CN102402982A - Loud reading system with selectable background sounds and realization method of system - Google Patents
Loud reading system with selectable background sounds and realization method of system Download PDFInfo
- Publication number
- CN102402982A CN102402982A CN2010102811972A CN201010281197A CN102402982A CN 102402982 A CN102402982 A CN 102402982A CN 2010102811972 A CN2010102811972 A CN 2010102811972A CN 201010281197 A CN201010281197 A CN 201010281197A CN 102402982 A CN102402982 A CN 102402982A
- Authority
- CN
- China
- Prior art keywords
- background sound
- text
- sound
- aloud
- bright
- 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
Abstract
The invention discloses a loud reading system with selectable background sounds, which comprises a background sound memory, a speech synthesizing device, a background sound generating module and a loud reading sound synthesizing module. The invention further discloses a realization method of the loud reading system, and the realization method includes steps of producing the background sound memory, labeling text, generating synthesis speech of the text, generating the background sounds, synthesizing loud reading sounds and the like. The loud reading system is rich in expressive force, and experiences of a user and interest in the system can be improved. When the user uses the loud reading system to listen to loud reading of the text, a recommended or default background sound can be selected, the user can also specify a preferred background sound or even can upload a background sound to the loud reading system, accordingly, a selection range of the background sound is enlarged, a loud reading effect of the text is improved, and interest in using the loud reading system of the user is also increased.
Description
Technical field
The present invention relates to a kind of bright read apparatus, especially a kind ofly can specify the bright read apparatus of selecting background sound based on content of text or user.The invention still further relates to the implementation method of this bright read apparatus.
Background technology
Current speech synthesis system no matter be based on parameter, also is based on the synthesis system of unit selection; The voice that are synthesized are all more dry as dust; Lack enough expressive forces, therefore, read aloud the bright read apparatus of news or novel merely as the website with such speech synthesis system; Shortage is to user's attractive force, and the audience continues the interest of listening listening to for a long time can lose because of it is dull after reading aloud.
In order to overcome above-mentioned defective, the author of the bright read apparatus that has can add background sound for reading aloud text, i.e. playing back music or other sound sound as a setting when playing synthetic speech, effect of reading aloud with raising and audience's interest.But at present, this type has background sound kind that the bright read apparatus of background sound can select seldom; Usually having only dull one or several, and the background sound relative fixed, can not change along with the difference of content of text; Therefore, the atmosphere of background sound performance sometimes or emotion may with read aloud the emotion that text contains and be not inconsistent, even produce conflict; For example, text representation be very happy emotion, and the background sound of joining is very sad; Like this, it is inharmonious that the audience will feel, even possibly produce resentment.
Summary of the invention
The technical matters that the present invention will solve provides the optional bright read apparatus of a kind of background sound, and it is rich in expressive force, can promote user's experience and to the interest of bright read apparatus.
For solving the problems of the technologies described above, bright read apparatus of the present invention comprises:
Speech synthetic device; Be used to generate the synthetic speech of reading aloud text; This speech synthetic device comprises text analysis model and phonetic synthesis module; Text analysis model is used for reading aloud text analysis, and analysis result is passed to the phonetic synthesis module, and the phonetic synthesis module is used to generate the synthetic speech of reading aloud text;
The background sound storehouse stores as the sound clip of reading aloud the system background sound, and this sound clip is music or unmusical sound;
The background sound generation module is used to generate the current corresponding background sound of text of reading aloud;
Bright pronunciation synthesis module connects speech synthetic device and background sound generation module respectively, is used for synthetic speech and background sound are merged the bright pronunciation of generation.
Another technical matters that the present invention will solve provides the implementation method of above-mentioned bright read apparatus.
For solving the problems of the technologies described above, the implementation method of bright read apparatus of the present invention comprises the following steps:
(A) collect music or unmusical sound, make the background sound storehouse;
(B) text that need read aloud in the bright read apparatus is marked, sets the kind of the background sound that each text need dispose, and with this as the background sound of reading aloud system recommendation;
When the user got into this bright read apparatus, bright read apparatus was realized function of reading aloud according to the following step:
(1) the prompting user imports the text that need read aloud;
(2) after the user had imported and read aloud text, this read aloud text the text analysis model analysis, and then, the phonetic synthesis module generates the synthetic speech that this reads aloud text according to the analysis result of text analysis model;
(3) the prompting user selects to read aloud the background sound of system recommendation or other sound clips in the background sound storehouse are read aloud the background sound of text as this.
