TWI770528B - Respiratory tract audio analysis system and respiratory tract audio analysis method - Google Patents

Abstract

The invention discloses a respiratory tract audio analysis system and a respiratory tract audio analysis method. A respiratory tract audio analysis system includes an analysis device and a microphone. The microphone device receives a first audio information at a first time. The microphone device receives a second audio information at a second time. The first audio information and the second audio information are generated by a user according to a text at the first time and the second time respectively. The processor of the analysis device performs an audio comparison process on the first audio information and the second audio information to generate a comparison result. The analysis device provides a respiratory tract audio analysis report based on the comparison result, the text, and a table of respiratory tract parts and sentences.

Description

Airway audio analysis system and airway audio analysis method

The invention relates to a respiratory tract audio analysis system and a respiratory tract audio analysis method, in particular to a respiratory tract audio analysis system and a respiratory tract audio analysis method using daily vocalizations for analysis.

In the past, changes in the state of the respiratory tract mostly required the perception of others or the discomfort of the respiratory tract to be noticed. In particular, patients with sleep apnea are not easily sensitive to changes in their own respiratory tract.

Therefore, how to provide an airway audio analysis system and an airway audio analysis method for analyzing daily vocalizations has become one of the important issues to be solved by this project.

The technical problem to be solved by the present invention is to provide a respiratory tract audio analysis system in view of the deficiencies of the prior art, including: an audio analysis device, including: a processor; a storage module electrically connected to the processor; a communication module a group, electrically connected to the processor; and a connection module, electrically connected to the processor; and a microphone device, connected to the audio analysis device; wherein, the microphone device receives a first time at a first time an audio information, the first audio information is transmitted to the audio analysis device and stored in the storage module, the microphone device receives a second audio information at a second time, the second audio information is transmitted to the audio analysis device and stored in the storage module; wherein, the first audio information and the second audio information are obtained by a user according to a text information at the first time and the The second time is generated by uttering sound; wherein, the processor of the audio analysis device performs an audio comparison program on the first audio information and the second audio information to generate an audio analysis and comparison result, The audio analysis device provides an airway audio analysis report according to the audio analysis and comparison result, the text information, and a comparison table of parts of the airway and sentences and paragraphs.

In order to solve the above-mentioned technical problems, one of the technical solutions adopted by the present invention is to provide a method for analyzing airway audio, comprising: using a microphone device to receive a first audio information at a first time; using the microphone device to receive a first audio information at a first time Receive a second audio information at two times; compare the first audio information and the second audio information to generate an audio analysis and comparison result; and according to the audio analysis and comparison result, a text information, an airway part And a sentence-paragraph comparison table to provide a respiratory audio analysis report.

One of the beneficial effects of the present invention is that the airway audio analysis system and the airway audio analysis method provided by the present invention can easily analyze the audio frequency at different time points to obtain the changes of various parts of the user's airway. It not only reduces various monitoring costs, but also improves the user experience.

For a further understanding of the features and technical content of the present invention, please refer to the following detailed descriptions and drawings of the present invention. However, the drawings provided are only for reference and description, and are not intended to limit the present invention.

The following are specific embodiments to illustrate the embodiments of the "airway audio analysis system and airway audio analysis method" disclosed in the present invention, and those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the concept of the present invention. In addition, the drawings of the present invention are merely schematic illustrations, and are not drawn according to the actual size, and are stated in advance. The following embodiments will further describe the related technical contents of the present invention in detail, but the disclosed contents are not intended to limit the protection scope of the present invention. In addition, the term "or", as used herein, should include any one or a combination of more of the associated listed items, as the case may be.

[First Embodiment]

Please refer to FIG. 1 , FIG. 2 , FIG. 3 and FIG. 4 . FIG. 1 is a schematic diagram of an airway audio analysis system according to a first embodiment of the present invention. FIG. 2 is a schematic diagram of the first audio information and the second audio information. FIG. 3 is a schematic diagram illustrating a plurality of sentence paragraphs in the text information corresponding to the first audio information and the second audio information. 4 is a schematic diagram of a comparison table of parts of the respiratory tract and sentences and paragraphs of the present invention.

