CN109686366A - Voice broadcast method and device - Google Patents
Voice broadcast method and device Download PDFInfo
- Publication number
- CN109686366A CN109686366A CN201811517453.6A CN201811517453A CN109686366A CN 109686366 A CN109686366 A CN 109686366A CN 201811517453 A CN201811517453 A CN 201811517453A CN 109686366 A CN109686366 A CN 109686366A
- Authority
- CN
- China
- Prior art keywords
- text
- casting
- music
- voice broadcast
- background music
- 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
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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The present invention proposes a kind of voice broadcast method and device, and wherein method comprises determining that the casting text of voice broadcast；Background music is determined according to casting text；It plays casting text and plays background music simultaneously.The content that casting text is understood and absorbed to facilitate user, improves user experience, does not have mood when solving voice broadcast in the prior art, excessively stiff, the low problem of user experience.
Description
Technical field
The present invention relates to voice broadcast fields, in particular to voice broadcast method and device.
Background technique
As artificial intelligence is gradually pursued, numerous intelligent sound equipment are come into being, intelligent sound assistant at
For a part in life.Intelligent sound assistance application is convenient, has the function of to inquire song, story, weather, stroke, translation etc..
For existing voice broadcast equipment, when carrying out voice broadcast, casting voice is stiff does not have mood, and being not achieved has
The effect conveyed is imitated, causes user experience low.
Therefore, user experience when voice broadcast is improved, is this field urgent problem to be solved.
Summary of the invention
The present invention provides a kind of voice broadcast method and devices, for improving user experience when voice broadcast.
To solve the above-mentioned problems, as one aspect of the present invention, a kind of voice broadcast method is provided, comprising:
Determine the casting text of voice broadcast；
Background music is determined according to casting text；
It plays casting text and plays background music simultaneously.
Optionally, voice broadcast text is determined, comprising:
Obtain phonetic order and/or text instruction；
Semantic parsing is carried out to phonetic order and/or text instruction；
Casting text is determined according to semantic parsing result.
Optionally, casting text is determined according to semantic parsing result, comprising:
Determine in phonetic order whether include inquiry instruction according to semantic parsing result；
If so, then being inquired according to inquiry instruction, use query result as voice broadcast text.
Optionally, background music is determined according to casting text, comprising:
Obtain the text type and/or text keyword of casting text；
Corresponding alternative music is obtained according to text type and/or text key word；
Background music is chosen from alternative music according to preset rules.
Optionally, any music is corresponding at least one text type and/or opposite at least one text keyword
It answers；
Broadcast text have at least one text type and/or have at least one broadcast text keyword；
Alternative music is corresponding with casting one or more text types of text；
And/or alternative music is corresponding with casting one or more text keywords of text.
Optionally, text type, comprising: style type, text reader and text mood.
Optionally, it after determining background music according to casting text, is playing casting text and is playing background sound simultaneously
Before pleasure, further includes:
Setting plays volume value when casting text；
And/or volume value when setting broadcasting background music.
The application also proposes a kind of sound broadcasting device, comprising:
Text identification unit, for determining the casting text of voice broadcast；
Music acquiring unit, for determining background music according to casting text；
Voice broadcast unit, for playing casting text and while playing background music.
Optionally, text identification unit determines voice broadcast text, comprising:
Obtain phonetic order and/or text instruction；
Semantic parsing is carried out to phonetic order and/or text instruction；
Casting text is determined according to semantic parsing result.
Optionally, text identification unit determines casting text according to semantic parsing result, comprising:
Determine in phonetic order whether include inquiry instruction according to semantic parsing result；
If so, then being inquired according to inquiry instruction, use query result as voice broadcast text.
Optionally, music acquiring unit determines background music according to casting text, comprising:
Obtain the text type and/or text keyword of casting text；
Corresponding alternative music is obtained according to text type and/or text key word；
Background music is chosen from alternative music according to preset rules.
Optionally, any music is corresponding at least one text type and/or opposite at least one text keyword
It answers；
Broadcast text have at least one text type and/or have at least one broadcast text keyword；
Alternative music is corresponding with casting one or more text types of text；
And/or alternative music is corresponding with casting one or more text keywords of text.
Optionally, text type, comprising: style type, text reader and text mood.
