CN112242139A - Voice interaction method, device, equipment and medium - Google Patents
Voice interaction method, device, equipment and medium Download PDFInfo
- Publication number
- CN112242139A CN112242139A CN201910657252.4A CN201910657252A CN112242139A CN 112242139 A CN112242139 A CN 112242139A CN 201910657252 A CN201910657252 A CN 201910657252A CN 112242139 A CN112242139 A CN 112242139A
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- pickup time
- recognition result
- matching
- 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.)
- Granted
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000002035 prolonged effect Effects 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 9
- 230000002452 interceptive effect Effects 0.000 description 18
- 238000013473 artificial intelligence Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000003287 optical effect Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 206010017577 Gait disturbance Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
- G09B19/06—Foreign languages
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
-
- 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
- G10L15/26—Speech to text systems
Abstract
The embodiment of the invention discloses a voice interaction method, a voice interaction device, voice interaction equipment and a voice interaction medium. The method comprises the following steps: if the user voice is detected within the preset time, recognizing the user voice acquired within the initial pickup time in real time; if the recognition result of the user voice acquired within the initial pickup time does not meet the matching requirement with the matching result of the preset candidate sentence, the pickup time is prolonged on the basis of the initial pickup time according to the relation between the matching result and the delay threshold; integrating the recognition result of the user voice acquired within the extended sound pickup time with the recognition result of the user voice acquired within the initial sound pickup time; and if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement, feeding back feedback information corresponding to the integrated voice recognition result to the user. The embodiment of the invention realizes that the user voice can be completely acquired in human-computer interaction even if the user voice is stumbled, thereby improving the intelligent teaching effect.
Description
Technical Field
The embodiment of the invention relates to the technical field of intelligent education, in particular to a voice interaction method, a voice interaction device, voice interaction equipment and voice interaction media.
Background
AI (Artificial Intelligence) is a branch of computer science that attempts to understand the essence of Intelligence and produces a new intelligent machine that can react in a manner similar to human Intelligence, including robotics, speech recognition, image recognition, natural language processing, and expert systems. Since birth, artificial intelligence has become more and more mature in theory and technology, and the application field is also expanding, so that the teaching of an AI interactive dialogue type between an intelligent education robot and students becomes possible, for example, children learn English through the interaction between children English teaching robots and children.
However, when a child learns a language, especially at an initial stage of learning a non-native language, a phenomenon that a speaker is stumbled may always occur, and if human-computer interaction is performed based on a child Voice acquired within a set Voice pickup time according to the prior art, a Detection technique based on Voice Activity Detection (VAD) may misjudge an end point of the child Voice, which may easily cause that the child Voice cannot be completely acquired during human-computer interaction, resulting in a poor intelligent teaching effect.
Disclosure of Invention
The embodiment of the invention provides a voice interaction method, a voice interaction device, voice interaction equipment and a voice interaction medium, and aims to solve the problem that in the prior art, the voice of a child cannot be completely acquired in a man-machine interaction process and the intelligent teaching effect is poor due to the fact that man-machine interaction is carried out based on the voice of the child acquired within set pickup time.
In a first aspect, an embodiment of the present invention provides a voice interaction method, where the method includes:
if the voice of the user is detected within the preset time, triggering the operation of recognizing the voice of the user within the initial pickup time;
recognizing user voice acquired within the initial pickup time in real time;
if the recognition result of the user voice acquired within the initial pickup time and the matching result of the preset candidate sentence do not meet the matching requirement, carrying out pickup time extension on the basis of the initial pickup time according to the relation between the matching result and a delay threshold value;
integrating the recognition result of the user voice acquired within the prolonged sound pickup time with the recognition result of the user voice acquired within the initial sound pickup time, and matching the integrated voice recognition result with the preset candidate sentence;
and if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement, feeding back feedback information corresponding to the integrated voice recognition result to the user.
In a second aspect, an embodiment of the present invention provides a voice interaction apparatus, where the apparatus includes:
the user voice recognition triggering module is used for triggering the operation of recognizing the user voice in the initial pickup time if the user voice is detected in the preset time;
the user voice recognition module is used for recognizing the user voice acquired in the initial pickup time in real time;
a pickup time extension module, configured to, if a matching result of a recognition result of the user speech obtained within the initial pickup time and a preset candidate sentence does not meet a matching requirement, extend a pickup time based on the initial pickup time according to a relationship between the matching result and a delay threshold;
the sentence matching module is used for integrating the recognition result of the user voice acquired within the prolonged sound pickup time with the recognition result of the user voice acquired within the initial sound pickup time and matching the integrated voice recognition result with the preset candidate sentences;
and the first information feedback module is used for feeding back feedback information corresponding to the integrated voice recognition result to a user if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement.