Please refer to FIG. 1 , the airway audio analysis system SYS1 includes an audio analysis device 1 , a microphone device 2 and a server 9 . The audio analysis device 1 is connected to the microphone device 2 . The audio analysis device 1 is connected to the server 9 in communication. In this embodiment, the results obtained by the analysis of the audio analysis device 1 can be sent to the server 9 for storage or provided to professionals for further analysis.

The audio analysis device 1 includes a processor 10 , a storage module 11 , a communication module 12 , a connection module 13 and a power module 14 . The processor 10 is electrically connected to the storage module 11 , the communication module 12 , the connection module 13 and the power module 14 .

The microphone device 2 receives a first audio information AS1 of a user at a first time T1. The first audio information AS1 is transmitted to the audio analysis device 1 and stored in the storage module 11 . The microphone device 2 receives a second audio information AS2 at a second time T2. The second audio information AS2 is also transmitted to the audio analysis device 1 and stored in the storage module 11 . In addition, the first audio information AS1 and the second audio information AS2 are generated by the user uttering sound at the first time T1 and the second time T2 respectively according to a text information TEXT.

The processor 10 is a central processing unit (CPU), an application specific integrated circuit (ASIC) or a microprocessor (MCU). The storage module 11 is a flash memory, a read-only memory, a programmable read-only memory, a power-rewritable read-only memory, an erasable programmable read-only memory, or a power-rewritable read-only memory. Erase programmable read-only memory.

The communication module 12 includes a wired communication unit (not shown) and a wireless communication unit (not shown). The wired communication unit (not shown in the figure) can also be independently set to communicate with the server 9 to receive the control signal of the server 9 or the data in the database of the server 9 (not shown in the figure). When the communication module 12 is a wireless communication unit, the communication module 12 can be a Wi-Fi communication unit, a Bluetooth communication unit, a Zigbee communication unit, a LoRa communication unit, a Sigfox communication unit or An NB-IoT communication unit. The power module 14 is an AC-to-DC voltage converter or a DC-to-DC voltage converter. The microphone device 2 can be connected with the audio analysis device 1 through the communication module 12 or through the connection module 13 . In this embodiment, the connection module 13 is a wired connection module. Includes a type-C USB port, a type-A USB port, a micro-USB port, or an XLR port.

The processor 10 of the audio analysis device 1 performs an audio comparison procedure on the first audio information AS1 and the second audio information AS2 to generate an audio analysis and comparison result. Next, the audio analysis device 1 provides an airway audio analysis report according to the audio analysis and comparison result, the text information TEXT, and a comparison table TAB of airway parts and text passages.

Referring to FIG. 2 , in this embodiment, the first time T1 and the second time T2 have a sequence in the time series. The second time T2 is later than the first time T1. In addition, the first time T1 and the second time T2 are a sleep time interval of the user. That is, the first time T1 is a time point before the user goes to sleep, and the second time T2 is a time point after the user wakes up. In this embodiment, the airway audio analysis system SYS1 can analyze changes in the user's airway during the sleep time interval, so as to appropriately adjust living habits, diet, or other causes caused by sleep interruption or snoring during the sleep time interval respiratory tract injury.

In this embodiment, the processor 10 of the audio analysis device 1 performs time domain segmentation on the first audio information AS1 according to a plurality of sentence segments TS1-TSN in the text information TEXT, so as to generate a plurality of first audio interval information AS1-1 -AS1-N. In addition, the processor 10 of the audio analysis device 1 performs time-domain segmentation on the second audio information AS2 according to the plurality of text segments TS1-TSN in the text information TEXT, so as to generate a plurality of second audio interval information AS2-1-AS2 -N.

Next, the processor 10 compares the plurality of first audio interval information AS1-1-AS1-N of the first audio information AS1 and the plurality of second audio interval information AS2-1-AS2-N of the second audio information AS2 respectively , to generate multiple interval audio analysis comparison results. The processor 10 combines a plurality of interval audio analysis and comparison results to obtain an audio analysis and comparison result.

