CN111179908A - Testing method and system of intelligent voice equipment - Google Patents
Testing method and system of intelligent voice equipment Download PDFInfo
- Publication number
- CN111179908A CN111179908A CN202010005894.9A CN202010005894A CN111179908A CN 111179908 A CN111179908 A CN 111179908A CN 202010005894 A CN202010005894 A CN 202010005894A CN 111179908 A CN111179908 A CN 111179908A
- Authority
- CN
- China
- Prior art keywords
- voice
- data
- test
- intelligent
- dialect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/01—Assessment or evaluation of speech recognition systems
Abstract
The invention discloses a testing method and a testing system of intelligent voice equipment, wherein the method comprises the following steps: converting the selected original text data into voice data corresponding to the preselected dialect data, and overlapping environmental sound data of a preselected scene to obtain complete test voice and play the test voice; acquiring recognition character data obtained by recognizing test voice by intelligent voice equipment; and comparing the identification character data with the original character data to obtain the identification accuracy of the intelligent voice equipment. The testing system of the intelligent voice equipment adopts the testing method of the intelligent voice equipment, so that the voice recognition accuracy of the intelligent voice equipment is tested under the condition that different environment sound data are superposed with dialect voice data with different timbres, and further more accurate intelligent voice equipment for voice recognition is provided for customers.
Description
Technical Field
The invention relates to the technical field of intelligent voice, in particular to a testing method and a testing system of intelligent voice equipment.
Background
Intelligent speech, i.e. intelligent speech technology, including speech recognition technology (ASR) and speech synthesis technology (TTS), starts with speech recognition technology and dates back to the 50 s of the 20 th century. With the development of information technology, intelligent voice technology has become the most convenient and effective means for people to acquire and communicate information.
At present, earphones, sound equipment and the like are widely applied as interactive intelligent voice equipment commonly used in the technical field of intelligent voice, but the mandarin in different areas is provided with dialects, particularly the old and the young can not even speak the mandarin, and the intelligent voice equipment has great difficulty and is not accurate enough for identifying the dialects, the voices of the male/female children in the old and the like in different areas. In addition, different environments make speech recognition of smart speech devices more difficult, for example: quiet environments, noisy indoor environments (airports, train stations, singing halls, etc.), noisy outdoor environments (traffic, people mixing, etc.) and different weather environments (rain, wind, thunder, etc.). Therefore, it is difficult to test the speech recognition accuracy of the intelligent speech device under the dialect in which different timbres are superimposed in different environments.
Disclosure of Invention
The invention aims to provide a testing method and a testing system of intelligent voice equipment, so as to realize testing of voice recognition accuracy of the intelligent voice equipment under the dialects with different overlapped timbres in different environments.
In order to achieve the above purpose, the invention provides the following technical scheme:
a testing method of intelligent voice equipment comprises the following steps:
converting the selected original text data into voice data corresponding to the preselected dialect data, and overlapping environmental sound data of a preselected scene to obtain complete test voice and play the test voice;
acquiring recognition character data obtained by recognizing test voice by intelligent voice equipment;
and comparing the identification character data with the original character data to obtain the identification accuracy of the intelligent voice equipment.
Preferably, the method for obtaining and playing the complete test voice specifically includes:
establishing a dialect database, a scene database and an original character database;
dialect data, scene data and original character data used for testing are set according to user selection;
converting the selected original text data into voice data corresponding to the preselected dialect data;
acquiring environmental sound data corresponding to a preselected scene;
and superposing the voice data and the environmental sound data to synthesize a complete test voice and play the test voice.
Specifically, the dialect data used for the test includes the region of the dialect, and the gender and age group of the speaker of the dialect;
the scenes used for the test include quiet environments, noisy indoor environments, noisy outdoor environments and different weather environments.