In a third aspect, an embodiment of the present invention provides an apparatus, where the apparatus further includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a voice interaction method as in any of the embodiments of the invention.
In a fourth aspect, the present invention provides a computer-readable medium, on which a computer program is stored, where the computer program is executed by a processor to implement the voice interaction method according to any one of the embodiments of the present invention.
According to the embodiment of the invention, the recognition result of the user voice acquired in the initial pickup time is matched with the preset candidate sentence, and if the matching requirement is not met, the pickup time is prolonged on the basis of the initial pickup time, so that even if the user voice is stumbled, the user voice can be acquired completely in the human-computer interaction process, and the intelligent teaching effect is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of a voice interaction method according to an embodiment of the present invention;
fig. 2 is a flowchart of a voice interaction method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a voice interaction apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the embodiments of the invention and that no limitation of the invention is intended. It should be further noted that, for convenience of description, only some structures, not all structures, relating to the embodiments of the present invention are shown in the drawings.
Example one
Fig. 1 is a flowchart of a voice interaction method according to an embodiment of the present invention. The embodiment is suitable for the condition that the children communicate with the intelligent equipment for learning in a voice interaction mode, the method can be executed by the voice interaction device provided by the embodiment of the invention, the device can be realized in a software and/or hardware mode, and the device can be integrated on any intelligent equipment, such as an intelligent teaching robot, a smart phone, a smart sound box and the like. As shown in fig. 1, the method may include:
step 101, if the voice of the user is detected within the preset time, triggering the operation of recognizing the voice of the user within the initial pickup time.
The device interacting with the user may include an intelligent teaching robot, a smart phone, a smart speaker, and the like, which are hereinafter collectively referred to as an interactive device. The preset time refers to a sound pickup preparation time before the interactive apparatus enters a voice interaction state with the user. The interactive device can start the voice detection function after being started, and can detect the voice of the user within a preset time. If the interactive equipment detects the voice of the user within the preset time, the user is considered to have the voice interaction requirement; and if the voice of the user is not detected after the preset time, the user is considered to have no voice interaction requirement, and the voice detection function is closed. The detection of the user's speech can be achieved in any way available in the art, such as VAD techniques. After the interactive device enters a voice interaction state with the user, the time lasting from the first time when the user starts speaking to the end of speaking is detected, which is called initial pickup time, the initial pickup time is not a fixed time length, which is determined by the voice duration of the user and is related to the speed of the user, for example, if the speed of the user is fast, the initial pickup time can be set to be a shorter time length, and if the speed of the user is slow, the initial pickup time can be set to be a longer time length.
Specifically, the interaction device is provided with a pickup device comprising a microphone, so that the voice of the user can be detected and acquired in real time, and when the user starts to make a sound, the operation of recognizing the voice of the user is triggered immediately. The voice operation of the user is triggered and recognized by detecting the voice of the user, so that the efficiency of man-machine interaction is improved, and the induction time is shortened.
And step 102, identifying the voice of the user acquired in the initial pickup time in real time.
Specifically, after detecting the utterance of the user, the voice of the user is continuously input into a voice recognition engine built in the interactive device, and the obtained voice of the user is recognized through the voice recognition engine.
And 103, if the recognition result of the user voice acquired in the initial sound pickup time and the matching result of the preset candidate sentence do not meet the matching requirement, prolonging the sound pickup time on the basis of the initial sound pickup time according to the relation between the matching result and a delay threshold value.
The preset candidate sentences comprise question sentences of the user in the human-computer interaction process predicted by the interaction equipment or standard reply sentences in the human-computer interaction process. Illustratively, research and development personnel can establish a prediction sentence library in advance according to different operation links of the interaction equipment, when the current operation link of the interaction equipment asks a question to the interaction equipment for a user, the interaction equipment can search and match in the prediction sentence library according to the recognized voice of the user, and predicts a sentence to be asked by the user as a current preset candidate sentence; and when the current operation link of the interactive equipment is that the interactive equipment asks a question to a user, presetting the candidate sentence as a pre-stored standard reply sentence.