Referring to FIG. 3 , the processor 10 according to the plurality of first audio interval information AS1-1-AS1-N of the first audio information AS1 and the plurality of second audio interval information AS2-1-AS2-N of the second audio information AS2 One of the interval audio analysis and comparison results of the multiple interval audio analysis and comparison results or the plurality of interval audio analysis and comparison results, the text information TEXT, and the comparison table TAB of airway parts and sentences and paragraphs, so as to provide the airway audio analysis report.

The processor 10 compares the plurality of first audio interval information AS1-1-AS1-N and the plurality of second audio interval information AS2-1-AS2-N respectively, because each first audio interval information AS1-1 -AS1-N and each of the second audio interval information AS2-1-AS2-N are corresponding to a plurality of sentence paragraphs TS1-TSN in the text information TEXT. For example, the first audio interval information AS1-1 and the first audio interval information AS2-1 are both the user uttering sound according to the sentence segment TS1 in the text information TEXT.

The processor 10 performs an audio comparison procedure on the first audio interval information AS1-1 and the second audio interval information AS2-1 corresponding to the same sentence segment TS1. For example, frequency, amplitude intensity, and duration. The processor 10 can further provide interval audio analysis comparison results including three-dimensional audio analysis of the first audio interval information AS1-1 and the second audio interval information AS2-1, including three dimensions of time, frequency, and amplitude intensity. The first audio interval information AS1-1-AS1-N and the second audio interval information AS2-1-AS2-N corresponding to each sentence segment TS1-TSN in the text information TEXT will be compared respectively to generate a plurality of interval audio The comparison results are analyzed, and finally the audio analysis and comparison results of the first audio information AS1 and the second audio information AS2 are comprehensively obtained.

Please refer to FIG. 4 . Next, the processor 10 compares the audio analysis and comparison results of the first audio information AS1 and the second audio information AS2 with the comparison table TAB of airway parts and sentence paragraphs to confirm the airway parts of the user. Changes.

The airway part and sentence paragraph comparison table TAB is the comparison content obtained according to the user uttering a plurality of sentence paragraphs in the text information TEXT according to a predetermined language. That is, the main airway part that the user will use when uttering the sentence paragraphs in the text information TEXT according to the predetermined language. The comparison table of airway parts and sentences and paragraphs TAB and text information TEXT are constructed through linguistics, physiology and audio analysis techniques.

In addition, the processor 10 of the audio analysis device 1 performs the audio comparison procedure only after the audio analysis device 1 receives both the first audio information AS1 and the second audio information AS2.

The plurality of text paragraphs TS1-TSN of the text information TEXT are corresponding to one respiratory tract part or a plurality of respiratory tract parts in the text-paragraph comparison table. The text information TEXT is designed according to at least one language. Since the habitual pronunciations of different languages are different, the text information TEXT can be designed according to the special pronunciations of different languages.

[Second Embodiment]

Please refer to FIG. 5 , which is a flowchart of a method for analyzing airway audio according to a second embodiment of the present invention.

This embodiment provides an airway audio analysis method, which is applicable to the airway audio analysis system SYS1 described in the first embodiment, and its structure and functions are not described here.

The airway audio analysis method of the present embodiment includes the following steps:

Using a microphone device to receive a first audio information at a first time (step S110 );

Use the microphone device to receive a second audio information at a second time (step S120 );

Comparing the first audio information and the second audio information to generate an audio analysis and comparison result (step S130 ); and

A respiratory tract audio analysis report is provided according to the audio analysis and comparison result, a text information, a respiratory tract part and a sentence-paragraph comparison table (step S140 ).