Preferably, the method for obtaining the recognized text data obtained by recognizing the test voice by the intelligent voice device includes:
the intelligent voice equipment identifies the test voice, and generates and displays corresponding identification characters in the character control;
and the identification character acquisition module is connected with the character control through an interface so as to acquire the identification characters.
Preferably, the comparison function of the character string is used to compare the identification text data with the original text data.
Preferably, the testing method of the intelligent voice device further comprises the steps of:
and automatically generating a test report according to the recognition accuracy of the intelligent voice equipment, and automatically sending the test report to a tester.
A test system of intelligent voice equipment comprises a voice generating module, a recognized character obtaining module and a comparison analysis module, wherein,
the voice generating module is used for converting the selected original text data into voice data corresponding to the preselected dialect data, overlapping the environmental sound data of the preselected scene to obtain complete test voice and playing the test voice;
the recognition character acquisition module is used for acquiring recognition character data obtained by recognizing test voice by the intelligent voice equipment;
and the comparison analysis module is used for comparing the identification character data with the original character data to obtain the identification accuracy of the intelligent voice equipment.
Preferably, the system further comprises a dialect database, a scene database and an original character database which are respectively used for storing dialect data, scene data and original character data used for testing.
Specifically, the speech generation module includes a setting unit, a conversion unit, and a synthesis unit, wherein,
the setting unit is used for setting dialect data, scene data and original character data used for testing according to user selection;
the conversion unit is used for converting the selected original text data into voice data corresponding to the preselected dialect data;
the synthesis unit is used for respectively acquiring the voice data and the environmental sound data corresponding to the preselected scene, superposing and synthesizing the voice data and the environmental sound data into a complete test voice and playing the test voice.
Preferably, the test system of the intelligent voice device further comprises a test report module, and the test report module is configured to automatically generate a test report according to the recognition accuracy of the intelligent voice device, and automatically send the test report to a tester.
Compared with the prior art, the testing method and the testing system of the intelligent voice equipment have the following beneficial effects that:
the test method of the intelligent voice equipment provided by the invention converts the selected original text data into the voice data of dialect version, superposes the environmental sound data of different scenes to synthesize complete test voice, and then plays the test voice for the intelligent voice equipment, and can set the combination of different dialects and different environments according to the selection of a user so as to realize the voice recognition accuracy rate of testing the intelligent voice equipment under the condition of superposing different dialects in different environments; the intelligent voice equipment automatically generates recognition character data after recognizing test voice, and finally obtains the recognition accuracy of the intelligent voice equipment by acquiring the recognition character data and comparing the recognition character data with the original character data, so that the test result is visual and accurate, and the workload of testers is reduced.
The testing system of the intelligent voice equipment provided by the invention adopts the testing method of the intelligent voice equipment, realizes the testing of the voice recognition accuracy of the intelligent voice equipment under the condition that different environment sound data are superposed with dialect voice data with different timbres, and further provides the intelligent voice equipment with more accurate voice recognition for customers.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of a testing method of an intelligent voice device according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for obtaining and playing a complete test voice according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1, the method for testing an intelligent speech device provided in this embodiment includes the steps of:
converting the selected original text data into voice data corresponding to the preselected dialect data, and overlapping environmental sound data of a preselected scene to obtain complete test voice and play the test voice;
acquiring recognition character data obtained by recognizing test voice by intelligent voice equipment;
comparing the recognition character data with the original character data to obtain the recognition accuracy of the intelligent voice equipment;
and automatically generating a test report according to the recognition accuracy of the intelligent voice equipment, and automatically sending the test report to a tester.
Converting the selected original text data into the voice data of dialect versions, overlapping the environmental sound data of different scenes, synthesizing complete test voice, then playing the test voice for the intelligent voice equipment, and setting the combination of different dialects and different environments according to the selection of a user so as to realize the voice recognition accuracy rate of testing the intelligent voice equipment under the condition of overlapping different dialects in different environments; the intelligent voice equipment automatically generates recognition character data after recognizing test voice, and finally obtains the recognition accuracy of the intelligent voice equipment by acquiring the recognition character data and comparing the recognition character data with the original character data, so that the test result is visual and accurate, and the workload of testers is reduced. And finally, automatically generating a test report, and automatically sending the test report to a tester in a communication mode such as a mail, so that the tester is not required to monitor the test process all the time, and the tester can timely collect the test report, find problems and correct the problems.
Referring to fig. 2, in the testing method of the intelligent voice device provided in this embodiment, the method for obtaining and playing the complete testing voice specifically includes:
establishing a dialect database, a scene database and an original character database;
dialect data, scene data and original character data used for testing are set according to user selection;
converting the selected original text data into voice data corresponding to the preselected dialect data;
acquiring environmental sound data corresponding to a preselected scene;
and superposing the voice data and the environmental sound data to synthesize a complete test voice and play the test voice.
The dialect data used for testing comprises the region of the dialect and the gender and age of a dialect speaker, the gender and age of the dialect speaker are set to simulate different timbres, particularly, the timbres with high difficulty and inaccurate recognition results of intelligent voice equipment such as male/female children, old male/female voices and the like are combined with the region of the dialect selected by a user to generate the dialect voice data with different timbres, and in addition, the user can adjust the voice attributes of the voice data such as the speed, the volume and the like according to needs. The voice data generation according to the Text data can be directly realized by adopting the software for Text-to-voice in the prior art and hardware devices such as a player and the like, such as a Text-to-voice broadcasting system, a Text-to-voice synthesizing system, a Text-to-voice assistant, a Text Speaker and the like, and can also be directly realized by programming.
The scenes used for the test include quiet environments, noisy indoor environments, noisy outdoor environments and different weather environments, wherein the quiet ambient sound data can be set to be quiet directly; the noisy indoor environment sound data can be recorded in advance to sound data of environments such as airports, railway stations, singing halls and the like; the noisy outdoor environment sound data can be sound data of environments such as roads, outdoor scenic spots and the like; the method comprises the steps that different weather environment sound data such as rain sound, wind sound, thunder and other weather environment sound data are stored in a scene database according to types and are selected by a common user, and a voice generation module of a test system automatically acquires the environment sound data of the scene selected by the user.
The method for superposing and synthesizing the voice data and the environmental sound data into complete test voice and playing the test voice can be realized by directly selecting two sets of playing equipment to play simultaneously, or can firstly superpose and synthesize the voice data and the environmental sound data into audio data by utilizing easy-cutting equal-tone video clipping software and then play the audio data, thereby providing freely combinable test voice generated by superposing different tone-color dialect voice data by different environmental sound data for testing the intelligent voice equipment.
In the testing method of the intelligent voice device provided in this embodiment, the method for obtaining the recognized text data obtained by recognizing the test voice by the intelligent voice device includes:
the intelligent voice equipment identifies the test voice, and generates and displays corresponding identification characters in the character control;
the identification character acquisition module is connected with the character control through an interface to acquire identification characters.
The text control of the intelligent voice equipment is integrated in the equipment body or in an APP corresponding to the equipment body, for example, a smart phone, a smart sound box and the like with a voice assistant function, and the text control is integrated in the equipment body; the intelligent earphones integrate the text controls into the corresponding APPs. The text control is connected by using sdk interface or api interface of the test system, so that the identification text can be easily acquired. When performing word alignment, it is preferable to align the recognized word data with the original word data by using a comparison function of a character string, and different programming languages have specific comparison functions for the character string, for example, comparison of the character string in C + + uses a match () function, a string comparison function strcmp in C language, and a public coolanequals () in Java, etc., which can be easily implemented by those skilled in the art in combination with the existing programming technology. Of course, the existing text comparison software or tool can also be directly called to compare the recognized text data with the original text data, such as the online text comparison tools of ultracompany and BeJSON, which is simple and fast. And then, the proportion of the characters which are not accurately identified in all the original character data is automatically counted, so that the identification accuracy of the intelligent voice equipment is obtained, the test result is visual and accurate, and the workload of testers is reduced. And finally, automatically generating a test report, and automatically sending the test report to a tester through communication modes such as mails and the like, so that the tester is not required to monitor the test process all the time, the test report is timely collected, problems are found and corrected, and more accurate intelligent voice equipment for voice recognition is further provided for clients.