(4) bright pronunciation synthesis module merges the background sound that user in synthetic speech and the step (3) selects, and generates a bright pronunciation, and plays.
Said step also comprises the steps: in (3)
If what the user selected is the background sound of reading aloud system recommendation, then execution in step (31); If what the user selected is other sound clips in the background sound storehouse, then execution in step (32);
(31) the background sound generation module is according to the result of step (B) Chinese version mark; Select this in the background sound storehouse and read aloud the needed background sound segment of text; And according to the length of each section of synthetic speech that obtains in the step (2), the length of the background sound fragment that adjustment is corresponding, then; Each background sound segment is stitched together, generates the background sound that this reads aloud text;
(32) the background sound generation module accesses corresponding sound clip in the background sound storehouse, and according to the length of the synthetic speech that obtains in the step (2), the length of adjustment background sound generates the background sound that this reads aloud text.
Bright read apparatus of the present invention and implementation method thereof; Be used in combination user's appointment and system and recommended dual mode based on content of text; Confirm the background sound of bright read apparatus; User's background sound that not only can selective system recommend or acquiescence, and can be at the fixed background sound of oneself liking of the existing background sound document of bright read apparatus, even can also upload the background sound that does not have in the bright read apparatus; Thereby enriched the kind of background sound and the expressive force of bright read apparatus, the effect and the user that have improved text reading use bright read apparatus to listen to the interest of text reading.
Description of drawings
Below in conjunction with accompanying drawing and embodiment the present invention is done further detailed explanation:
Fig. 1 is the module diagram of bright read apparatus of the present invention;
Fig. 2 is that the present invention recommends the process flow diagram under the background sound situation in user's selective system;
Fig. 3 is the process flow diagram of the present invention under user's specific context sound situation.
Embodiment
Understand for technology contents of the present invention, characteristics and effect being had more specifically, combine illustrated embodiment at present, details are as follows:
The bright read apparatus that background sound of the present invention is optional can be used for reading aloud automatically text, and for example, novel is read aloud in the novel website, and perhaps news website is read aloud news etc.This bright read apparatus includes a background sound storehouse; Store in the background sound storehouse and can be used as the sound clip of reading aloud the text background sound; These sound clips can be music; Song that for example a head is complete or the part fragment in the song also can be unmusical sound, for example environment sounds such as the patter of rain, sound of the wind, road noise.In addition, this bright read apparatus also comprises following modules:
Speech synthetic device is used for the synthetic speech according to the content generation text of reading aloud text, and speech synthetic device further comprises the text analysis model of front end and the phonetic synthesis module of rear end again; The text analysis model of front end is used for reading aloud text analysis; For example, how each literal of analyzing in the text is read, and how to make pauses in reading unpunctuated ancient writings etc.; Then analysis result is passed to the phonetic synthesis module of rear end, generated this by the phonetic synthesis module and read aloud the synthetic speech of text;
The background sound generation module is used to generate the current corresponding background sound of text of reading aloud;
Bright pronunciation synthesis module connects speech synthetic device and background sound synthesis module respectively, is used for the synthetic speech of speech synthetic device generation and the background sound of background sound generation module generation are merged, and generates bright pronunciation.
For the bright pronunciation that makes final generation more harmonious; Volume is more suitable; A volume can also further be set in bright read apparatus regulate interface; The volume that supplies the user to regulate background sound and synthetic speech respectively by the volume relation of bright pronunciation synthesis module according to background sound and synthetic speech, is merged into final bright pronunciation with background sound and synthetic speech then.
Below in conjunction with embodiment the implementation method of bright read apparatus of the present invention is done further detailed explanation.
At first, background music or other sound that can be used as background sound of collecting various expression different emotions (for example, happiness, sadness etc.) are (for example; Can record the sound under the various varying environments such as rain sound, sound of the wind, sound of sea wave, road noise, fairground brouhaha); Be made into the background sound storehouse, this background sound storehouse is open database, after the sound storehouse is built up; Still can replenish perfectly to it, promptly allow the user to upload audio files to the background sound storehouse.
Then, each text in the bright read apparatus is marked.Mark is that unit carries out with the paragraph, marks the kind of the background sound that every section text need dispose.Because the text automatic analysis technology does not also reach effect stable, that can receive now; So the present invention adopts artificial method to carry out text marking, can be by the author of text, editor or other people, according to the content of text; The background sound of selecting them to see fit; Be labeled in the text, because mark is that unit carries out with the paragraph, so the workload of mark is very little.For example, below be one section original text of reading aloud:
At this moment, the mobile phone that stands in chief of township Lee on the river levee has rung, and general headquarters beat from flood-fighting.