In step S110 and step S120, the first audio information AS1 and the second audio information AS2 are generated by a user uttering sound at the first time and the second time respectively according to the text information TEXT. In this embodiment, the first time T1 and the second time T2 have a sequence in the time series. The second time T2 is later than the first time T1. In addition, the interval between the first time T1 and the second time T2 is a sleep time interval of the user. That is, the first time T1 is a time point before the user goes to sleep, and the second time T2 is a time point after the user wakes up. In this embodiment, the airway audio analysis system SYS1 can analyze changes in the user's airway during the sleep time interval, so as to appropriately adjust living habits, diet, or other causes caused by sleep interruption or snoring during the sleep time interval respiratory tract injury. In other embodiments, the interval between the first time T1 and the second time T2 can be adjusted according to actual needs, such as vocal training for singers and vocalists or a lot of practice time.

The first audio information AS1 and the second audio information AS2 are transmitted to the audio analysis apparatus 1 in the first embodiment for audio analysis. The audio analysis apparatus is as described above, and will not be repeated here.

In step S130, in this embodiment, the processor 10 of the audio analysis device 1 performs time-domain segmentation on the first audio information AS1 according to the plurality of sentence segments TS1-TSN in the text information TEXT to generate a plurality of first audios Section information AS1-1-AS1-N. In addition, the processor 10 of the audio analysis device 1 performs time-domain segmentation on the second audio information AS2 according to the plurality of text segments TS1-TSN in the text information TEXT, so as to generate a plurality of second audio interval information AS2-1-AS2 -N.

Next, the processor 10 compares the plurality of first audio interval information AS1-1-AS1-N of the first audio information AS1 and the plurality of second audio interval information AS2-1-AS2-N of the second audio information AS2 respectively , to generate multiple interval audio analysis comparison results. The processor 10 combines a plurality of interval audio analysis and comparison results to obtain an audio analysis and comparison result.

In step S140, the processor 10 of the audio analysis device 1 according to the plurality of first audio interval information AS1-1-AS1-N of the first audio information AS1 and the plurality of second audio interval information AS2-N of the second audio information AS2 One of the audio analysis and comparison results of multiple intervals of 1-AS2-N or the audio analysis and comparison results of multiple intervals, the text information TEXT, and the comparison table TAB of airway parts and sentences and paragraphs, to provide Airway Audio Analysis Report.

The processor 10 compares the plurality of first audio interval information AS1-1-AS1-N and the plurality of second audio interval information AS2-1-AS2-N respectively, because each first audio interval information AS1-1 -AS1-N and each of the second audio interval information AS2-1-AS2-N are corresponding to a plurality of sentence paragraphs TS1-TSN in the text information TEXT. For example, the first audio interval information AS1-1 and the first audio interval information AS2-1 are both the user uttering sound according to the sentence segment TS1 in the text information TEXT.

The processor 10 performs an audio comparison procedure on the first audio interval information AS1-1 and the second audio interval information AS2-1 corresponding to the same sentence segment TS1. For example, frequency, amplitude intensity, and duration. The processor 10 can further provide interval audio analysis comparison results including three-dimensional audio analysis of the first audio interval information AS1-1 and the second audio interval information AS2-1, including three dimensions of time, frequency, and amplitude intensity. The first audio interval information AS1-1-AS1-N and the second audio interval information AS2-1-AS2-N corresponding to each sentence segment TS1-TSN in the text information TEXT will be compared respectively to generate a plurality of interval audio The comparison results are analyzed, and finally the audio analysis and comparison results of the first audio information AS1 and the second audio information AS2 are comprehensively obtained.

Next, the processor 10 compares the audio analysis and comparison results of the first audio information AS1 and the second audio information AS2 with the airway parts and sentence paragraph comparison table TAB to confirm changes in the user's airway parts.

The airway part and sentence paragraph comparison table TAB is the comparison content obtained according to the user uttering a plurality of sentence paragraphs in the text information TEXT according to a predetermined language. That is, the main airway part that the user will use when uttering the sentence paragraphs in the text information TEXT according to the predetermined language. The comparison table of airway parts and sentences and paragraphs TAB and text information TEXT are constructed through linguistics, physiology and audio analysis techniques.