It optionally, further include sound volume regulation unit；
After music acquiring unit determines background music according to casting text, casting text is played in voice broadcast unit
And simultaneously play background music before, sound volume regulation unit is used for:
Setting plays volume value when casting text；
And/or volume value when setting broadcasting background music.
The invention proposes a kind of voice broadcast method and devices, determine background music according to casting text, broadcast in broadcasting
This while of message, plays background music, to facilitate the content that user understands and absorbs casting text, improves user experience,
There is no mood when solving voice broadcast in the prior art, excessively stiff, the low problem of user experience.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the method for voice broadcast in the embodiment of the present invention；
Fig. 2 is a kind of composition figure of the device of voice broadcast in the embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the specific embodiment of the invention and
Technical solution of the present invention is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Covering non-exclusive includes to be not necessarily limited to for example, containing the process, method of a series of steps or units, device, product or electric appliance
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that electric appliance is intrinsic.
In the prior art, when carrying out voice broadcast, often only text is broadcasted in simple broadcasting, not any
The mode of emotion, broadcasting is extremely stiff, influences the content that user absorbs and understands casting text, user experience is low, in order to improve
The experience of user, the application propose a kind of voice broadcast method, to improve user experience when voice broadcast, user are helped to understand
The content of text is broadcasted with absorption, as shown in Figure 1, the method that the application proposes, comprising:
S11: the casting text of voice broadcast is determined；
S12: background music is determined according to casting text；
S13: playing casting text and plays background music simultaneously.
Specifically, the method that the application proposes can be used for smart machine, especially intelligent sound equipment, such as voice helps
The equipment such as hand, the household electrical appliance with phonetic function, smartwatch, Intelligent bracelet, in the casting text for determining voice broadcast,
The microphone of intelligent sound equipment receives user and issues to obtain phonetic order either smart machine, such as smart phone, passes through
The content of text of user's input is detected to determine the intention of user, determines the casting text of voice broadcast according to the user's intention,
Such as user inputs in mobile phone searching and searches Qiao Busi brief introduction, then mobile phone will search for the brief introduction of Qiao Busi, the brief introduction automatically
Word content be exactly this voice broadcast casting text, later according to casting text determine background music, play broadcast
It is played out in the form of voice broadcast when text, while playing background music, it should be noted that casting text is corresponding
Background music possible more than one is first, i.e., one casting text can correspond to multiple background musics, but play appointing for casting text
One moment only played a wherein first background music, such as when the content of casting text is the brief introduction of Qiao Busi, in Qiao Busi cause
High music is played during smoothly, droning music is played when Qiao Busi cause is tried out, so that when playing casting text
The variation of background music is realized according to the variation of content of text, so that user experience is improved, the voice broadcast that the application proposes
Method is according to different casting texts so that it is determined that corresponding background music, enables user when listening to voice broadcast
More accurately understand casting text, improves user experience, solving voice broadcast in the prior art does not have mood to be difficult to absorb
The problem of grasping casting content of text.Optionally, it if the casting text Central Plains got is originally embedded with embedded music, protects
It stays embedded music or replaces the embedded music with background music.
Preferably, voice broadcast text is determined, comprising:
Obtain phonetic order and/or text instruction；
Semantic parsing is carried out to phonetic order and/or text instruction；
Casting text is determined according to semantic parsing result.
Specifically, the method for the voice broadcast that the application proposes is preferred for intelligent terminal, such as intelligent sound control is set
It is standby, such as with voice control function mobile phone, the microphone on mobile phone receives the control voice of user, refers to obtain voice
It enables, then the input interface in semantic parsing or mobile phone is carried out to phonetic order and detects that user has input text instruction, it is right
Text instruction is parsed.Here the process for carrying out semantic parsing can be carried out automatically by mobile phone, or will be on phonetic order
Server is passed to, semantic parsing is carried out to phonetic order by server, semantic parsing result is obtained after parsing and determines casting text
Sheet, semantic parsing result is the content wanted to the user of phonetic order into determination after analysis, such as phonetic order here
Be: " how is weather tomorrow ", then the result of semantic parsing is exactly that user wants inquiry weather tomorrow, and corresponding casting text is exactly
The weather of tomorrow, such as casting text can be " 26-30 DEG C of temperature, calm tomorrow, clear to cloudy ".In another example phonetic order
It is " GDP for inquiring this year ", then semantic parsing result is that user wants inquiry GDP, then corresponding text of broadcasting is the state in this year
Interior total output value.
Optionally, casting text is determined according to semantic parsing result, comprising:
Determine in phonetic order whether include inquiry instruction according to semantic parsing result；
If so, then being inquired according to inquiry instruction, use query result as voice broadcast text.
Specifically, judging in phonetic order whether to include inquiry after parsing phonetic order or literal order
Instruction, such as phonetic order or literal order can be analyzed, whether see wherein has for example: lookup, search, inquiry etc. are closed
Key word is to judge whether there is inquiry instruction.It when having inquiry instruction, is inquired according to inquiry instruction, then obtains inquiry
As a result it is used as voice broadcast text, to meet the needs of user.
Optionally, background music is determined according to casting text, comprising:
Obtain the text type and/or text keyword of casting text；
Corresponding alternative music is obtained according to text type and/or text key word；
Background music is chosen from alternative music according to preset rules.
Specifically, the corresponding text type of casting text can be a variety of, i.e., one casting text corresponds to multiple text classes
Type, same casting text can correspond to multiple text keywords, and text type may include: style type, text reading
Person and text mood.Such as: user requires the resume of inquiry Huo Jin by voice command, then the life of Huo Jin is found from network
Brief introduction, text type are personage's biography, corresponding text reader for greater than 7 years old, text mood was neutrality at this time.Text type refers to
Be subject matter, the style of text, such as can be autobiography, novel, prose, children's stories etc., text reader refers to be suitable for reading this to broadcast
Crowd of message sheet, such as children, old man, young people, owner, sex etc., text mood are in the casting text
The mood classification contained, for example, actively, passive and neutrality etc..Text keyword can be the concrete term in casting text,
It is also possible to the label being arranged for word, i.e. the text keyword label that is to be able to quick localization of text, such as can be with
Be: science and technology, personage, natural etc. are also possible to specific a certain item science and technology, some personage or some natural landscape etc.
Deng.By setting text type and text keyword quickly to be matched with alternative music.Such as casting text is Huo Jin
Biography when, text keyword may is that personage, Huo Jin.When broadcasting text is Andersen's children's stories " lobo ", text
Keyword may is that Andersen's children's stories, lobo.Text type are as follows: children's stories, corresponding text reader are children, corresponding text
This mood is neutrality.
Optionally, any music is corresponding at least one text type and/or opposite at least one text keyword
It answers；
Broadcast text have at least one text type and/or have at least one broadcast text keyword；
Alternative music is corresponding with casting one or more text types of text；
And/or alternative music is corresponding with casting one or more text keywords of text.
Specifically, having pre-established music libraries in the method that the application proposes, more songs are stored in music libraries, in advance
For each music in music libraries, corresponding text type and/or text keyword, the corresponding all texts of a music are set
Type and the set of all text keywords composition can be the musical features set of the music, broadcast all text types of text
With text keyword composition set can be the casting text casting characteristic set, the musical features set of alternative music with broadcast
There are intersections for the casting characteristic set of message sheet, such as: the corresponding text type of alternative music is: children, positive, children's stories, right
The keyword answered is: Andersen, Snow White.And broadcasting at least one in the text type of text is the corresponding text of alternative music
This type, and/or, broadcasting at least one in the text keyword of text is the corresponding text keyword of alternative music, is passed through
Text type is respectively set for casting text and music and the quick of casting text and alternative music may be implemented in text keyword
Matching.Need to obtain optimum music after obtaining alternative music from alternative music as music type.In the application
Preset rules for example can be weighting algorithm, such as be respectively each text type and text keyword setting power of casting text
Weight, each alternative music calculates weighted value according to text type and text keyword of its corresponding casting text, from alternative
Select the highest music of weighted value as background music in music.Such as: user issues phonetic order and wishes to play Andersen child
Words, then broadcasting text is children, broadcasts the text type of text are as follows: children's (weight 5), actively (weight 6) and children's stories
(weight 4) broadcasts the text keyword of text are as follows: Andersen's (weight 2), Snow White's (weight 3), if one is standby
Select music corresponding with children and Andersen, then the weighted value of the alternative music is that the weight of children adds the weight etc. of Andersen
In 7.The specific weight of each text type and the weight of keyword can according to need and be configured, preferred text type
Weight be greater than text keyword weight, the presence of text keyword be in order to enable screening music it is more accurate.Default rule
It then can also be and chosen according to scoring height of the user each on network to each music, having collected a large number of users to each
After the scoring of a music, chosen according to scoring height, the highest alternative music that preferably scores is as background music.Either in advance
The use habit for collecting active user, the use preference of user is determined according to use habit, according to using preference to determine background sound
It is happy.Such as: the use preference that user is determined by collecting information in advance is to like listening children's class music, likes positive music,
Like the children's stories of Andersen, then preferably user recommends alternative music background corresponding with children, positive, Andersen and children's stories
Music.