" chief of township Lee; we here are flood-fighting directorate, I am commander in chief Fan Jin, according to the data analysis result of directorate; flood peak will arrive your township after two hours; make provision against emergencies, and please you in two hours, evacuate near the resident the river levee two sides, guarantee the people's the security of the lives and property ".
" the model commander in chief please be relieved, and I guarantee to fulfil a task, and in addition, please send one group of people to support, and want to reinforce river levee here, but staff is not enough ".
" good, chief of township Lee, I go contact at once ".
The above-mentioned original text of reading aloud after unit marks, is marked text as follows:
< B:4>at this moment, the mobile phone that stands in chief of township Lee on the river levee has rung, general headquarters beat from flood-fighting.<E：4>
< B:11>" chief of township Lee; we here are flood-fighting directorate, I am commander in chief Fan Jin, according to the data analysis result of directorate; flood peak will arrive your township after two hours; make provision against emergencies, and please you in two hours, evacuate near the resident the river levee two sides, guarantee the people's the security of the lives and property ".<E：11>
< B:4>" the model commander in chief please be relieved, and I guarantee to fulfil a task, and in addition, please send one group of people to support, and want to reinforce river levee here, but staff is not enough ".<E：4>
< B:11>" good, chief of township Lee, I go contact at once ".<E：11>
In the above-mentioned mark text; The implication of each symbol is respectively: symbol " B " representes that the background sound of this section text begins; Symbol " E " representes that the background sound of this section text finishes, the kind of numbering (being arabic numeral) expression background sound, wherein; Numbering 4 is illustrated in big river bank, is illustrated in office and number 11.
Text is through after marking, and the background sound of mark i.e. conduct is read aloud the background sound of system recommendation, and when the user uses this bright read apparatus first, reads aloud the background sound of text acquiescence as this.
After the user got into this bright read apparatus, bright read apparatus at first pointed out the user to import the text that need read aloud.After the user confirms to read aloud text; The speech synthetic device of bright read apparatus utilizes the text analysis model of front end that this is read aloud text analysis; Confirm the pronunciation of each literal in the text; Analyze and how to make pauses in reading unpunctuated ancient writings etc., then by the phonetic synthesis module of rear end according to analysis result, generate the synthetic speech that this reads aloud text.
Then, read aloud the system prompt user and select the background sound that cooperates the text to read aloud.At this moment; The user can select to read aloud the background sound of system recommendation; Also can in the background sound storehouse, select other sound clips sound as a setting; If the background sound that does not have the user to want in the background sound storehouse, the song that the user also can like oneself or other audio files upload in the bright read apparatus, by bright read apparatus this audio files of uploading are saved in the background sound storehouse.
If the user has selected to read aloud the background sound of system recommendation; Promptly this reads aloud the background sound of text marking; Then the background sound generation module is according to the result of text marking, selects in the background sound storehouse and reads aloud the needed background sound fragment of text, and read aloud the length of each section of synthetic speech of text according to this; The length of the background sound fragment that adjustment is corresponding, being stitched together at last generates the whole background sound of reading aloud text.The method of adjustment background sound fragment length is: if current background sound fragment length according to the length of this section synthetic speech, keeps the previous section of this background sound fragment greater than the length of its corresponding that section synthetic speech, and the deletion aft section; If the length of current background sound fragment less than the length of that section synthetic speech of correspondence, then copies this background sound segment, until the length that reaches this section synthetic speech repeatedly.
If the user dislikes reading aloud the background sound of system recommendation; And in the background sound storehouse, specified other sound clips (comprising that user oneself uploads to the audio files in background sound storehouse) sound as a setting; The background sound generation module of bright read apparatus can directly access corresponding background sound segment according to user's designated result in the background sound storehouse, then according to the length of reading aloud the synthetic speech of text; The length of adjustment background sound generates the background sound of reading aloud text.The method of background sound length adjustment is: if the user has only specified a sound clip, then copy this sound clip repeatedly, until reaching the length that this reads aloud the synthetic speech of text; If the user has specified a plurality of sound clips, then circulation copies these sound clips in order, until reaching the length that this reads aloud the synthetic speech of text.For example, the user prepare to use this bright read apparatus to child with story, and the background sound when hoping that story is read aloud in the two first nursery rhymes conducts of using child to like; The user can be uploaded to bright read apparatus with these two first nursery rhymes; Bright read apparatus is according to the length of story synthetic speech, at the total length of two first nursery rhymes during less than synthetic speech length, and these two first nursery rhymes of circulation copy according to the order of sequence; Be stitched together at last and generate the background sound of story; And at the nursery rhymes total length during greater than synthetic speech length, the nursery rhymes segment of intercepting front is sound as a setting, and the segment that the back surpasses synthetic speech length then deletes.