The matching of the recognition result of the user voice and the preset candidate sentence is a sentence similarity calculation process, and the matching result is a sentence similarity calculation value. And if the matching result of the recognition result of the user voice and the preset candidate sentence is smaller than the similarity threshold value, the matching result of the recognition result of the user voice and the preset candidate sentence does not meet the matching requirement. Illustratively, the preset similarity threshold is 80%, if the recognition result of the user speech and the matching result of the preset candidate sentence are 75%, and if 75% < 80%, the recognition result of the user speech and the matching result of the preset candidate sentence do not meet the matching requirement.
And when the matching result does not meet the matching requirement, prolonging the sound pickup time, wherein the higher the matching result is, the user is about to express the voice to be expressed, and the lower the matching result is, the user is not required to express the voice to be expressed. Optionally, based on the relationship between the matching result and the different delay thresholds and the corresponding relationship between the different delay thresholds and the target extension time, the pickup time is extended based on the initial pickup time, wherein the larger the delay threshold is, the shorter the corresponding target extension time is.
Optionally, this embodiment further provides a specific implementation scenario of "step 103": the cloud server stores a large number of preset candidate sentences, the interaction equipment communicates with the cloud server, the interaction equipment matches the recognition result of the user voice obtained locally with the preset candidate sentences stored in the cloud server, and when the matching requirement is not met, pickup is continued after the user stops speaking.
When the matching result of the recognition result of the user voice and the preset candidate sentence does not meet the matching requirement, the pickup time is prolonged, and the user voice can be completely acquired under the condition that the user voice is stumbled; according to the relation between the matching result and the delay threshold value, the pickup time is prolonged, and the length of the pickup prolonging time can be flexibly adjusted according to different voice expression conditions of a user.
And step 104, integrating the recognition result of the user voice acquired in the prolonged sound pickup time with the recognition result of the user voice acquired in the initial sound pickup time, and matching the integrated voice recognition result with the preset candidate sentence.
For example, the recognition result of the user voice obtained during the initial sound pickup time is "My name is", the recognition result of the user voice obtained during the extended sound pickup time is "Smith", and the integrated voice recognition result is "My name is Smith".
And 105, if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement, feeding back feedback information corresponding to the integrated voice recognition result to the user.
Wherein, according to the interactive link of difference, feedback information can carry out nimble setting to increase interactive teaching's interest, improve the teaching effect. Specifically, the feedback information may be obtained according to a preset candidate sentence matched with the voice recognition result and an AI interaction policy.
For example, if the current link is that the user asks a question to the interactive device, the integrated speech recognition result is "how do the apple say in english? "which satisfies the matching requirement, and the matched preset candidate sentence is" how should an apple read in english? ", the feedback information includes" applet "in text display or voice form, according to the AI interaction strategy.
Illustratively, if the current link is that the interactive device asks the user a question, "today is the day of the week? If the preset candidate sentence is "Monday" and the integrated speech recognition result is "Monday", which satisfies the matching requirement, the feedback information includes an encouraging sentence in a text display form or a speech form, such as "true bar, answer correct" or "correct, answer then answer again" and the like, according to the AI interaction policy.
Optionally, if the matching result of the integrated voice recognition result and the preset candidate sentence does not meet the matching requirement, generating voice interaction abnormal prompt information.
Illustratively, if the current link is that the user asks a question to the interactive device and the integrated voice recognition result does not meet the matching requirement, the voice interaction abnormal prompt information includes: "i do not know what you are saying, change a question bar" or "i need to add extra learning and answer you after i learn, etc.
Illustratively, if the current link is that the interactive device asks the user a question, "today is the day of the week? If the preset candidate sentence is assumed to be "Monday", the integrated voice recognition result is "Friday", and the matching requirement is not satisfied, the voice interaction abnormal prompt information includes: "answer wrong, think of what you want the bar" or broadcast the wrong warning tone directly, etc..
If the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement, feedback information corresponding to the integrated voice recognition result is fed back to the user, the AI interactive process is completed according to the voice of the user, and the use experience of the user is improved.