Example two
The test system of the intelligent voice equipment provided by the embodiment of the invention comprises a voice generation module, a recognition character acquisition module and a comparison analysis module. The voice generating module is used for converting the selected original text data into voice data corresponding to the preselected dialect data, overlapping the environmental sound data of the preselected scene to obtain complete test voice and playing the complete test voice; the recognition character acquisition module is used for acquiring recognition character data obtained by recognizing the test voice by the intelligent voice equipment; and the comparison analysis module is used for comparing the recognized character data with the original character data to obtain the recognition accuracy of the intelligent voice equipment.
Preferably, the testing system of the intelligent voice device provided by the embodiment of the present invention further includes a dialect database, a scene database, and an original character database, which are respectively used for storing dialect data, scene data, and original character data used for testing.
Specifically, the speech generation module includes a setting unit, a conversion unit, and a synthesis unit. The setting unit is used for setting dialect data, scene data and original character data used for testing according to user selection; the conversion unit is used for converting the selected original text data into voice data corresponding to the pre-selected dialect data; the synthesis unit is used for respectively acquiring the voice data and the environmental sound data corresponding to the preselected scene, superposing and synthesizing the voice data and the environmental sound data into a complete test voice and playing the test voice.
Preferably, the test system for the intelligent voice device provided by the embodiment of the present invention further includes a test report module, where the test report module is configured to automatically generate a test report according to the recognition accuracy of the intelligent voice device, and automatically send the test report to a tester.
The testing system of the intelligent voice equipment provided by the invention adopts the testing method of the intelligent voice equipment, realizes the testing of the voice recognition accuracy of the intelligent voice equipment under the condition that different environment sound data are superposed with dialect voice data with different timbres, and further provides the intelligent voice equipment with more accurate voice recognition for customers. Compared with the prior art, the beneficial effects of the testing system of the intelligent voice device provided by the embodiment of the invention are the same as the beneficial effects of the testing method of the intelligent voice device provided by the first embodiment, and other technical features in the system are the same as those disclosed in the method of the first embodiment, which are not repeated herein.
In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A test method of intelligent voice equipment is characterized by comprising the following steps:
converting the selected original text data into voice data corresponding to the preselected dialect data, and overlapping environmental sound data of a preselected scene to obtain complete test voice and play the test voice;
acquiring recognition character data obtained by recognizing test voice by intelligent voice equipment;
and comparing the identification character data with the original character data to obtain the identification accuracy of the intelligent voice equipment.
2. The method for testing the intelligent voice device according to claim 1, wherein the method for obtaining and playing the complete test voice specifically comprises:
establishing a dialect database, a scene database and an original character database;
dialect data, scene data and original character data used for testing are set according to user selection;
converting the selected original text data into voice data corresponding to the preselected dialect data;
acquiring environmental sound data corresponding to a preselected scene;
and superposing the voice data and the environmental sound data to synthesize a complete test voice and play the test voice.
3. The intelligent voice device test method according to claim 2, wherein the dialect data used for the test includes the region of the dialect, and the gender and age group of the speaker of the dialect;
the scenes used for the test include quiet environments, noisy indoor environments, noisy outdoor environments and different weather environments.
4. The method for testing an intelligent voice device according to claim 1, wherein the method for acquiring recognized text data obtained by recognizing the test voice by the intelligent voice device comprises:
the intelligent voice equipment identifies the test voice, and generates and displays corresponding identification characters in the character control;
and the identification character acquisition module is connected with the character control through an interface so as to acquire the identification characters.
