TWI752682B - Method for updating speech recognition system through air - Google Patents
Method for updating speech recognition system through air Download PDFInfo
- Publication number
- TWI752682B TWI752682B TW109136375A TW109136375A TWI752682B TW I752682 B TWI752682 B TW I752682B TW 109136375 A TW109136375 A TW 109136375A TW 109136375 A TW109136375 A TW 109136375A TW I752682 B TWI752682 B TW I752682B
- Authority
- TW
- Taiwan
- Prior art keywords
- asr
- cloud
- server
- client
- speech recognition
- Prior art date
Links
Images
Abstract
Description
本發明有關於更新語音辨識系統的方法,尤其是指經由雲端更新語音辨識系統的方法。 The present invention relates to a method for updating a speech recognition system, in particular to a method for updating the speech recognition system via the cloud.
一般的雲端自動語音辨識系統(ASR,Automatic Speech Recognition)若需要更新時,必須專業人員攜帶USB隨身碟進入一控制該雲端自動語音辨識系統的機房進行更新,相當耗費人力與時間。 When a general cloud automatic speech recognition system (ASR, Automatic Speech Recognition) needs to be updated, professionals must bring a USB flash drive into a computer room that controls the cloud automatic speech recognition system to update, which is quite labor-intensive and time-consuming.
雲端自動語音辨識系統既然在雲端,則從雲端更新自動語音辨識系統,是更加便捷的方式。這種技術由雲端自動語音辨識系統的開發廠商直接設計並供客戶使用,開發廠商將新版的自動語音辨識系統放在雲端,由其客戶的雲端自動語音辨識系統經由網路而選擇新版的自動語音辨識系統以便使用。 Since the cloud automatic speech recognition system is in the cloud, it is more convenient to update the automatic speech recognition system from the cloud. This technology is directly designed by the developer of the cloud automatic speech recognition system and used by customers. The developer puts the new version of the automatic speech recognition system on the cloud, and the customer's cloud automatic speech recognition system selects the new version of the automatic speech through the network. Identify the system for use.
本發明的目的在提出一種經由雲端更新語音辨識系統的方法,以供客戶ASR服務端與中央ASR雲端伺服端以網路相連,而能選擇新版的自動語音辨識系統。本發明的方法,其內容敘述如下。 The purpose of the present invention is to provide a method for updating the speech recognition system via the cloud, so that the client ASR server and the central ASR cloud server are connected via the network, and a new version of the automatic speech recognition system can be selected. The content of the method of the present invention is described below.
客戶ASR服務端作為提供雲端自動語音辨識的系統,並設置一中央ASR雲端伺服端與該客戶ASR服務端以網路相連。 The client ASR server serves as a system for providing automatic speech recognition in the cloud, and a central ASR cloud server is set up to be connected to the client ASR server via the network.
新版的自動語音辨識系統放在中央ASR雲端伺服端,由客戶ASR服務端經由網路而選擇新版的自動語音辨識系統以便使用。 The new version of the automatic speech recognition system is placed on the central ASR cloud server, and the customer ASR server selects the new version of the automatic speech recognition system for use through the network.
新版中的自動語音辨識系統分析語音的步驟,順序為音訊前處理、抽取語音特徵參數、聲學模型和語言模型,其中該聲學模型和該語言模型是雲端更新的主體。 The steps of the automatic speech recognition system in the new version to analyze speech are in the order of audio preprocessing, extraction of speech feature parameters, acoustic model and language model, where the acoustic model and the language model are the main body of the cloud update.
1:客戶ASR服務端 1: Client ASR server
2:客戶ASR服務端 2: Client ASR server
3:客戶ASR服務端 3: Client ASR server
4:中央ASR雲端伺服端 4: Central ASR cloud server
21:音訊前處理 21: Audio preprocessing
22:抽取語音特徵參數 22: Extract speech feature parameters
23:聲學模型 23: Acoustic Model
24:語言模型 24: Language Models
31:語音辨識執行程序 31: Speech recognition executive program
32:根據設定檔描述決定使用何種版本 32: Decide which version to use based on the profile description
41:步驟 41: Steps
42:步驟 42: Steps
43:步驟 43: Steps
44:步驟 44: Steps
45:步驟 45: Steps
46:步驟 46: Steps
47:步驟 47: Steps
48:步驟 48: Steps
49:步驟 49: Steps
50:步驟 50: Steps
A:版本 A: version
B:版本 B: version
C:版本 C:version
圖1為本發明的基本架構說明圖。 FIG. 1 is an explanatory diagram of the basic structure of the present invention.