According to the embodiment of the invention, the recognition result of the user voice acquired in the initial pickup time is matched with the preset candidate sentence, and if the matching requirement is not met, the pickup time is prolonged on the basis of the initial pickup time, so that even if the user voice is stumbled, the user voice can be acquired completely in the human-computer interaction process, and the intelligent teaching effect is improved.
Example two
Fig. 2 is a flowchart of a voice interaction method according to a second embodiment of the present invention. The embodiment provides a specific implementation manner for the above embodiment, and as shown in fig. 2, the method may include:
step 201, if the voice of the user is detected within the preset time, triggering the operation of recognizing the voice of the user within the initial pickup time.
And 202, identifying the voice of the user acquired in the initial pickup time in real time.
If yes, go to step 204; if not, go to step 205.
And step 204, feeding back feedback information corresponding to the recognition result of the user voice acquired in the initial pickup time to the user.
For example, if the current link is that the user asks questions of the interactive device, the speech recognition result in the initial pickup time is "how do apple say in english? "which satisfies the matching requirement, and the matched preset candidate sentence is" how should an apple read in english? ", the feedback information includes" applet "in text display or voice form, according to the AI interaction strategy.
Illustratively, if the current link is that the interactive device asks the user a question, "today is the day of the week? If the preset candidate sentence is "Monday", the voice recognition result in the initial pickup time is "Monday", which satisfies the matching requirement, the feedback information includes an encouraging sentence in a text display form or a voice form, such as "true stick, answer correct" or "correct, answer again" and the like, according to the AI interaction policy.
And step 205, according to the relationship between the matching result and different delay thresholds and the corresponding relationship between different delay thresholds and target extension time, on the basis of the initial pickup time, extending the pickup time, wherein the larger the delay threshold is, the shorter the corresponding target extension time is.
The higher the matching result is, the more the user is about to express the desired voice, so the longer the time is required.
For example, the delay thresholds may be set to be two, which are a first delay threshold "60%" and a second delay threshold "40%", respectively, the target extension time corresponding to the first delay threshold may be optionally 3 seconds, the target extension time corresponding to the second delay threshold may be optionally 5 seconds, the target extension time corresponding to the first delay threshold and the second delay threshold may be optionally 4 seconds, and the matching requirement may be optionally "70%".
If the matching result between the recognition result of the user's voice acquired within the initial sound collection time and the preset candidate sentence is 65% and 60% < 65% < 70%, the sound collection time is extended to 3 seconds as the target extension time on the basis of the initial sound collection time.
If the matching result between the recognition result of the user's voice acquired within the initial sound collection time and the preset candidate sentence is 55% and 40% < 55% < 60%, the sound collection time is extended by 4 seconds as the target extension time on the basis of the initial sound collection time.
If the matching result of the recognition result of the user's voice acquired within the initial sound collection time with the preset candidate sentence is 35% and 35% < 40%, the sound collection time is extended by 5 seconds as the target extension time on the basis of the initial sound collection time.
And step 206, integrating the recognition result of the user voice acquired in the prolonged sound pickup time with the recognition result of the user voice acquired in the initial sound pickup time, and matching the integrated voice recognition result with the preset candidate sentence.
And step 208, feeding back feedback information corresponding to the integrated voice recognition result to the user.
In the embodiment of the invention, if the recognition result of the user voice acquired in the initial pickup time and the matching result of the preset candidate sentence meet the matching requirement, feedback information corresponding to the recognition result of the user voice acquired in the initial pickup time is fed back to the user, so that the effect of immediately returning the feedback information is realized, and the waiting time of the user is reduced; if the recognition result of the user voice acquired within the initial pickup time and the matching result of the preset candidate sentence do not meet the matching requirement, determining corresponding target extension time according to the matching result, and prolonging the pickup time, so that the user voice can be acquired completely in the human-computer interaction process even if the user voice has the problem of 'stumbling after knocking over', and the intelligent teaching effect is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a voice interaction apparatus according to a third embodiment of the present invention, which is suitable for a situation where a child exchanges and learns with an intelligent device in a voice interaction manner. The device can be realized in a software and/or hardware mode, and can be integrated on any intelligent equipment, such as an intelligent teaching robot, a smart phone and a smart sound box. As shown in fig. 3, the apparatus may include:
a user voice recognition triggering module 31, configured to trigger an operation of recognizing a user voice within an initial pickup time if the user voice is detected within a preset time;
a user voice recognition module 32, configured to recognize, in real time, a user voice acquired within the initial pickup time;
a sound pickup time extension module 33, configured to, if a matching result between a recognition result of the user speech obtained within the initial sound pickup time and a preset candidate sentence does not meet a matching requirement, extend a sound pickup time based on the initial sound pickup time according to a relationship between the matching result and a delay threshold;
a sentence matching module 34, configured to integrate a recognition result of the user speech obtained in the extended sound pickup time with a recognition result of the user speech obtained in the initial sound pickup time, and match the integrated speech recognition result with the preset candidate sentence;
a first information feedback module 35, configured to feed back feedback information corresponding to the integrated speech recognition result to the user if the matching result of the integrated speech recognition result and the preset candidate sentence meets the matching requirement.
