CN112016275A - Intelligent error correction method and system for voice recognition text and electronic equipment - Google Patents
Intelligent error correction method and system for voice recognition text and electronic equipment Download PDFInfo
- Publication number
- CN112016275A CN112016275A CN202011191600.2A CN202011191600A CN112016275A CN 112016275 A CN112016275 A CN 112016275A CN 202011191600 A CN202011191600 A CN 202011191600A CN 112016275 A CN112016275 A CN 112016275A
- Authority
- CN
- China
- Prior art keywords
- word
- error correction
- text
- corrected
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/226—Validation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
-
- 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 invention provides an intelligent error correction method and system for a voice recognition text and electronic equipment. The method comprises the following steps: constructing an error correction word bank by using the historical error-free text of the topic type dialog; receiving user voice input, and converting the user voice input into user text input; inputting the converted user text, and performing word segmentation processing; using the error correction word bank to perform error correction judgment on each word after word segmentation processing, and determining words to be corrected; performing similarity matching with word vectors in the error correction word bank based on the vector similarity; and correcting the word to be corrected according to the similarity matching result. The method of the invention optimizes the error correction method, improves the accuracy and effectively avoids the problem that the voice text to be corrected is not corrected.
Description
Technical Field
The invention relates to the field of computer information processing, in particular to an intelligent error correction method, system and electronic equipment for a voice recognition text.
Background
With the development of speech recognition technology, the application field of speech recognition technology is wider and wider, and more users use speech for interaction. Therefore, there is also an increasing research on speech recognition text correction.
In the related art, a method for error detection and correction of a text after voice recognition is disclosed, that is, a semantic analysis is performed on the voice text to be recognized, so as to locate anchor words in the voice text to be recognized, then, an instance (for example, an instance formed by a text office containing the anchor words) corresponding to each anchor word is extracted from a pre-configured context knowledge base in which a large number of instances (for example, sentences under various contexts) are stored, then, word correlation between the instance corresponding to each anchor word and the voice text to be recognized is respectively calculated, and a word is selected from the instances corresponding to each anchor word, so as to determine words to be corrected, and the words to be corrected are corrected. Because the examples of the same word formed under different scenes are different, the existing context knowledge base cannot cover the examples under all the contexts of each word, so that the problem that the speech text to be corrected is not corrected exists, and the accuracy is not high.
However, due to various external environmental factors, the scene difference is large, and it is difficult to avoid a speech recognition error occurring in the speech recognition process, and the speech recognition error affects subsequent semantic understanding models and dialogue logic processing, thereby greatly affecting the effect and experience of the whole speech dialogue system. Therefore, it is urgently required to locate and correct a speech recognition error in a speech recognition result. However, the update cycle of the existing voice recognition model is often long, and the problems of difficulty and rapidness in solving the voice recognition error, low accuracy and the like exist.
Therefore, it is necessary to provide an intelligent error correction method with higher accuracy.
Disclosure of Invention
In order to further optimize the error correction method, the invention provides an intelligent error correction method for a voice recognition text, which is used for a voice conversation robot of a topic type conversation and comprises the following steps: constructing an error correction word bank by using the historical error-free text of the topic type dialog; receiving user voice input, and converting the user voice input into user text input; inputting the converted user text, and performing word segmentation processing; using the error correction word bank to perform error correction judgment on each word after word segmentation processing, and determining words to be corrected; performing similarity matching with word vectors in the error correction word bank based on the vector similarity; and correcting the word to be corrected according to the similarity matching result.
Preferably, the thesaurus for correcting errors includes an example sentence, a first order dictionary and a second order dictionary.
Preferably, the using the word bank for error correction to determine words to be corrected further includes: performing frequency statistical calculation on the single word after the word segmentation processing based on the error correction word bank; and using a first-order dictionary and determining the word to be corrected according to a first judgment rule.
Preferably, the method further comprises the following steps: based on the error correction word bank, further performing frequency statistical calculation on the two continuous words after the word segmentation processing; and using a second-order dictionary and determining the word to be corrected according to a second judgment rule.