No matter how the user selects background sound, bright read apparatus all can be noted user's selection result, and the background sound of giving tacit consent to when landing bright read apparatus next time as this user offers this user and selects.
At last, bright read apparatus can also further require the user to adjust the volume of synthetic speech and background sound respectively, after volume is confirmed, by reading aloud the phonetic synthesis module synthetic speech and background sound is merged bright pronunciation of generation again, plays.Certainly, do not adjust the volume of two sounds, and directly synthetic bright pronunciation is fine also, but influences the effect of the bright pronunciation that is synthesized sometimes.
In sum; Bright read apparatus and implementation method thereof that background sound of the present invention is optional; Not only can for text is mixed suitable background sound, but also allow the hobby specific context sound of user by the author who reads aloud text, editor or other people based on the content of reading aloud text according to oneself; Thereby enriched the kind of background sound, improved the expressive force of bright read apparatus when reading aloud text.
Claims (10)
1. bright read apparatus that background sound is optional comprises:
Speech synthetic device; Be used to generate the synthetic speech of reading aloud text; This speech synthetic device comprises text analysis model and phonetic synthesis module; Text analysis model is used for reading aloud text analysis, and analysis result is passed to the phonetic synthesis module, and the phonetic synthesis module is used to generate the synthetic speech of reading aloud text; It is characterized in that this bright read apparatus also comprises:
The background sound storehouse stores as the sound clip of reading aloud the system background sound, and this sound clip is music or unmusical sound;
The background sound generation module is used to generate the current corresponding background sound of text of reading aloud;
Bright pronunciation synthesis module connects speech synthetic device and background sound generation module respectively, is used for synthetic speech and background sound are merged the bright pronunciation of generation.
2. bright read apparatus as claimed in claim 1 is characterized in that: said unmusical sound is the environment sound.
3. bright read apparatus as claimed in claim 1 is characterized in that: this bright read apparatus also comprises volume adjusting interface, the volume that is used to regulate background sound and synthetic speech.
4. the implementation method of the described bright read apparatus of claim 1 is characterized in that, comprises the following steps:
(A) collect music or unmusical sound, make the background sound storehouse;
(B) text that need read aloud in the bright read apparatus is marked, sets the kind of the background sound that each text need dispose, and with this as the background sound of reading aloud system recommendation;
When the user got into this bright read apparatus, bright read apparatus was realized function of reading aloud according to the following step:
(1) the prompting user imports the text that need read aloud;
(2) after the user had imported and read aloud text, this read aloud text the text analysis model analysis, and then, the phonetic synthesis module generates the synthetic speech that this reads aloud text according to the analysis result of text analysis model;
(3) the prompting user selects to read aloud the background sound of system recommendation or other sound clips in the background sound storehouse are read aloud the background sound of text as this.
(4) bright pronunciation synthesis module merges the background sound that user in synthetic speech and the step (3) selects, and generates a bright pronunciation, and plays.
5. the implementation method of bright read apparatus as claimed in claim 4 is characterized in that: said mark adopts artificial method, is that unit carries out with the paragraph.
6. the implementation method of bright read apparatus as claimed in claim 4 is characterized in that, said step also comprises the steps: in (3)
If what the user selected is the background sound of reading aloud system recommendation, then execution in step (31); If what the user selected is other sound clips in the background sound storehouse, then execution in step (32);
(31) the background sound generation module is according to the result of step (B) Chinese version mark; Select this in the background sound storehouse and read aloud the needed background sound segment of text; And according to the length of each section of synthetic speech that obtains in the step (2), the length of the background sound fragment that adjustment is corresponding, then; Each background sound segment is stitched together, generates the background sound that this reads aloud text;
(32) the background sound generation module accesses corresponding sound clip in the background sound storehouse, and according to the length of the synthetic speech that obtains in the step (2), the length of adjustment background sound generates the background sound that this reads aloud text.
7. the implementation method of bright read apparatus as claimed in claim 6; It is characterized in that: in the said step (31); The method of adjustment background sound fragment length is: when background sound fragment length during greater than the length of the synthetic speech of correspondence; According to the length of this section synthetic speech, keep the previous section of this background sound fragment, the deletion aft section; When the length of this background sound fragment during, copy this background sound segment repeatedly, until the length that reaches this section synthetic speech less than the length of the synthetic speech of correspondence.