On the basis of the above embodiment, the sound pickup time extension module 33 is specifically configured to:
and according to the relationship between the matching result and different delay thresholds and the corresponding relationship between different delay thresholds and target extension time, on the basis of the initial pickup time, the pickup time is extended, wherein the larger the delay threshold is, the shorter the corresponding target extension time is.
On the basis of the above embodiment, the preset candidate sentences include predicted question sentences of the user in the human-computer interaction process, or standard reply sentences in the human-computer interaction process.
On the basis of the above embodiment, the apparatus further includes a second information feedback module, specifically configured to:
and if the recognition result of the user voice acquired in the initial pickup time meets the matching requirement with the matching result of the preset candidate sentence, feeding back feedback information corresponding to the recognition result of the user voice acquired in the initial pickup time to the user.
On the basis of the above embodiment, the apparatus further includes an exception prompt information generating module, specifically configured to:
and if the matching result of the integrated voice recognition result and the preset candidate sentence does not meet the matching requirement, generating voice interaction abnormal prompt information.
The voice interaction generating device provided by the embodiment of the invention can execute the voice interaction method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details which are not described in detail in this example, reference is made to the description in any method example of the invention.
Example four
Fig. 4 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention. Fig. 4 illustrates a block diagram of an exemplary device 400 suitable for use in implementing embodiments of the present invention. The apparatus 400 shown in fig. 4 is only an example and should not bring any limitations to the functionality or scope of use of the embodiments of the present invention.
As shown in FIG. 4, device 400 is in the form of a general purpose computing device. The components of device 400 may include, but are not limited to: one or more processors or processing units 401, a memory device 402, and a bus 403 that couples the various system components including the memory device 402 and the processing unit 401.
A program/utility 408 having a set (at least one) of program modules 407 may be stored, for example, in storage 402, such program modules 407 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 407 generally perform the functions and/or methods of the described embodiments of the invention.
The processing unit 401 executes various functional applications and data processing by running programs stored in the system storage device 402, for example, implementing a voice interaction method provided by the embodiment of the present invention, including:
if the voice of the user is detected within the preset time, triggering the operation of recognizing the voice of the user within the initial pickup time;
recognizing user voice acquired within the initial pickup time in real time;
if the recognition result of the user voice acquired within the initial pickup time and the matching result of the preset candidate sentence do not meet the matching requirement, carrying out pickup time extension on the basis of the initial pickup time according to the relation between the matching result and a delay threshold value;
integrating the recognition result of the user voice acquired within the prolonged sound pickup time with the recognition result of the user voice acquired within the initial sound pickup time, and matching the integrated voice recognition result with the preset candidate sentence;
and if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement, feeding back feedback information corresponding to the integrated voice recognition result to the user.
EXAMPLE five
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-executable instructions, when executed by a computer processor, are configured to perform a method for voice interaction, where the method includes:
if the voice of the user is detected within the preset time, triggering the operation of recognizing the voice of the user within the initial pickup time;
recognizing user voice acquired within the initial pickup time in real time;
if the recognition result of the user voice acquired within the initial pickup time and the matching result of the preset candidate sentence do not meet the matching requirement, carrying out pickup time extension on the basis of the initial pickup time according to the relation between the matching result and a delay threshold value;
integrating the recognition result of the user voice acquired within the prolonged sound pickup time with the recognition result of the user voice acquired within the initial sound pickup time, and matching the integrated voice recognition result with the preset candidate sentence;
and if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement, feeding back feedback information corresponding to the integrated voice recognition result to the user.