5. The method for testing an intelligent speech device according to claim 1, wherein the recognized text data is compared with the original text data by using a comparison function of a character string.
6. The method for testing an intelligent voice device according to claim 1, further comprising the steps of:
and automatically generating a test report according to the recognition accuracy of the intelligent voice equipment, and automatically sending the test report to a tester.
7. The testing system of the intelligent voice equipment is characterized by comprising a voice generating module, a recognized character acquiring module and a comparison and analysis module, wherein,
the voice generating module is used for converting the selected original text data into voice data corresponding to the preselected dialect data, overlapping the environmental sound data of the preselected scene to obtain complete test voice and playing the test voice;
the recognition character acquisition module is used for acquiring recognition character data obtained by recognizing test voice by the intelligent voice equipment;
and the comparison analysis module is used for comparing the identification character data with the original character data to obtain the identification accuracy of the intelligent voice equipment.
8. The system for testing an intelligent voice device according to claim 7, further comprising a dialect database, a scene database and an original text database for storing dialect data, scene data and original text data for testing, respectively.
9. The system for testing an intelligent speech device according to claim 8, wherein the speech generation module comprises a setup unit, a conversion unit, and a synthesis unit, wherein,
the setting unit is used for setting dialect data, scene data and original character data used for testing according to user selection;
the conversion unit is used for converting the selected original text data into voice data corresponding to the preselected dialect data;
the synthesis unit is used for respectively acquiring the voice data and the environmental sound data corresponding to the preselected scene, superposing and synthesizing the voice data and the environmental sound data into a complete test voice and playing the test voice.
10. The system for testing intelligent voice equipment according to claim 7, further comprising a test report module, wherein the test report module is configured to automatically generate a test report according to the recognition accuracy of the intelligent voice equipment, and automatically send the test report to a tester.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010005894.9A CN111179908A (en) | 2020-01-03 | 2020-01-03 | Testing method and system of intelligent voice equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010005894.9A CN111179908A (en) | 2020-01-03 | 2020-01-03 | Testing method and system of intelligent voice equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179908A true CN111179908A (en) | 2020-05-19 |
Family
ID=70657845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010005894.9A Pending CN111179908A (en) | 2020-01-03 | 2020-01-03 | Testing method and system of intelligent voice equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179908A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102813A (en) * | 2020-07-31 | 2020-12-18 | 南京航空航天大学 | Method for generating voice recognition test data based on context in user comment |
| CN113223559A (en) * | 2021-05-07 | 2021-08-06 | 北京有竹居网络技术有限公司 | Evaluation method, device and equipment for synthesized voice |
| CN113759869A (en) * | 2021-08-16 | 2021-12-07 | 深圳Tcl新技术有限公司 | Intelligent household appliance testing method and device |
| CN114120969A (en) * | 2022-01-29 | 2022-03-01 | 中国电子技术标准化研究院 | Method and system for testing voice recognition function of intelligent terminal and electronic equipment |
| CN114822501A (en) * | 2022-04-18 | 2022-07-29 | 四川虹美智能科技有限公司 | Automatic testing method and system for voice recognition and semantic recognition of intelligent equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170278509A1 (en) * | 2015-06-30 | 2017-09-28 | International Business Machines Corporation | Testing words in a pronunciation lexicon |
| CN109192195A (en) * | 2018-09-29 | 2019-01-11 | 深圳市微测检测有限公司 | A kind of speech recognition test macro and method |
| CN110415681A (en) * | 2019-09-11 | 2019-11-05 | 北京声智科技有限公司 | A kind of speech recognition effect testing method and system |