Preferably, the method further comprises the following steps: setting a first judgment rule and a second judgment rule corresponding to the first order dictionary and the second order dictionary; the first judgment rule includes configuring a frequency threshold corresponding to a single word in the first order dictionary, and the second judgment rule includes configuring a frequency threshold corresponding to two words in the second order dictionary.
Preferably, the method further comprises the following steps: and when the frequency calculation value of each word input by the user text is smaller than the frequency threshold value of the corresponding word in the first-order dictionary, determining the word as a word to be corrected.
Preferably, the method further comprises the following steps: and when the frequency calculation value of the two continuous words input by the user text is smaller than the frequency threshold value of the two corresponding words in the second-order dictionary, determining the two continuous words as the words to be corrected.
Preferably, the similarity matching with the word vectors in the error correction word bank based on the vector similarity includes: performing word vector conversion on the user text input, and performing similarity calculation on the user text input and example sentences in the error correction word stock; and when the calculated text similarity is greater than a set threshold value, performing word-by-word matching on each word in the screened example sentence and each word input by the user text to determine a correct word corresponding to the word to be corrected.
Preferably, the word-by-word matching includes searching similar words with the same pinyin from the error correction word bank to correct the word to be corrected.
In addition, the invention also provides an intelligent error correction system for the voice recognition text, which is used for a voice conversation robot of the topic conversation and comprises the following components: the building module is used for building an error correction word bank by utilizing the historical error-free text of the topic type conversation; the receiving module is used for receiving the voice input of a user and converting the text input of the user to the voice input of the user; the processing module is used for inputting the converted user text and performing word segmentation processing; the judging module is used for carrying out error correction judgment on each word after the word is processed by using the error correction word bank and determining a word to be corrected; the matching module is used for performing similarity matching with word vectors in the error correction word bank based on vector similarity; and the error correction module is used for correcting the words to be corrected according to the similarity matching result.
Preferably, the thesaurus for correcting errors includes an example sentence, a first order dictionary and a second order dictionary.
Preferably, the system further comprises a first calculation module, wherein the first calculation module performs frequency statistical calculation on the single word after the word segmentation processing based on the error correction word bank; and using a first-order dictionary and determining the word to be corrected according to a first judgment rule.
Preferably, the word processing device further comprises a second calculation module, wherein the second calculation module further performs frequency statistical calculation on two continuous words after the word processing based on the error correction word bank; and using a second-order dictionary and determining the word to be corrected according to a second judgment rule.
Preferably, the device further comprises a setting module, wherein the setting module is used for setting a first judgment rule and a second judgment rule corresponding to the first-order dictionary and the second-order dictionary; the first judgment rule includes configuring a frequency threshold corresponding to a single word in the first order dictionary, and the second judgment rule includes configuring a frequency threshold corresponding to two words in the second order dictionary.
Preferably, the method further comprises the following steps: and when the frequency calculation value of each word input by the user text is smaller than the frequency threshold value of the corresponding word in the first-order dictionary, determining the word as a word to be corrected.
Preferably, the method further comprises the following steps: and when the frequency calculation value of the two continuous words input by the user text is smaller than the frequency threshold value of the two corresponding words in the second-order dictionary, determining the two continuous words as the words to be corrected.
Preferably, the method further comprises the following steps: performing word vector conversion on the user text input, and performing similarity calculation on the user text input and example sentences in the error correction word stock; and when the calculated text similarity is greater than a set threshold value, performing word-by-word matching on each word in the screened example sentence and each word input by the user text to determine a correct word corresponding to the word to be corrected.
Preferably, the word-by-word matching includes searching similar words with the same pinyin from the error correction word bank to correct the word to be corrected.
In addition, the present invention also provides an electronic device, wherein the electronic device includes: a processor; and a memory storing computer executable instructions that, when executed, cause the processor to perform the intelligent method of speech recognition text correction of the present invention.
Further, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs which, when executed by a processor, implement the intelligent error correction method for speech recognition text according to the present invention.