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in a voice interaction method provided by any embodiments of the present invention. The computer-readable storage media of embodiments of the invention may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method of voice interaction, the method comprising:
if the voice of the user is detected within the preset time, triggering the operation of recognizing the voice of the user within the initial pickup time;
recognizing user voice acquired within the initial pickup time in real time;
if the recognition result of the user voice acquired within the initial pickup time and the matching result of the preset candidate sentence do not meet the matching requirement, carrying out pickup time extension on the basis of the initial pickup time according to the relation between the matching result and a delay threshold value;
integrating the recognition result of the user voice acquired within the prolonged sound pickup time with the recognition result of the user voice acquired within the initial sound pickup time, and matching the integrated voice recognition result with the preset candidate sentence;
and if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement, feeding back feedback information corresponding to the integrated voice recognition result to the user.
2. The method of claim 1, wherein extending the sound pickup time based on the initial sound pickup time according to a relationship between the matching result and a delay threshold comprises:
and according to the relationship between the matching result and different delay thresholds and the corresponding relationship between different delay thresholds and target extension time, on the basis of the initial pickup time, the pickup time is extended, wherein the larger the delay threshold is, the shorter the corresponding target extension time is.
3. The method of claim 1, wherein the preset candidate sentences include predicted question sentences of the user during the human-computer interaction or standard answer sentences during the human-computer interaction.
4. The method of claim 1, further comprising:
and if the recognition result of the user voice acquired in the initial pickup time meets the matching requirement with the matching result of the preset candidate sentence, feeding back feedback information corresponding to the recognition result of the user voice acquired in the initial pickup time to the user.
5. The method of claim 1, further comprising:
and if the matching result of the integrated voice recognition result and the preset candidate sentence does not meet the matching requirement, generating voice interaction abnormal prompt information.
6. A voice interaction apparatus, comprising:
the user voice recognition triggering module is used for triggering the operation of recognizing the user voice in the initial pickup time if the user voice is detected in the preset time;
the user voice recognition module is used for recognizing the user voice acquired in the initial pickup time in real time;
a pickup time extension module, configured to, if a matching result of a recognition result of the user speech obtained within the initial pickup time and a preset candidate sentence does not meet a matching requirement, extend a pickup time based on the initial pickup time according to a relationship between the matching result and a delay threshold;
the sentence matching module is used for integrating the recognition result of the user voice acquired within the prolonged sound pickup time with the recognition result of the user voice acquired within the initial sound pickup time and matching the integrated voice recognition result with the preset candidate sentences;
and the first information feedback module is used for feeding back feedback information corresponding to the integrated voice recognition result to a user if the matching result of the integrated voice recognition result and the preset candidate sentence meets the matching requirement.
7. The apparatus of claim 6, wherein the pickup time extension module is specifically configured to:
and according to the relationship between the matching result and different delay thresholds and the corresponding relationship between different delay thresholds and target extension time, on the basis of the initial pickup time, the pickup time is extended, wherein the larger the delay threshold is, the shorter the corresponding target extension time is.
8. The apparatus according to claim 6, wherein the apparatus further comprises a second information feedback module, specifically configured to:
and if the recognition result of the user voice acquired in the initial pickup time meets the matching requirement with the matching result of the preset candidate sentence, feeding back feedback information corresponding to the recognition result of the user voice acquired in the initial pickup time to the user.
9. An apparatus, characterized in that the apparatus further comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the voice interaction method of any of claims 1-5.
10. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method for voice interaction according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910657252.4A CN112242139B (en) | 2019-07-19 | 2019-07-19 | Voice interaction method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910657252.4A CN112242139B (en) | 2019-07-19 | 2019-07-19 | Voice interaction method, device, equipment and medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112242139A true CN112242139A (en) | 2021-01-19 |
CN112242139B CN112242139B (en) | 2024-01-23 |
Family
ID=74167980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910657252.4A Active CN112242139B (en) | 2019-07-19 | 2019-07-19 | Voice interaction method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112242139B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107146618A (en) * | 2017-06-16 | 2017-09-08 | 北京云知声信息技术有限公司 | Method of speech processing and device |
CN107146602A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | A kind of audio recognition method, device and electronic equipment |
CN107195303A (en) * | 2017-06-16 | 2017-09-22 | 北京云知声信息技术有限公司 | Method of speech processing and device |
CN108257616A (en) * | 2017-12-05 | 2018-07-06 | 苏州车萝卜汽车电子科技有限公司 | Interactive detection method and device |
CN108847236A (en) * | 2018-07-26 | 2018-11-20 | 珠海格力电器股份有限公司 | The analysis method and device of the method for reseptance and device of voice messaging, voice messaging |
CN109712610A (en) * | 2019-03-12 | 2019-05-03 | 百度在线网络技术(北京)有限公司 | The method and apparatus of voice for identification |
CN109961787A (en) * | 2019-02-20 | 2019-07-02 | 北京小米移动软件有限公司 | Determine the method and device of acquisition end time |
-
2019
- 2019-07-19 CN CN201910657252.4A patent/CN112242139B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107146602A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | A kind of audio recognition method, device and electronic equipment |
CN107146618A (en) * | 2017-06-16 | 2017-09-08 | 北京云知声信息技术有限公司 | Method of speech processing and device |
CN107195303A (en) * | 2017-06-16 | 2017-09-22 | 北京云知声信息技术有限公司 | Method of speech processing and device |
CN108257616A (en) * | 2017-12-05 | 2018-07-06 | 苏州车萝卜汽车电子科技有限公司 | Interactive detection method and device |
CN108847236A (en) * | 2018-07-26 | 2018-11-20 | 珠海格力电器股份有限公司 | The analysis method and device of the method for reseptance and device of voice messaging, voice messaging |
CN109961787A (en) * | 2019-02-20 | 2019-07-02 | 北京小米移动软件有限公司 | Determine the method and device of acquisition end time |
CN109712610A (en) * | 2019-03-12 | 2019-05-03 | 百度在线网络技术(北京)有限公司 | The method and apparatus of voice for identification |
Also Published As
Publication number | Publication date |
---|---|
CN112242139B (en) | 2024-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110718223B (en) | Method, apparatus, device and medium for voice interaction control | |
US9805718B2 (en) | Clarifying natural language input using targeted questions | |
CN108922564B (en) | Emotion recognition method and device, computer equipment and storage medium | |
CN108985358B (en) | Emotion recognition method, device, equipment and storage medium | |
KR20200108775A (en) | Training corpus generating method, apparatus, device and storage medium | |
CN109686383B (en) | Voice analysis method, device and storage medium | |
CN110047481B (en) | Method and apparatus for speech recognition | |
WO2018045646A1 (en) | Artificial intelligence-based method and device for human-machine interaction | |
JP7063937B2 (en) | Methods, devices, electronic devices, computer-readable storage media, and computer programs for voice interaction. | |
CN111402861A (en) | Voice recognition method, device, equipment and storage medium | |
JP7178394B2 (en) | Methods, apparatus, apparatus, and media for processing audio signals | |
CN109712610A (en) | The method and apparatus of voice for identification | |
CN111916088B (en) | Voice corpus generation method and device and computer readable storage medium | |
CN112069206B (en) | Data query method, device, medium and computing device based on RPA and AI | |
CN114330371A (en) | Session intention identification method and device based on prompt learning and electronic equipment | |
CN110647613A (en) | Courseware construction method, courseware construction device, courseware construction server and storage medium | |
CN113782030B (en) | Error correction method based on multi-mode voice recognition result and related equipment | |
CN113051895A (en) | Method, apparatus, electronic device, medium, and program product for speech recognition | |
Lison et al. | Salience-driven contextual priming of speech recognition for human-robot interaction | |
KR20190074508A (en) | Method for crowdsourcing data of chat model for chatbot | |
CN111400463B (en) | Dialogue response method, device, equipment and medium | |
CN114067790A (en) | Voice information processing method, device, equipment and storage medium | |
CN112242139B (en) | Voice interaction method, device, equipment and medium | |
CN112002325B (en) | Multi-language voice interaction method and device | |
US20220164200A1 (en) | Unstructured extensions to rpa |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210817 Address after: Room 301-112, floor 3, building 2, No. 18, YANGFANGDIAN Road, Haidian District, Beijing 100089 Applicant after: Beijing Rubu Technology Co.,Ltd. Address before: Room 508-598, Xitian Gezhuang Town Government Office Building, No. 8 Xitong Road, Miyun District Economic Development Zone, Beijing 101500 Applicant before: BEIJING ROOBO TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |