound file 26, wherein the audio sample second signal 242 is converted to any one of the audio formats of MP3, WAV, m4a, flac, ogg, amr, MP, m4r by an audio converter, and after being transferred to the sound file 26, the sound file 26 is processed by the voice recognition module 27 to generate a sound source recognition content 271, wherein the voice recognition module 27 converts the voice content of the sound file 26 to related text by a voice conversion text recognition (STT) to generate the sound source recognition content 271.

And, the radio system 20 is connected to the display 30, when the first signal 241 is transmitted to the sound positioning module 25 to perform sound positioning processing and generate the sound positioning position 251, and the second signal 242 is transferred to the sound file 26, the sound file 26 performs voice recognition processing through the voice recognition module 27 and generates the sound recognition content 271, and then integrates the sound positioning position 251 and the sound recognition content 271 generated by the at least one sound source 11, so that the position and the content of the voice can be known, and the voice can be provided to a Car core management (Car Server) system (not shown), wherein the Car core management (Car Server) system is provided with at least one application program (APP) layer and at least one bottom service layer, and when the bottom service layer receives the integrated at least one sound source 11, the application program (APP) layer is called for corresponding and action according to the at least one sound source 11, and then the content corresponding to and action is displayed through the display 30 (as shown in fig. 1 and 2) and the voice content of at least one sound source 11 are clearly shown.

Therefore, the present utility model mainly uses the combined design of at least two microphone devices 10, a sound receiving system 20 and a display screen 30, and is installed in the vehicle to receive sound, and uses at least one processor 21 installed in the sound receiving system 20 to perform sound conversion, sound noise reduction and sound frequency sampling on at least one sound source 11, and then outputs a first sound source sampling signal 241 and a second sound source sampling signal 242 to perform sound positioning and sound identification, so as to achieve the effects of sound positioning and voice identification in the cabin, thereby increasing the overall practicability.

However, the foregoing is merely illustrative of the preferred embodiments of the present utility model, and is not intended to limit the scope of the utility model; therefore, all simple and equivalent changes and modifications made in accordance with the claims and the specification should be considered as falling within the scope of the present utility model.

Claims (10)

1. An in-cabin radio system comprising:

at least two microphone devices installed in a vehicle, the at least two microphone devices receiving at least one sound source;

the sound receiving system is arranged in the vehicle, a circuit board is arranged in the sound receiving system and is connected with the at least two paths of microphone devices, the circuit board is provided with at least one processor, the at least one processor is provided with a sound source signal module, a sound source noise reduction module, a sound source sampling module, a sound source positioning module and a voice recognition module, the at least one processor firstly carries out sound source conversion on the recorded at least one sound source through the sound source signal module, then carries out sound source noise reduction processing through the sound source noise reduction module, carries out sound source frequency sampling through the sound source sampling module, and respectively outputs a first sound source sampling signal and a second sound source sampling signal after carrying out the sound source frequency sampling, the first sound source sampling signal is transmitted to the sound source positioning module for carrying out the sound source positioning processing, a sound source positioning position is generated, the second sound source sampling signal is transferred into a sound file, the sound file carries out voice recognition processing through the voice recognition module, and a sound source recognition content is generated; and

and the display screen is connected with the sound receiving system to display the sound source positioning position and the sound source identification content.

2. The system of claim 1, wherein the at least one processor is a central processing unit.

3. The system of claim 1, wherein the at least one processor further comprises a central processing unit and a digital signal processor, the audio signal module and the audio noise reduction module are disposed in the digital signal processor, and the audio sampling module, the audio positioning module and the voice recognition module are disposed in the central processing unit.

4. The system of claim 1, wherein the audio signal module converts the at least one audio signal into a digital signal.

5. The system of claim 1, wherein the noise reduction module further removes noise by a voice activity detection, extracts features from a block of the input signal after removing noise, and classifies the block using a classifier to determine whether the block is a voice signal.

6. The system of claim 1, wherein the source sampling module extracts at one of a sampling frequency of 44.1KHz or 48 KHz.

7. The system of claim 1 wherein the source localization module detects and calculates the time of entry of the sources of at least two microphone devices into the processor by a time difference of arrival to determine the source orientation.

8. The system of claim 1, wherein the second signal is converted to any one of the audio formats of mp3.Wav. Mfa. Flac. Ogg. Amr. Mp2.M4r by an audio converter.

9. The system of claim 1, wherein the voice recognition module converts voice content of the audio file into related text by a voice conversion text recognition to generate the audio source recognition content.

10. The system of claim 1, wherein the sound source positioning module performs a sound source positioning process, and the sound source positioning module performs a sound recognition process with the sound recognition module to integrate the sound source positioning location and the sound source recognition content and provide the integrated sound source positioning location and the sound source recognition content to a vehicle core management system.