In addition, the processor 10 of the audio analysis device 1 performs the audio comparison procedure only after the audio analysis device 1 receives both the first audio information AS1 and the second audio information AS2.

The plurality of text paragraphs TS1-TSN of the text information TEXT are corresponding to one respiratory tract part or a plurality of respiratory tract parts in the text-paragraph comparison table. The text information TEXT is designed according to at least one language. Since the habitual pronunciations of different languages are different, the text information TEXT can be designed according to the special pronunciations of different languages.

[Advantageous effects of the embodiment]

One of the beneficial effects of the present invention is that the airway audio analysis system and the airway audio analysis method provided by the present invention can easily analyze the audio frequency at different time points to obtain the changes of various parts of the user's airway. It not only reduces various monitoring costs, but also improves the user experience.

The contents disclosed above are only preferred feasible embodiments of the present invention, and are not intended to limit the scope of the present invention. Therefore, any equivalent technical changes made by using the contents of the description and drawings of the present invention are included in the application of the present invention. within the scope of the patent.

SYS1: Airway Audio Analysis System 1: Audio analysis device 2: Microphone device 10: Processor 11: Storage Module 12: Communication module 13: Connect the module 14: Power Module AS1: First Audio Information AS2: Second Audio Information T1: The first time T2: Second time R1-RN: respiratory site AS1-1-AS1-N: Second Audio Section Information AS2-1-AS2-N: First Audio Section Information TS1-TSN: Sentence paragraph TEXT: text information S110-S140: Steps 9: Server

FIG. 1 is a schematic diagram of an airway audio analysis system according to a first embodiment of the present invention.

FIG. 2 is a schematic diagram of the first audio information and the second audio information.

FIG. 3 is a schematic diagram illustrating a plurality of sentence paragraphs in the text information corresponding to the first audio information and the second audio information.

4 is a schematic diagram of a comparison table of parts of the respiratory tract and sentences and paragraphs of the present invention.

FIG. 5 is a flowchart of a method for analyzing airway audio according to a second embodiment of the present invention.

SYS1: Airway Audio Analysis System

1: Audio analysis device

2: Microphone device

9: Server

10: Processor

11: Storage Module

12: Communication module

13: Connect the module

14: Power Module

AS1: First Audio Information

AS2: Second Audio Information

Claims (23)