-
2020
- 2020-01-03 CN CN202010005894.9A patent/CN111179908A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170278509A1 (en) * | 2015-06-30 | 2017-09-28 | International Business Machines Corporation | Testing words in a pronunciation lexicon |
| CN109192195A (en) * | 2018-09-29 | 2019-01-11 | 深圳市微测检测有限公司 | A kind of speech recognition test macro and method |
| CN110415681A (en) * | 2019-09-11 | 2019-11-05 | 北京声智科技有限公司 | A kind of speech recognition effect testing method and system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102813A (en) * | 2020-07-31 | 2020-12-18 | 南京航空航天大学 | Method for generating voice recognition test data based on context in user comment |
| CN112102813B (en) * | 2020-07-31 | 2023-10-03 | 南京航空航天大学 | Speech recognition test data generation method based on context in user comment |
| CN113223559A (en) * | 2021-05-07 | 2021-08-06 | 北京有竹居网络技术有限公司 | Evaluation method, device and equipment for synthesized voice |
| CN113759869A (en) * | 2021-08-16 | 2021-12-07 | 深圳Tcl新技术有限公司 | Intelligent household appliance testing method and device |
| CN113759869B (en) * | 2021-08-16 | 2024-04-02 | 深圳Tcl新技术有限公司 | Intelligent household appliance testing method and device |
| CN114120969A (en) * | 2022-01-29 | 2022-03-01 | 中国电子技术标准化研究院 | Method and system for testing voice recognition function of intelligent terminal and electronic equipment |
| CN114822501A (en) * | 2022-04-18 | 2022-07-29 | 四川虹美智能科技有限公司 | Automatic testing method and system for voice recognition and semantic recognition of intelligent equipment |
| CN114822501B (en) * | 2022-04-18 | 2023-07-25 | 四川虹美智能科技有限公司 | Automatic test method and system for intelligent equipment voice recognition and semantic recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179908A (en) | Testing method and system of intelligent voice equipment | |
| US9430467B2 (en) | Mobile speech-to-speech interpretation system | |
| CN102930866B (en) | Evaluation method for student reading assignment for oral practice | |
| CN108847215B (en) | Method and device for voice synthesis based on user timbre | |
| CN107039050B (en) | Automatic testing method and device for voice recognition system to be tested | |
| CN106548772A (en) | Speech recognition test system and method | |
| CN105989842B (en) | The method, apparatus for comparing vocal print similarity and its application in digital entertainment VOD system | |
| US20110144997A1 (en) | Voice synthesis model generation device, voice synthesis model generation system, communication terminal device and method for generating voice synthesis model | |
| CN106328146A (en) | Video subtitle generation method and apparatus | |
| CN109147761A (en) | Test method based on batch speech recognition and TTS text synthesis | |
| CN113205793B (en) | Audio generation method and device, storage medium and electronic equipment | |
| CN110047474A (en) | A kind of English phonetic pronunciation intelligent training system and training method | |
| CN104361883A (en) | Production method and device of singing evaluation standards files | |
| CN109545196B (en) | Speech recognition method, device and computer readable storage medium | |
| JP2013088552A (en) | Pronunciation training device | |
| US11790913B2 (en) | Information providing method, apparatus, and storage medium, that transmit related information to a remote terminal based on identification information received from the remote terminal | |
| CN109545195B (en) | Accompanying robot and control method thereof | |
| Mögele et al. | SmartWeb UMTS Speech Data Collection: The SmartWeb Handheld Corpus. | |
| JP6003352B2 (en) | Data generation apparatus and data generation method | |
| CN113079327A (en) | Video generation method and device, storage medium and electronic equipment | |
| CN114724540A (en) | Model processing method and device, emotion voice synthesis method and device | |
| JP7200597B2 (en) | Information processing method and information processing system | |
| JP2016206394A (en) | Information providing system | |
| JP2013238819A (en) | Voice conversion function learning device, voice converter, voice conversion function learning method, voice conversion method and program | |
| KR20240033425A (en) | System and Method for matching of voice for speaking practice of foreign language |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |
|
| RJ01 | Rejection of invention patent application after publication |