Advantageous effects
Compared with the prior art, the intelligent error correction method provided by the invention has the advantages that the error correction word bank is built, the first-order dictionary and the second-order dictionary of the error correction word bank are used for respectively carrying out error correction judgment on each word and two continuous words input by the user text, the correct word is determined through similarity matching, and finally the word to be corrected is corrected, so that the error correction method is optimized, the accuracy is improved, and the problem that the voice text to be corrected is not corrected is effectively avoided. In addition, the method has wider application scene range.
Drawings
In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects obtained more clear, the following will describe in detail the embodiments of the present invention with reference to the accompanying drawings. It should be noted, however, that the drawings described below are only illustrations of exemplary embodiments of the invention, from which other embodiments can be derived by those skilled in the art without inventive faculty.
Fig. 1 is a flowchart of an example of a method of intelligent error correction of speech recognition text of the present invention.
Fig. 2 is a flowchart of another example of the intelligent error correction method of speech recognition text of the present invention.
Fig. 3 is a flowchart of still another example of the intelligent error correction method of speech recognition text of the present invention.
FIG. 4 is a block diagram of a schematic structure of an example of the intelligent error correction system for speech recognition text of the present invention.
Fig. 5 is a schematic block diagram of another example of the intelligent correction system for speech recognition text of the present invention.
Fig. 6 is a schematic structural block diagram of still another example of the intelligent correction system for speech recognition text of the present invention.
Fig. 7 is a block diagram of an exemplary embodiment of an electronic device according to the present invention.
Fig. 8 is a block diagram of an exemplary embodiment of a computer-readable medium according to the present invention.
Detailed Description
Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. The same reference numerals denote the same or similar elements, components, or parts in the drawings, and thus their repetitive description will be omitted.
Features, structures, characteristics or other details described in a particular embodiment do not preclude the fact that the features, structures, characteristics or other details may be combined in a suitable manner in one or more other embodiments in accordance with the technical idea of the invention.
In describing particular embodiments, the present invention has been described with reference to features, structures, characteristics or other details that are within the purview of one skilled in the art to provide a thorough understanding of the embodiments. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific features, structures, characteristics, or other details.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, or sections, these terms should not be construed as limiting. These phrases are used to distinguish one from another. For example, a first device may also be referred to as a second device without departing from the spirit of the present invention.
The term "and/or" and/or "includes any and all combinations of one or more of the associated listed items.
In view of the above problems, the invention provides an intelligent error correction method for a speech recognition text, which comprises the steps of constructing an error correction word bank, using a first-order dictionary and a second-order dictionary of the error correction word bank to respectively perform error correction judgment on each word and two continuous words input by a user text, determining a correct word through similarity matching, and finally correcting a word to be corrected, so that the error correction method is optimized, the accuracy is improved, and the problem that the speech text to be corrected is not corrected is effectively avoided.
In order that the objects, technical solutions and advantages of the present invention will become more apparent, the present invention will be further described in detail with reference to the accompanying drawings in conjunction with the following specific embodiments.
Example 1
Hereinafter, an embodiment of the intelligent error correction method of speech recognition text of the present invention will be described with reference to fig. 1 to 3.
Fig. 1 is a flowchart of an example of a method of intelligent error correction of speech recognition text of the present invention.
As shown in fig. 1, an intelligent error correction method for speech recognition text includes the following steps.
And step S101, constructing an error correction word bank by using the historical error-free text of the topic type dialog.
Step S102, receiving user voice input, and converting the user voice input into user text input.
And step S103, inputting the converted user text and performing word segmentation processing.
And step S104, using the error correction word bank to perform error correction judgment on each word after word processing and determine the word to be corrected.
And step S105, performing similarity matching with word vectors in the error correction word bank based on the vector similarity.
And S106, correcting the word to be corrected according to the similarity matching result.
First, in step S101, an error correction lexicon is constructed using the historical error-free text of the topic dialog.
In this example, the method of the present invention is applied to speech recognition error correction of a speech dialog robot for a topic dialog.
Specifically, historical dialogue information of the man-machine dialogue is obtained, text conversion is carried out, and historical error-free text information of the topic dialogue is extracted.
More specifically, an error correction lexicon is constructed using the historical error-free text of the topic dialog.
Further, the error correction lexicon comprises example sentences and a multi-order dictionary. In this example, the multi-order dictionary includes a first-order dictionary and a second-order dictionary, both of which are used to determine the word to be corrected.
For example, a first order dictionary includes the words in w1、w2、w3、w4、…wnThe n words represented make up. And the second order dictionary comprises1w2、w2w3、w3w4、w4w5、…wn-1wnThe n pairs of the representation are composed.
It should be noted that, in other examples, a third order dictionary and/or a fourth order dictionary may also be included. However, the above description is only illustrative and not intended to limit the present invention.
Next, in step S102, a user voice input is received, and conversion of the user text input is performed on the user voice input.
Specifically, for example, the speech robot receives a user speech input and performs text conversion on the received speech input to obtain a user text input.
Next, in step S103, the converted user text input is subjected to word segmentation processing.
In the present example, for example, the user dialogously inputs "how much money can be made at one time", and after the voice robot recognizes the dialog input, it erroneously recognizes as text information "how much money can be made at one time".
Specifically, the word segmentation processing is performed on the text information "how much money can be changed at one time" in units of words, and the text information is divided into 5 words "once", "can", "change", "how much", and "money".
Next, in step S104, the error correction word bank is used to perform error correction judgment on each word after the word segmentation processing, and determine a word to be corrected.
In the present example, based on the error correction lexicon, frequency statistical calculation is performed on the single words after the word segmentation processing, for example, using a TF-IDF method, to calculate the frequency of occurrence of the single words in the error correction lexicon.
Further, a first order dictionary is used, and the word to be corrected is determined according to the first judgment rule.
Preferably, based on the error correction word bank, a TF-IDF method is further used to perform frequency statistical calculation on the two continuous words after word segmentation processing, so as to calculate the frequency of occurrence of the two words in the error correction word bank.
Further, a second order dictionary is used, and the word to be corrected is determined according to a second judgment rule.
As shown in fig. 2, the method further includes a step S201 of setting a first determination rule and a second determination rule corresponding to the first order dictionary and the second order dictionary.
In step S201, a first determination rule and a second determination rule corresponding to the first order dictionary and the second order dictionary are set.
Specifically, the first determination rule includes configuring a frequency threshold corresponding to a single word in the first-order dictionary, and the second determination rule includes configuring a frequency threshold corresponding to two words in the second-order dictionary.
For example, the frequency threshold of "change" is set to 5 times. For another example, the frequency threshold of "swappable" is set to 3 times.
Further, when the frequency calculation value of each word input by the user text is smaller than the frequency threshold value of the corresponding word in the first-order dictionary, the word is determined to be a word to be corrected. For example, the word "change" is calculated 2 times, 2 times < 5 times of the set threshold value, so the word "change" is determined as the word to be corrected.
Furthermore, when the frequency calculation value of two continuous words input by the user text is smaller than the frequency threshold value of two corresponding words in the second-order dictionary, the two continuous words are determined as the words to be corrected. For example, the word "can be exchanged" is calculated 1 times, the calculated value 1 times < the set threshold value 3 times, so that the two words "can be exchanged" are determined as the words to be corrected.
Next, in step S105, similarity matching is performed with the word vectors in the error correction lexicon based on vector similarity.
As shown in fig. 3, a step S301 of performing word vector conversion on the user text input is further included.
In step S301, word vector conversion is performed on the user text input.
Specifically, a sentence vector is formed by performing text word vector conversion, and similarity calculation is performed on the formed sentence vector and a sentence vector of an example sentence in the error correction lexicon.
It should be noted that, for example, a Word2vec model, a Bert model, or the like is used for calculation of the Word vector, but the calculation is not limited thereto, and the above description is only given as a preferable example, and the present invention is not limited thereto.
Preferably, a set threshold for judging the text similarity is preset according to factors such as the length of the text or the number of words.
Specifically, a corresponding set threshold is determined based on the user text input and the number of words after word segmentation.
Further, when the calculated text similarity is greater than a set threshold (for example, 90%), the example sentence is screened as the similar sentence input by the user text.
Next, in step S106, the word to be corrected is corrected according to the similarity matching result.
In this example, according to the similarity matching result, word-by-word matching is performed on each word in the screened example sentence and each word input by the user text, so as to determine a correct word corresponding to the word to be corrected.
Preferably, the word-by-word matching includes searching similar words with the same pinyin from the error correction word bank to correct the word to be corrected.
In this example, for example, the example sentences "how much money can be saved at a time", "how much money can be saved at a time" are screened out, and the user text input "how much money can be changed at a time" is matched word by word with each example sentence to determine the correct word "still" corresponding to "change".
It should be noted that the above description is only for illustrative purposes, and the present invention is not limited thereto.
The procedures of the above-described method are merely for illustrating the present invention, and the order and number of the steps are not particularly limited. In addition, the steps in the method can be split into two or three steps, or some steps can be combined into one step, and the steps are adjusted according to practical examples.
Compared with the prior art, the intelligent error correction method provided by the invention has the advantages that the error correction word bank is built, the first-order dictionary and the second-order dictionary of the error correction word bank are used for respectively carrying out error correction judgment on each word and two continuous words input by the user text, the correct word is determined through similarity matching, and finally the word to be corrected is corrected, so that the error correction method is optimized, the accuracy is improved, and the problem that the voice text to be corrected is not corrected is effectively avoided. In addition, the method has wider application scene range.
Those skilled in the art will appreciate that all or part of the steps to implement the above-described embodiments are implemented as programs (computer programs) executed by a computer data processing apparatus. When the computer program is executed, the method provided by the invention can be realized. Furthermore, the computer program may be stored in a computer readable storage medium, which may be a readable storage medium such as a magnetic disk, an optical disk, a ROM, a RAM, or a storage array composed of a plurality of storage media, such as a magnetic disk or a magnetic tape storage array. The storage medium is not limited to centralized storage, but may be distributed storage, such as cloud storage based on cloud computing.
Embodiments of systems of the present invention are described below, which may be used to perform method embodiments of the present invention. Details described in the system embodiments of the invention should be considered supplementary to the above-described method embodiments; reference is made to the above-described method embodiments for details not disclosed in the system embodiments of the invention.
Example 2
Referring to fig. 4, 5 and 6, the present invention also provides an intelligent error correction system 400 for speech recognition text, which is used for a speech dialogue robot of a topic dialogue, the intelligent error correction system 400 comprising: the building module 401 is configured to build an error correction word bank by using the historical error-free text of the topic dialog; a receiving module 402, configured to receive a user voice input, and perform conversion of a user text input on the user voice input; a processing module 403, configured to perform word segmentation processing on the converted user text input; a judging module 404, configured to perform error correction judgment on each word after the word segmentation processing by using the error correction word bank, and determine a word to be corrected; a matching module 405, which performs similarity matching with the word vectors in the error correction word bank based on the vector similarity; and the error correction module 406 is configured to correct the error of the word to be corrected according to the similarity matching result.
Preferably, the thesaurus for correcting errors includes an example sentence, a first order dictionary and a second order dictionary.
As shown in fig. 5, the apparatus further includes a first calculating module 501, where the first calculating module 501 performs frequency statistical calculation on a single word after word segmentation processing based on the error correction word bank; and using a first-order dictionary and determining the word to be corrected according to a first judgment rule.
Preferably, the word processing method further includes a second calculating module 502, where the second calculating module 502 further performs frequency statistical calculation on two consecutive words after word processing based on the error correction word bank; and using a second-order dictionary and determining the word to be corrected according to a second judgment rule.
As shown in fig. 6, the apparatus further includes a setting module 601, where the setting module 601 is configured to set a first determination rule and a second determination rule corresponding to the first-order dictionary and the second-order dictionary; the first judgment rule includes configuring a frequency threshold corresponding to a single word in the first order dictionary, and the second judgment rule includes configuring a frequency threshold corresponding to two words in the second order dictionary.
Preferably, the method further comprises the following steps: and when the frequency calculation value of each word input by the user text is smaller than the frequency threshold value of the corresponding word in the first-order dictionary, determining the word as a word to be corrected.
Preferably, the method further comprises the following steps: and when the frequency calculation value of the two continuous words input by the user text is smaller than the frequency threshold value of the two corresponding words in the second-order dictionary, determining the two continuous words as the words to be corrected.
Preferably, the method further comprises the following steps: performing word vector conversion on the user text input, and performing similarity calculation on the user text input and example sentences in the error correction word stock; and when the calculated text similarity is greater than a set threshold value, performing word-by-word matching on each word in the screened example sentence and each word input by the user text to determine a correct word corresponding to the word to be corrected.
Preferably, the word-by-word matching includes searching similar words with the same pinyin from the error correction word bank to correct the word to be corrected.
In embodiment 2, the same portions as those in embodiment 1 are not described.
Compared with the prior art, the intelligent error correction system provided by the invention has the advantages that the error correction word bank is built, the first-order dictionary and the second-order dictionary of the error correction word bank are used for respectively carrying out error correction judgment on each word and two continuous words input by the user text, the correct word is determined through similarity matching, and finally the word to be corrected is corrected, so that the accuracy is improved, and the problem that the voice text to be corrected is not corrected is effectively avoided. In addition, the system has wider application scene range.
Those skilled in the art will appreciate that the modules in the above-described system embodiments may be distributed in the system as described, and that corresponding variations may be made in one or more systems other than the above-described embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Example 3
Embodiments of the electronic device of the present invention are described below, which may be considered as specific physical implementations of the above-described embodiments of the method and system of the present invention. Details described in the embodiments of the electronic device of the invention should be considered supplementary to the embodiments of the method or system described above; for details not disclosed in the embodiments of the electronic device of the invention, reference may be made to the above-described method or system embodiments.
Fig. 7 is a block diagram of an exemplary embodiment of an electronic device according to the present invention. An electronic device 200 according to the invention will be described below with reference to fig. 7. The electronic device 200 shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 7, the electronic device 200 is embodied in the form of a general purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one memory unit 220, a bus 230 connecting different system components (including the memory unit 220 and the processing unit 210), a display unit 240, and the like.
Wherein the storage unit stores program code executable by the processing unit 210 to cause the processing unit 210 to perform steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic device processing method section of the present specification. For example, the processing unit 210 may perform the steps as shown in fig. 2.
The memory unit 220 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM) 2201 and/or a cache memory unit 2202, and may further include a read only memory unit (ROM) 2203.
The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 200 may also communicate with one or more external devices 300 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 200 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 250. Also, the electronic device 200 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention. The computer program, when executed by a data processing apparatus, enables the computer readable medium to carry out the above-described methods of the invention.
As shown in fig. 8, the computer program may be stored on one or more computer readable media. The computer readable medium may be a readable signal medium or a readable storage medium. A 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 readable storage medium include: an electrical connection having one or more wires, a portable disk, 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.
The computer readable storage medium may include a propagated data signal with 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 readable storage medium may also be any readable medium that is not a 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 readable storage 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.
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, 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 computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in embodiments in accordance with the invention may be implemented in practice using a general purpose data processing device such as a microprocessor or a Digital Signal Processor (DSP). The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
While the foregoing detailed description of the embodiments has described the objects, solutions, and advantages of the present invention in further detail, it is to be understood that the present invention is not inherently related to any particular computer, virtual machine, or electronic device, but may be implemented in various general-purpose systems. The invention is not to be considered as limited to the specific embodiments thereof, but is to be understood as being modified in all respects, all changes and equivalents that come within the spirit and scope of the invention.
Claims (10)
1. An intelligent error correction method for a speech recognition text, which is used for a speech dialogue robot of a topic dialogue and is characterized by comprising the following steps:
constructing an error correction word bank by using the historical error-free text of the topic type dialog;
receiving user voice input, and converting the user voice input into user text input;
inputting the converted user text, and performing word segmentation processing;
using the error correction word bank to perform error correction judgment on each word after word segmentation processing, and determining words to be corrected;
performing similarity matching with word vectors in the error correction word bank based on the vector similarity;
and correcting the word to be corrected according to the similarity matching result.
2. The intelligent method of error correction of speech recognition text according to claim 1, wherein the lexicon of error correction includes example sentences, a first order dictionary and a second order dictionary.
3. The intelligent error correction method for the speech recognition text according to claim 1 or 2, wherein the using the error correction thesaurus to perform error correction judgment on each word after the word segmentation processing and determining the word to be corrected further comprises:
performing frequency statistical calculation on the single word after the word segmentation processing based on the error correction word bank;
and using a first-order dictionary and determining the word to be corrected according to a first judgment rule.
4. The intelligent error correction method for speech recognition text according to claim 3, further comprising:
based on the error correction word bank, further performing frequency statistical calculation on the two continuous words after the word segmentation processing;
and using a second-order dictionary and determining the word to be corrected according to a second judgment rule.
5. The intelligent error correction method for speech recognition text according to claim 1 or 4, further comprising:
setting a first judgment rule and a second judgment rule corresponding to the first order dictionary and the second order dictionary;
the first judgment rule includes configuring a frequency threshold corresponding to a single word in the first order dictionary, and the second judgment rule includes configuring a frequency threshold corresponding to two words in the second order dictionary.
6. The intelligent error correction method for speech recognition text according to claim 5, further comprising:
and when the frequency calculation value of each word input by the user text is smaller than the frequency threshold value of the corresponding word in the first-order dictionary, determining the word as a word to be corrected.
7. The intelligent error correction method for speech recognition text according to claim 5, further comprising:
and when the frequency calculation value of the two continuous words input by the user text is smaller than the frequency threshold value of the two corresponding words in the second-order dictionary, determining the two continuous words as the words to be corrected.
8. An intelligent error correction system for speech recognition text, for use in a speech dialog robot for a topic dialog, comprising:
the building module is used for building an error correction word bank by utilizing the historical error-free text of the topic type conversation;
the receiving module is used for receiving the voice input of a user and converting the text input of the user to the voice input of the user;
the processing module is used for inputting the converted user text and performing word segmentation processing;
the judging module is used for carrying out error correction judgment on each word after the word is processed by using the error correction word bank and determining a word to be corrected;
the matching module is used for performing similarity matching with word vectors in the error correction word bank based on vector similarity;
and the error correction module is used for correcting the words to be corrected according to the similarity matching result.
9. An electronic device, wherein the electronic device comprises:
a processor; and the number of the first and second groups,
a memory storing computer executable instructions that, when executed, cause the processor to perform the intelligent method of error correction of speech recognition text according to any one of claims 1 to 7.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs which, when executed by a processor, implement the intelligent correction method of speech recognition text according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011191600.2A CN112016275A (en) | 2020-10-30 | 2020-10-30 | Intelligent error correction method and system for voice recognition text and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011191600.2A CN112016275A (en) | 2020-10-30 | 2020-10-30 | Intelligent error correction method and system for voice recognition text and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112016275A true CN112016275A (en) | 2020-12-01 |
Family
ID=73527665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011191600.2A Pending CN112016275A (en) | 2020-10-30 | 2020-10-30 | Intelligent error correction method and system for voice recognition text and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112016275A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417867A (en) * | 2020-12-07 | 2021-02-26 | 四川长虹电器股份有限公司 | Method and system for correcting video title error after voice recognition |
| CN112685550A (en) * | 2021-01-12 | 2021-04-20 | 腾讯科技（深圳）有限公司 | Intelligent question answering method, device, server and computer readable storage medium |
| CN112861521A (en) * | 2021-01-29 | 2021-05-28 | 思必驰科技股份有限公司 | Speech recognition result error correction method, electronic device, and storage medium |
| CN113778226A (en) * | 2021-08-26 | 2021-12-10 | 江西恒必达实业有限公司 | Infrared AI intelligent glasses based on speech recognition technology control intelligence house |
| CN113990302A (en) * | 2021-09-14 | 2022-01-28 | 北京左医科技有限公司 | Telephone follow-up voice recognition method, device and system |
| CN114742040A (en) * | 2022-06-09 | 2022-07-12 | 北京沃丰时代数据科技有限公司 | Text error correction method, text error correction device and electronic equipment |
| CN116341543A (en) * | 2023-05-31 | 2023-06-27 | 安徽商信政通信息技术股份有限公司 | Method, system, equipment and storage medium for identifying and correcting personal names |
-
2020
- 2020-10-30 CN CN202011191600.2A patent/CN112016275A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417867A (en) * | 2020-12-07 | 2021-02-26 | 四川长虹电器股份有限公司 | Method and system for correcting video title error after voice recognition |
| CN112685550A (en) * | 2021-01-12 | 2021-04-20 | 腾讯科技（深圳）有限公司 | Intelligent question answering method, device, server and computer readable storage medium |
| CN112685550B (en) * | 2021-01-12 | 2023-08-04 | 腾讯科技（深圳）有限公司 | Intelligent question-answering method, intelligent question-answering device, intelligent question-answering server and computer readable storage medium |
| CN112861521A (en) * | 2021-01-29 | 2021-05-28 | 思必驰科技股份有限公司 | Speech recognition result error correction method, electronic device, and storage medium |
| CN112861521B (en) * | 2021-01-29 | 2023-11-24 | 思必驰科技股份有限公司 | Speech recognition result error correction method, electronic device and storage medium |
| CN113778226A (en) * | 2021-08-26 | 2021-12-10 | 江西恒必达实业有限公司 | Infrared AI intelligent glasses based on speech recognition technology control intelligence house |
| CN113990302A (en) * | 2021-09-14 | 2022-01-28 | 北京左医科技有限公司 | Telephone follow-up voice recognition method, device and system |
| CN114742040A (en) * | 2022-06-09 | 2022-07-12 | 北京沃丰时代数据科技有限公司 | Text error correction method, text error correction device and electronic equipment |
| CN116341543A (en) * | 2023-05-31 | 2023-06-27 | 安徽商信政通信息技术股份有限公司 | Method, system, equipment and storage medium for identifying and correcting personal names |
| CN116341543B (en) * | 2023-05-31 | 2023-09-19 | 安徽商信政通信息技术股份有限公司 | Method, system, equipment and storage medium for identifying and correcting personal names |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112016275A (en) | Intelligent error correction method and system for voice recognition text and electronic equipment | |
| CN108847241B (en) | Method for recognizing conference voice as text, electronic device and storage medium | |
| CN109754809B (en) | Voice recognition method and device, electronic equipment and storage medium | |
| CN111402861B (en) | Voice recognition method, device, equipment and storage medium | |
| US20170116187A1 (en) | Natural language processor for providing natural language signals in a natural language output | |
| US20170352348A1 (en) | No Loss-Optimization for Weighted Transducer | |
| KR20160058531A (en) | Method for establishing syntactic analysis model using deep learning and apparatus for perforing the method | |
| CN112100339A (en) | User intention recognition method and device for intelligent voice robot and electronic equipment | |
| CN111326144B (en) | Voice data processing method, device, medium and computing equipment | |
| WO2020220824A1 (en) | Voice recognition method and device | |
| CN112346696A (en) | Speech comparison of virtual assistants | |
| US11610581B2 (en) | Multi-step linear interpolation of language models | |
| KR20210125449A (en) | Method for industry text increment, apparatus thereof, and computer program stored in medium | |
| CN113051895A (en) | Method, apparatus, electronic device, medium, and program product for speech recognition | |
| CN113160820A (en) | Speech recognition method, and training method, device and equipment of speech recognition model | |
| CN112151021A (en) | Language model training method, speech recognition device and electronic equipment | |
| JP7348447B2 (en) | Speaker diarization correction method and system utilizing text-based speaker change detection | |
| CN114783405B (en) | Speech synthesis method, device, electronic equipment and storage medium | |
| CN115101072A (en) | Voice recognition processing method and device | |
| CN114758649A (en) | Voice recognition method, device, equipment and medium | |
| CN110929749B (en) | Text recognition method, text recognition device, text recognition medium and electronic equipment | |
| CN109036379B (en) | Speech recognition method, apparatus and storage medium | |
| CN113689866A (en) | Training method and device of voice conversion model, electronic equipment and medium | |
| CN111883133A (en) | Customer service voice recognition method, customer service voice recognition device, customer service voice recognition server and storage medium | |
| CN113901841A (en) | Translation method, translation device and storage medium |
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 |