A respiratory tract audio analysis system, comprising: an audio analysis device, including: a processor; a storage module electrically connected to the processor; a communication module electrically connected to the processor; and a connection module , electrically connected to the processor; and a microphone device, connected to the audio analysis device; wherein, the microphone device receives a first audio information at a first time, and the first audio information is transmitted to the The audio analysis device is stored in the storage module, the microphone device receives a second audio information at a second time, and the second audio information is transmitted to the audio analysis device and stored in the storage module. In the group; wherein, the first audio information and the second audio information are generated by a user uttering sound at the first time and the second time respectively according to a text information; wherein, the processor An audio comparison program is performed on the first audio information and the second audio information to generate an audio analysis and comparison result, and the audio analysis device is based on the audio analysis and comparison result, the text information and an airway A comparison table of parts and sentences and paragraphs provides a respiratory audio analysis report. The airway audio analysis system according to claim 1, wherein the first time and the second time have a sequence in time series, and the second time is later than the first time. The airway audio analysis system according to claim 2, wherein the first time and the second time are a sleep time interval between the user. The respiratory tract audio analysis system according to claim 3, wherein the processor performs an analysis on the first audio information according to a plurality of sentence paragraphs in the text information time-domain division to generate a plurality of first audio interval information, the processor performs time-domain division on the second audio information according to the plurality of sentence paragraphs in the text information to generate a plurality of second audio interval information. The airway audio analysis system of claim 4, wherein the processor compares the plurality of first audio interval information of the first audio information and the plurality of first audio information of the second audio information respectively Two audio interval information to generate a plurality of interval audio analysis and comparison results, and the processor combines the plurality of interval audio analysis and comparison results to obtain the audio analysis and comparison results. The airway audio analysis system of claim 5, wherein the processor is based on the plurality of first audio interval information of the first audio information and the plurality of second audios of the second audio information One of the interval audio analysis and comparison results of multiple interval audio analysis and comparison results of interval information or a comparison table of multiple interval audio analysis and comparison results, the text information, and the respiratory tract parts and sentence paragraphs, so as to provide the The airway audio analysis report. The airway audio analysis system according to claim 1, wherein after the audio analysis device receives the first audio information and the second audio information, the processor performs the audio comparison procedure. The airway audio analysis system according to claim 4, wherein the plurality of sentence paragraphs of the text information correspond to one airway part or a plurality of airway parts in the comparison table of airway parts and sentence paragraphs. The airway audio analysis system of claim 8, wherein the text information is designed according to at least one language. The airway audio analysis system according to claim 1, wherein the audio analysis device is communicatively connected to a server. A method for analyzing airway audio, comprising: using a microphone device to receive a first audio information at a first time; using the microphone device to receive a second audio information at a second time; Comparing the first audio information and the second audio information to generate an audio analysis and comparison result; and providing an airway audio according to the audio analysis and comparison result, a text information, a respiratory part and a sentence paragraph comparison table analysis report. The airway audio analysis method according to claim 11, wherein the first audio information and the second audio information are performed by a user at the first time and the second time respectively according to the text information produced by sound. The airway audio analysis method according to claim 11, wherein the first audio information and the second audio information are transmitted to an audio analysis device for audio analysis, the audio analysis device comprising: a processor; a a storage module, electrically connected to the processor; a communication module, electrically connected to the processor; and a connection module, electrically connected to the processor; and wherein the microphone device is connected to the audio an analysis device; the first audio information and the second audio information are stored in the storage module. The airway audio analysis method of claim 13, wherein the processor of the audio analysis device performs an audio comparison procedure on the first audio information and the second audio information to generate an audio analysis ratio For the result, the audio analysis device provides the airway audio analysis report according to the audio analysis and comparison result, the text information, and the comparison table of parts of the airway and sentences and paragraphs. The airway audio analysis method according to claim 12, wherein the first time and the second time have a sequence in a time series, and the second time is later than the first time. The airway audio analysis method according to claim 15, wherein the first time The interval and the second time are a sleep time interval between the user. The airway audio analysis method according to claim 13, wherein the processor of the audio analysis device performs time-domain segmentation on the first audio information according to a plurality of sentence paragraphs in the text information to generate multiple pieces of first audio interval information, the processor of the audio analysis device performs time domain segmentation on the second audio information according to the plurality of sentence segments in the text information to generate a plurality of second audio intervals News. The airway audio analysis method according to claim 17, wherein the processor of the audio analysis device compares the plurality of first audio interval information and the second audio information of the first audio information respectively The plurality of second audio interval information to generate a plurality of interval audio analysis and comparison results, the processor of the audio analysis device combines the plurality of interval audio analysis and comparison results to become the audio analysis and comparison result. The airway audio analysis method according to claim 18, wherein the processor of the audio analysis device is based on the plurality of first audio interval information and the second audio information of the first audio information. One of the interval audio analysis and comparison results of the plurality of interval audio analysis and comparison results of the plurality of second audio interval information or the plurality of interval audio analysis and comparison results, the text information, the respiratory tract part and the sentence paragraph A comparison table to provide the airway audio analysis report. The airway audio analysis method according to claim 13, wherein when the audio analysis device receives the first audio information and the second audio information, the processor of the audio analysis device performs the Audio comparison program. The respiratory tract audio analysis method according to claim 12, wherein the plurality of text paragraphs of the text information correspond to one respiratory tract part or multiple respiratory tract parts in the respiratory tract part and the text-paragraph comparison table. The airway audio analysis method of claim 12, wherein the textual data The message is designed according to at least one language. The airway audio analysis method according to claim 13, wherein the audio analysis device is communicatively connected to a server.

Images