8. the implementation method of bright read apparatus as claimed in claim 6; It is characterized in that: in the said step (32); The method of adjustment background sound length is: when the user has only specified a sound clip, copy this sound clip repeatedly, until reaching the length that this reads aloud the synthetic speech of text; When the user had specified plural sound clip, circulation copied these sound clips in order, until reaching the length that this reads aloud the synthetic speech of text.
9. the implementation method of bright read apparatus as claimed in claim 6; It is characterized in that: after accomplish said step (31) or (32); Read aloud the system prompt user and adjust the volume of synthetic speech and background sound respectively, confirmed the volume of synthetic speech and background sound the user after, execution in step (4) again.
10. the implementation method of bright read apparatus as claimed in claim 4, it is characterized in that: other sound clips in the said step (3) comprise that the user is uploaded to the audio files of bright read apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102811972A CN102402982A (en) | 2010-09-14 | 2010-09-14 | Loud reading system with selectable background sounds and realization method of system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102811972A CN102402982A (en) | 2010-09-14 | 2010-09-14 | Loud reading system with selectable background sounds and realization method of system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102402982A true CN102402982A (en) | 2012-04-04 |
Family
ID=45885133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010102811972A Pending CN102402982A (en) | 2010-09-14 | 2010-09-14 | Loud reading system with selectable background sounds and realization method of system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102402982A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105336329A (en) * | 2015-09-25 | 2016-02-17 | 联想(北京)有限公司 | Speech processing method and system |
| CN105609096A (en) * | 2015-12-30 | 2016-05-25 | 小米科技有限责任公司 | Text data output method and device |
| CN105787005A (en) * | 2016-02-22 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Information processing method and mobile terminal |
| CN105872253A (en) * | 2016-05-31 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Live broadcast sound processing method and mobile terminal |
| CN107464555A (en) * | 2016-06-03 | 2017-12-12 | 索尼移动通讯有限公司 | Background sound is added to the voice data comprising voice |
| CN108242238A (en) * | 2018-01-11 | 2018-07-03 | 广东小天才科技有限公司 | A kind of audio file generation method and device, terminal device |
| CN109065018A (en) * | 2018-08-22 | 2018-12-21 | 北京光年无限科技有限公司 | A kind of narration data processing method and system towards intelligent robot |
| CN109686366A (en) * | 2018-12-12 | 2019-04-26 | 珠海格力电器股份有限公司 | Voice broadcast method and device |
| CN110177155A (en) * | 2019-06-24 | 2019-08-27 | 广州酷狗计算机科技有限公司 | Playback method, the apparatus and system of audio file |
| WO2020024582A1 (en) * | 2018-07-28 | 2020-02-06 | 华为技术有限公司 | Speech synthesis method and related device |
| CN111128204A (en) * | 2018-11-01 | 2020-05-08 | 阿里巴巴集团控股有限公司 | Comment method and device, terminal device and computer storage medium |
| CN111276122A (en) * | 2020-01-14 | 2020-06-12 | 广州酷狗计算机科技有限公司 | Audio generation method and device and storage medium |
| CN112040310A (en) * | 2020-09-03 | 2020-12-04 | 广州优谷信息技术有限公司 | Audio and video synthesis method and device, mobile terminal and storage medium |
| TWI722709B (en) * | 2019-12-10 | 2021-03-21 | 東海大學 | Method and system for generating intelligent sound story |
| CN112541323A (en) * | 2020-12-21 | 2021-03-23 | 广州优谷信息技术有限公司 | Method and device for processing reading materials |
| CN112562430A (en) * | 2019-09-26 | 2021-03-26 | 阿里巴巴集团控股有限公司 | Auxiliary reading method, video playing method, device, equipment and storage medium |
-
2010
- 2010-09-14 CN CN2010102811972A patent/CN102402982A/en active Pending
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105336329A (en) * | 2015-09-25 | 2016-02-17 | 联想(北京)有限公司 | Speech processing method and system |
| CN105609096A (en) * | 2015-12-30 | 2016-05-25 | 小米科技有限责任公司 | Text data output method and device |
| CN105787005A (en) * | 2016-02-22 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Information processing method and mobile terminal |
| CN105872253A (en) * | 2016-05-31 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Live broadcast sound processing method and mobile terminal |
| CN105872253B (en) * | 2016-05-31 | 2020-07-07 | 腾讯科技（深圳）有限公司 | Live broadcast sound processing method and mobile terminal |
| CN107464555A (en) * | 2016-06-03 | 2017-12-12 | 索尼移动通讯有限公司 | Background sound is added to the voice data comprising voice |
| CN108242238B (en) * | 2018-01-11 | 2019-12-31 | 广东小天才科技有限公司 | Audio file generation method and device and terminal equipment |
| CN108242238A (en) * | 2018-01-11 | 2018-07-03 | 广东小天才科技有限公司 | A kind of audio file generation method and device, terminal device |
| WO2020024582A1 (en) * | 2018-07-28 | 2020-02-06 | 华为技术有限公司 | Speech synthesis method and related device |
| CN109065018A (en) * | 2018-08-22 | 2018-12-21 | 北京光年无限科技有限公司 | A kind of narration data processing method and system towards intelligent robot |
| CN109065018B (en) * | 2018-08-22 | 2021-09-10 | 北京光年无限科技有限公司 | Intelligent robot-oriented story data processing method and system |
| CN111128204A (en) * | 2018-11-01 | 2020-05-08 | 阿里巴巴集团控股有限公司 | Comment method and device, terminal device and computer storage medium |
| CN109686366A (en) * | 2018-12-12 | 2019-04-26 | 珠海格力电器股份有限公司 | Voice broadcast method and device |
| CN110177155A (en) * | 2019-06-24 | 2019-08-27 | 广州酷狗计算机科技有限公司 | Playback method, the apparatus and system of audio file |
| CN112562430A (en) * | 2019-09-26 | 2021-03-26 | 阿里巴巴集团控股有限公司 | Auxiliary reading method, video playing method, device, equipment and storage medium |
| TWI722709B (en) * | 2019-12-10 | 2021-03-21 | 東海大學 | Method and system for generating intelligent sound story |
| CN111276122A (en) * | 2020-01-14 | 2020-06-12 | 广州酷狗计算机科技有限公司 | Audio generation method and device and storage medium |
| CN111276122B (en) * | 2020-01-14 | 2023-10-27 | 广州酷狗计算机科技有限公司 | Audio generation method and device and storage medium |
| CN112040310A (en) * | 2020-09-03 | 2020-12-04 | 广州优谷信息技术有限公司 | Audio and video synthesis method and device, mobile terminal and storage medium |
| CN112541323A (en) * | 2020-12-21 | 2021-03-23 | 广州优谷信息技术有限公司 | Method and device for processing reading materials |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102402982A (en) | Loud reading system with selectable background sounds and realization method of system | |
| CN101557483B (en) | Methods and systems for generating a media program | |
| JP2015517684A (en) | Content customization | |
| CN108269560A (en) | A kind of speech synthesizing method and system | |
| Bell et al. | SMARTVOX-A Web-Based Distributed Media Player as Notation Tool For Choral Practices | |
| Leech‐Wilkinson | Cortot's Berceuse | |
| Lemaitre et al. | Vocal imitations of basic auditory features | |
| CN101094469A (en) | Method and device for creating prompt information of mobile terminal | |
| KR20100005177A (en) | Customized learning system, customized learning method, and learning device | |
| CN102447785A (en) | Generation method of prompt information of mobile terminal and device | |
| Phillips et al. | Multimodality and aurality: Sound spaces in student digital book trailers | |
| Green | User serviceable parts: Practice, technology, sociality and method in live electronic musicking | |
| JP2007200495A (en) | Music reproduction apparatus, music reproduction method and music reproduction program | |
| Fröjd et al. | Sound texture synthesis using an overlap–add/granular synthesis approach | |
| Rudi | Soundscape in the Arts | |
| Hunt | Composition as Commentary: Voice and Poetry in Electroacoustic Music | |
| Cárcamo-Huechante | Wixage anai!: Mapuche Voices on the Air | |
| Cushing | Three solitudes and a DJ: A mashed-up study of counterpoint in a digital realm | |
| Heinrich et al. | Influences of word predictability and type of masker noise on intelligibility of sung text in live concerts | |
| Coroiu | Richard Clayderman and André Gagnon-Common references of componistic stylistics | |
| Flood | Magnús Pálsson. Gapassipi | |
| KR20080066896A (en) | Customized learning system, customized learning method, and learning device | |
| KR20080065205A (en) | Customized learning system, customized learning method, and learning device | |
| Prior | Sonic methods in geography | |
| Alper | XM reinvents Radio's Future |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120404 |