Optionally, it after determining background music according to casting text, is playing casting text and is playing background sound simultaneously
Before pleasure, further includes:
Setting plays volume value when casting text；
And/or volume value when setting broadcasting background music.
Specifically, needing to combine current environment in the volume value of the volume value and background music that set casting text
Volume first obtains current environmental volume, the volume value for playing casting text is adjusted according to environmental volume and plays background sound
Happy volume value.The corresponding volume value for increasing and playing text and background music is needed when environmental volume is larger, such as guarantees to broadcast
The volume for putting text and background music is not less than environmental volume, to prevent volume is improper from causing user that can hear casting text
This content.Preferably, setting plays the volume value of background music no more than the volume value for playing casting text at any one time.
The application also proposes a kind of sound broadcasting device, comprising:
Text identification unit 10, for determining the casting text of voice broadcast；
Music acquiring unit 20, for determining background music according to casting text；
Voice broadcast unit 30, for playing casting text and while playing background music.
Specifically, the device that the application proposes can be smart machine, especially intelligent sound equipment, such as voice helps
The equipment such as hand, the household electrical appliance with phonetic function, smartwatch, Intelligent bracelet are by smart phone of sound broadcasting device
Example, text identification unit 10 can be the speech processing software on smart phone, in the casting text for determining voice broadcast, intelligence
The microphone of energy mobile phone receives user and issues to obtain phonetic order alternatively, semantic by the content of text progress of detection user's input
It identifies the intention to determine user, determines the casting text of voice broadcast according to the user's intention.Such as user is in mobile phone searching
Qiao Busi brief introduction is searched in middle input, then mobile phone will search for the brief introduction of Qiao Busi automatically, and the word content of the brief introduction is exactly this
The casting text of voice broadcast determines background music according to casting text later, uses voice broadcast when playing and broadcasting text
Form play out, while playing background music, it should be noted that the corresponding background music of casting text may more than one
Head, i.e., one casting text can correspond to multiple background musics, but only play wherein one in any moment for playing casting text
First background music, such as content when being the brief introduction of Qiao Busi of casting text, play high during Qiao Busi has a successful career
Music plays droning music when Qiao Busi cause is tried out so that voice broadcast unit 30 play casting text when according to
The variation of background music is realized in the variation of content of text, so that user experience is improved, the method for the voice broadcast that the application proposes
According to different casting texts so that it is determined that corresponding background music, enable user when listening to voice broadcast more
Accurately understand casting text, improves user experience, solving voice broadcast in the prior art does not have mood to be difficult to absorb grasp
The problem of broadcasting content of text.
The device that the application proposes can also be combined by server and intelligent terminal two parts, and intelligent terminal receives user
Instruction, send server for the instruction, server as the corresponding casting text of text identification unit judges user instruction,
Then server is used as music acquiring unit to inquire suitable background music from database simultaneously, then will casting text and background
Music sends back intelligent terminal, plays casting text and background music as voice broadcast unit 30 by intelligent terminal.
Optionally, text identification unit 10 determines voice broadcast text, comprising:
Obtain phonetic order and/or text instruction；
Semantic parsing is carried out to phonetic order and/or text instruction；
Casting text is determined according to semantic parsing result.
Specifically, the device for the voice broadcast that the application proposes preferably includes intelligent terminal and server, such as with language
Sound control functional mobile phone and server, the microphone on mobile phone receives the control voice of user, to obtain phonetic order, then right
The input interface that phonetic order carries out on semantic parsing or mobile phone detects that user has input text instruction, refers to text
Order is parsed.Here the process for carrying out semantic parsing can be carried out automatically by mobile phone, or phonetic order is uploaded to clothes
Business device carries out semantic parsing to phonetic order by server, obtains semantic parsing result after parsing and determine casting text, here
Semantic parsing result is the content wanted to the user of phonetic order into determination after analysis, such as phonetic order is: " tomorrow
How is weather ", then the result of semantic parsing is exactly that user wants inquiry weather tomorrow, and corresponding casting text is exactly the day of tomorrow
Gas, such as casting text can be " 26-30 DEG C of temperature, calm tomorrow, clear to cloudy ".In another example phonetic order is that " inquiry is modern
The GDP " in year, then semantic parsing result is that user wants inquiry GDP, then corresponding casting text is total for the domestic production in this year
Value.
Optionally, text identification unit 10 determines casting text according to semantic parsing result, comprising:
Determine in phonetic order whether include inquiry instruction according to semantic parsing result；
If so, then being inquired according to inquiry instruction, use query result as voice broadcast text.
Specifically, judging in phonetic order whether to include inquiry after parsing phonetic order or literal order
Instruction, such as phonetic order or literal order can be analyzed, whether see wherein has for example: lookup, search, inquiry etc. are closed
Key word is to judge whether there is inquiry instruction.It when having inquiry instruction, is inquired according to inquiry instruction, then obtains inquiry
As a result it is used as voice broadcast text, to meet the needs of user.
Optionally, music acquiring unit 20 determines background music according to casting text, comprising:
Obtain the text type and/or text keyword of casting text；
Corresponding alternative music is obtained according to text type and/or text key word；
Background music is chosen from alternative music according to preset rules.
Specifically, the corresponding text type of casting text can be a variety of, i.e., one casting text corresponds to multiple text classes
Type, same casting text can correspond to multiple text keywords, and text type may include: style type, text reading
Person and text mood.Such as: user requires the resume of inquiry Huo Jin by voice command, then the life of Huo Jin is found from network
Brief introduction, text type are personage's biography, corresponding text reader for greater than 7 years old, text mood was neutrality at this time.Text type refers to
Be subject matter, the style of text, such as can be autobiography, novel, prose, children's stories etc., text reader refers to be suitable for reading this to broadcast
Crowd of message sheet, such as children, old man, young people, owner, sex etc., text mood are in the casting text
The mood classification contained, for example, actively, passive and neutrality etc..Text keyword is to be able to the mark of quick localization of text
Label, such as may is that science and technology, personage, natural etc..By setting text type and text keyword with quick and alternative sound
Pleasure is matched.
Optionally, any music is corresponding at least one text type and/or opposite at least one text keyword
It answers；
Broadcast text have at least one text type and/or have at least one broadcast text keyword；
Alternative music is corresponding with casting one or more text types of text；
And/or alternative music is corresponding with casting one or more text keywords of text.
Specifically, corresponding text type and text keyword, a sound is arranged for each music in music libraries in advance
Happy corresponding all text types and the set of all text keywords composition can be the musical features set of the music, casting text
The set of this all text types and text keyword composition can be the casting characteristic set of the casting text, alternative music
There are intersections for the casting characteristic set of musical features set and casting text, such as: the corresponding text type of alternative music is: youngster
Virgin, positive, children's stories, corresponding keyword is: Andersen, Snow White.And broadcasting at least one in the text type of text is
The corresponding text type of alternative music, and/or, broadcasting at least one in the text keyword of text is that alternative music is corresponding
Text keyword, by be respectively set text type for casting text and music and text keyword may be implemented casting text and
The Rapid matching of alternative music.Need to obtain optimum music after obtaining alternative music from alternative music as music
Type.Preset rules for example can be weighting algorithm in the application, such as be respectively each text type and text for broadcasting text
Weight is arranged in this keyword, each alternative music is calculated according to the text type and text keyword of its corresponding casting text
Weighted value selects the highest music of weighted value as background music from alternative music.Such as: broadcast the text type of text
Are as follows: children's (weight 5), actively (weight 6) and children's stories (weight 4) broadcast the text keyword of text are as follows: Andersen
(weight 2), Snow White's (weight 3), if an alternative music is corresponding with children and Andersen, the alternative music
Weighted value be children weight plus Andersen weight be equal to 7.The weight of specific each text type and keyword
Weight, which can according to need, to be configured, and the weight of preferred text type is greater than the weight of text keyword, text keyword
Presence be in order to enable screening music it is more accurate.