圖2為本發明自動語音辨識系統分析語音的步驟示意圖。 FIG. 2 is a schematic diagram of the steps of analyzing speech by the automatic speech recognition system of the present invention.
圖3為本發明雲端自動語音辨識系統選擇版本的流程圖。 FIG. 3 is a flow chart of the version selection of the cloud automatic speech recognition system of the present invention.
圖4為本發明自動語音辨識系統經由雲端通訊更新版本的流程圖。 FIG. 4 is a flow chart of the updated version of the automatic speech recognition system of the present invention via cloud communication.
圖1說明本發明的基本架構。客戶ASR服務端1、客戶ASR服務端2、客戶ASR服務端3都是提供雲端自動語音辨識的系統,都與本發明中央ASR雲端伺服端4以網路相連。本發明中央ASR雲端伺服端4由雲端自動語音辨識系統的開發廠商直接設計並供客戶ASR服務端1、ASR服務端2、ASR服務端3使用,開發廠商將新版的自動語音辨識系統放在中央ASR雲端伺服端4,由其客戶的雲端自動語音辨識系統經由網路而選擇新版的自動語音辨識系統以便使用。
Figure 1 illustrates the basic architecture of the present invention. The client ASR server 1, the client ASR server 2, and the client ASR server 3 are all systems that provide automatic speech recognition in the cloud, and are connected to the central
圖2說明自動語音辨識系統分析語音的步驟,順序為音訊前處理21、抽取語音特徵參數22、聲學模型23和語言模型24。其中聲學模型23和語言模型24是雲端更新的主體,開發廠商著力於此,使雲端更新簡單
輕便快速。
FIG. 2 illustrates the steps of the automatic speech recognition system for analyzing speech, the sequence is audio preprocessing 21 , extraction of speech feature parameters 22 ,
請見圖3,說明客戶ASR服務端1、客戶ASR服務端2、客戶ASR服務端3、、、等提供雲端自動語音辨識的系統如何選擇版本的流程。語音辨識系統首先進行「語音辨識執行程序」31,然後根據其設定檔描述決定使用何種版本32。若其設定檔描述的是版本A,則導向版本A的聲學模型與語言模型。若描述的是版本B,則導向版本B的聲學模型與語言模型。若未來需要進行雲端版本更新時,則留一個位置給版本C。 Please refer to Figure 3 to illustrate the process of how to select the version of the system that provides cloud automatic speech recognition, such as customer ASR server 1, customer ASR server 2, customer ASR server 3, , , etc. The speech recognition system first performs a "speech recognition execution program" 31 , and then decides which version to use 32 according to its profile description. If its profile describes version A, it leads to the acoustic model and language model of version A. If it is describing version B, it leads to the acoustic model and language model of version B. If the cloud version needs to be updated in the future, leave a location for version C.
圖4說明客戶ASR服務端1、客戶ASR服務端2、客戶ASR服務端3、、、等與中央ASR雲端伺服端4的雲端通訊更新流程。客戶ASR服務端一般會在比方說凌晨兩點主動詢問中央ASR雲端伺服端4上的新版(步驟41),中央ASR雲端伺服端4答覆其新版(步驟42)。客戶ASR服務端比較其設定檔中的版本(步驟43),如果與新版相同就不會進行雲端更新。若與新版不同,客戶的ASR服務端就會向中央ASR雲端伺服端4請求下載新版(步驟44)。
FIG. 4 illustrates the cloud communication update process between the client ASR server 1, the client ASR server 2, the client ASR server 3, , , etc. and the central ASR
中央ASR雲端伺服端4將已經打包成ZIP(壓縮檔案)的新版的聲學和語言模型,計算其MD5(訊息摘要演算法)(步驟45),然後下載到客戶ASR服務端,並且告知其MD5數值(步驟46)。
The central
客戶ASR服務端對於下載後的ZIP進行MD5運算(步驟47),並比較回應訊令中的MD5數值(步驟48)。步驟48是為了驗證下載的ZIP檔案是否完整,MD5數值相同就表示ZIP檔案的完整性。 The client ASR server performs MD5 operation on the downloaded ZIP (step 47 ), and compares the MD5 value in the response message (step 48 ). Step 48 is to verify whether the downloaded ZIP archive is complete, and the same MD5 value indicates the completeness of the ZIP archive.
最後客戶ASR服務端進行ZIP解壓(步驟49),並將「設定檔」的描述指向新版(步驟50),最後重啟整個系統,即完成雲端更新。 Finally, the client ASR server performs ZIP decompression (step 49), and points the description of the "configuration file" to the new version (step 50), and finally restarts the entire system, that is, the cloud update is completed.
本發明的精神與範圍決定於下面的申請專利範圍,不受限於上述實施例。 The spirit and scope of the present invention are determined by the following patent application scope, and are not limited to the above-mentioned embodiments.
1:客戶ASR服務端 1: Client ASR server
2:客戶ASR服務端 2: Client ASR server
3:客戶ASR服務端 3: Client ASR server
4:中央ASR雲端伺服端 4: Central ASR cloud server
Claims (2)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109136375A TWI752682B (en) | 2020-10-21 | 2020-10-21 | Method for updating speech recognition system through air |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109136375A TWI752682B (en) | 2020-10-21 | 2020-10-21 | Method for updating speech recognition system through air |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI752682B true TWI752682B (en) | 2022-01-11 |
TW202217797A TW202217797A (en) | 2022-05-01 |
Family
ID=80809328
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109136375A TWI752682B (en) | 2020-10-21 | 2020-10-21 | Method for updating speech recognition system through air |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI752682B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090259470A1 (en) * | 2003-02-13 | 2009-10-15 | At&T Intellectual Property 1, L.P. | Bio-Phonetic Multi-Phrase Speaker Identity Verification |
TW201610986A (en) * | 2014-07-28 | 2016-03-16 | 弗勞恩霍夫爾協會 | Audio encoder and decoder using a frequency domain processor with full-band gap filling and a time domain processor |
CN107004410A (en) * | 2014-10-01 | 2017-08-01 | 西布雷恩公司 | Voice and connecting platform |
CN109977216A (en) * | 2019-04-01 | 2019-07-05 | 苏州思必驰信息科技有限公司 | Dialogue recommended method and system based on scene |
-
2020
- 2020-10-21 TW TW109136375A patent/TWI752682B/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090259470A1 (en) * | 2003-02-13 | 2009-10-15 | At&T Intellectual Property 1, L.P. | Bio-Phonetic Multi-Phrase Speaker Identity Verification |
TW201610986A (en) * | 2014-07-28 | 2016-03-16 | 弗勞恩霍夫爾協會 | Audio encoder and decoder using a frequency domain processor with full-band gap filling and a time domain processor |
CN107004410A (en) * | 2014-10-01 | 2017-08-01 | 西布雷恩公司 | Voice and connecting platform |
CN109977216A (en) * | 2019-04-01 | 2019-07-05 | 苏州思必驰信息科技有限公司 | Dialogue recommended method and system based on scene |
Also Published As
Publication number | Publication date |
---|---|
TW202217797A (en) | 2022-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108876121B (en) | Work order processing method and device, computer equipment and storage medium | |
US9940225B2 (en) | Automated error checking system for a software application and method therefor | |
CN110321254B (en) | Software version rollback method, device, server and storage medium | |
JP7297769B2 (en) | Shader distribution among client machines for pre-caching | |
WO2015078333A1 (en) | Method for offline updating virtual machine images | |
US20090259993A1 (en) | Sandbox Support for Metadata in Running Applications | |
CN107247592B (en) | Model management system and method under multi-service scene | |
CN108614701B (en) | Linux operating system customizing method and device | |
CN106371881B (en) | Method and system for updating program version in server | |
CN110825413A (en) | Database upgrading method and device and application deployment upgrading method and device | |
CN111400102A (en) | Application program change monitoring method, device, equipment and storage medium | |
TWI752682B (en) | Method for updating speech recognition system through air | |
US10949333B1 (en) | Application maturity console | |
CN114003264B (en) | Linux operating system upgrading method | |
CN115718606A (en) | Method and system for automatic and continuous integration and deployment of server | |
CN102541593A (en) | Rapid comparison method of versions of remote files | |
EP1895408A1 (en) | Method of re-using software attributes in graphical programs | |
US9454361B2 (en) | System and method of merging of objects from different replicas | |
CN112256283A (en) | Application version control method and device for Android equipment | |
CN110083351B (en) | Method and device for generating code | |
CN111464347A (en) | Automatic deployment device and method for large-scale heterogeneous equipment application | |
CN115357270A (en) | Database deployment method, device, equipment and storage medium | |
US8381171B2 (en) | Customized networked-based commerce system packages | |
CN107861739A (en) | ReactNative applications method of adjustment, client and system | |
CN114510322A (en) | Pressure measurement control method and device of service cluster, computer equipment and medium |