It optionally, further include sound volume regulation unit 40；Background music is determined according to casting text in music acquiring unit 20
Later, before voice broadcast unit 30 plays casting text and plays background music simultaneously, sound volume regulation unit 40 is used for:
Setting plays volume value when casting text；
And/or volume value when setting broadcasting background music.
Specifically, sound volume regulation unit 40 set casting text volume value and background music volume value when, need
In conjunction with current environmental volume, i.e., current environmental volume is first obtained, the volume for playing casting text is adjusted according to environmental volume
Value and the volume value for playing background music.To prevent the improper content for causing user that can hear casting text of volume.It is preferred that
Ground, setting play the volume value of background music no more than the volume value for playing casting text at any one time.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (14)
1. a kind of voice broadcast method characterized by comprising
Determine the casting text of voice broadcast；
Background music is determined according to the casting text；
It plays the casting text and plays the background music simultaneously.
2. voice broadcast method according to claim 1, which is characterized in that determine voice broadcast text, comprising:
Obtain phonetic order and/or text instruction；
Semantic parsing is carried out to the phonetic order and/or text instruction；
Casting text is determined according to semantic parsing result.
3. voice broadcast method according to claim 2, which is characterized in that determine casting text according to semantic parsing result
This, comprising:
Determine in the phonetic order whether include inquiry instruction according to the semantic parsing result；
If so, then being inquired according to the inquiry instruction, use query result as the voice broadcast text.
4. voice broadcast method according to claim 1-3, which is characterized in that determined according to the casting text
Background music, comprising:
Obtain the text type and/or text keyword of the casting text；
Corresponding alternative music is obtained according to the text type and/or text key word；
Background music is chosen from the alternative music according to preset rules.
5. voice broadcast method according to claim 4, which is characterized in that
Any music is corresponding with text type described at least one and/or corresponding with text keyword described at least one；
It is that the casting text has a text type described at least one and/or there is at least one described casting text key
Word；
The alternative music is corresponding with casting one or more text types of text；
And/or the alternative music is corresponding with casting one or more text keywords of text.
6. according to the method for the described in any item voice broadcasts of claim 4-5, which is characterized in that the text type, comprising:
Style type, text reader and text mood.
7. the method for voice broadcast according to claim 6, which is characterized in that determining background according to the casting text
After music, before playing the casting text and playing the background music simultaneously, further includes:
Setting plays the volume value when casting text；
And/or the volume value when setting broadcasting background music.
8. a kind of sound broadcasting device characterized by comprising
Text identification unit, for determining the casting text of voice broadcast；
Music acquiring unit, for determining background music according to the casting text；
Voice broadcast unit, for playing the casting text and playing the background music simultaneously.
9. sound broadcasting device according to claim 8, which is characterized in that the text identification unit determines voice broadcast
Text, comprising:
Obtain phonetic order and/or text instruction；
Semantic parsing is carried out to the phonetic order and/or text instruction；
Casting text is determined according to semantic parsing result.
10. sound broadcasting device according to claim 9, which is characterized in that the text identification unit is solved according to semanteme
It analyses result and determines casting text, comprising:
Determine in the phonetic order whether include inquiry instruction according to the semantic parsing result；
If so, then being inquired according to the inquiry instruction, use query result as the voice broadcast text.
11. according to the described in any item sound broadcasting devices of claim 8-10, which is characterized in that the music acquiring unit root
Background music is determined according to the casting text, comprising:
Obtain the text type and/or text keyword of the casting text；
Corresponding alternative music is obtained according to the text type and/or text key word；
Background music is chosen from the alternative music according to preset rules.
12. sound broadcasting device according to claim 11, which is characterized in that
Any music is corresponding with text type described at least one and/or corresponding with text keyword described at least one；
It is that the casting text has a text type described at least one and/or there is at least one described casting text key
Word；
The alternative music is corresponding with casting one or more text types of text；
And/or the alternative music is corresponding with casting one or more text keywords of text.
13. the device of the described in any item voice broadcasts of 1-12 according to claim 1, which is characterized in that the text type, packet
It includes: style type, text reader and text mood.
14. the device of voice broadcast according to claim 13, which is characterized in that further include sound volume regulation unit；
After the music acquiring unit determines background music according to the casting text, played in the voice broadcast unit
Before the casting text simultaneously plays the background music simultaneously, the sound volume regulation unit is used for:
Setting plays the volume value when casting text；
And/or the volume value when setting broadcasting background music.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517453.6A CN109686366A (en) | 2018-12-12 | 2018-12-12 | Voice broadcast method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517453.6A CN109686366A (en) | 2018-12-12 | 2018-12-12 | Voice broadcast method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109686366A true CN109686366A (en) | 2019-04-26 |
Family
ID=66186544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811517453.6A Pending CN109686366A (en) | 2018-12-12 | 2018-12-12 | Voice broadcast method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109686366A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681640A (en) * | 2020-05-29 | 2020-09-18 | 北京百度网讯科技有限公司 | Broadcast text determination method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005189454A (en) * | 2003-12-25 | 2005-07-14 | Casio Comput Co Ltd | Text synchronous speech reproduction controller and program |
| CN102402982A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Loud reading system with selectable background sounds and realization method of system |
| CN106531149A (en) * | 2016-12-07 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| CN106874239A (en) * | 2015-12-14 | 2017-06-20 | 中兴通讯股份有限公司 | It is a kind of to show the method and device for reading text |
| CN107545029A (en) * | 2017-07-17 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Voice feedback method, equipment and the computer-readable recording medium of smart machine |
-
2018
- 2018-12-12 CN CN201811517453.6A patent/CN109686366A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005189454A (en) * | 2003-12-25 | 2005-07-14 | Casio Comput Co Ltd | Text synchronous speech reproduction controller and program |
| CN102402982A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Loud reading system with selectable background sounds and realization method of system |
| CN106874239A (en) * | 2015-12-14 | 2017-06-20 | 中兴通讯股份有限公司 | It is a kind of to show the method and device for reading text |
| CN106531149A (en) * | 2016-12-07 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| CN107545029A (en) * | 2017-07-17 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Voice feedback method, equipment and the computer-readable recording medium of smart machine |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111681640A (en) * | 2020-05-29 | 2020-09-18 | 北京百度网讯科技有限公司 | Broadcast text determination method, device, equipment and medium |
| CN111681640B (en) * | 2020-05-29 | 2023-09-15 | 阿波罗智联(北京)科技有限公司 | Method, device, equipment and medium for determining broadcast text |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108769772B (en) | Direct broadcasting room display methods, device, equipment and storage medium | |
| CN107146610B (en) | Method and device for determining user intention | |
| CN109410927B (en) | Voice recognition method, device and system combining offline command word and cloud analysis | |
| CN101075435B (en) | Intelligent chatting system and its realizing method | |
| CN108231059A (en) | Treating method and apparatus, the device for processing | |
| CN105335455A (en) | Text reading method and apparatus | |
| CN107833574A (en) | Method and apparatus for providing voice service | |
| CN105068661A (en) | Man-machine interaction method and system based on artificial intelligence | |
| CN102163198A (en) | A method and a system for providing new or popular terms | |
| CN103150356B (en) | A kind of the general demand search method and system of application | |
| CN110164415A (en) | A kind of recommended method based on speech recognition, device and medium | |
| CN109271550A (en) | A kind of music personalization classification recommended method based on deep learning | |
| CN111178081B (en) | Semantic recognition method, server, electronic device and computer storage medium | |
| Thorogood et al. | Computationally Created Soundscapes with Audio Metaphor. | |
| CN101739437A (en) | Implementation method for network sound-searching unit and specific device thereof | |
| CN111680129B (en) | Training method and system of semantic understanding system | |
| CN109325124A (en) | A kind of sensibility classification method, device, server and storage medium | |
| CN111522909A (en) | Voice interaction method and server | |
| CN104090968B (en) | The method and apparatus that a kind of intelligent information is pushed | |
| CN109237740A (en) | A kind of control method of electric appliance, device, storage medium and electric appliance | |
| CN107436871A (en) | A kind of data search method, device and electronic equipment | |
| CN109408717A (en) | A kind of content recommendation method and system | |
| CN107145509A (en) | A kind of information search method and its equipment | |
| CN109492126B (en) | Intelligent interaction method and device | |
| KR20220158644A (en) | System of making contents for learning korean 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |