CN110176249A - A kind of appraisal procedure and device of spoken language pronunciation - Google Patents

A kind of appraisal procedure and device of spoken language pronunciation Download PDF

Info

Publication number
CN110176249A
CN110176249A CN201910266722.4A CN201910266722A CN110176249A CN 110176249 A CN110176249 A CN 110176249A CN 201910266722 A CN201910266722 A CN 201910266722A CN 110176249 A CN110176249 A CN 110176249A
Authority
CN
China
Prior art keywords
word
pronunciation
consonant
feature
gop
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
Application number
CN201910266722.4A
Other languages
Chinese (zh)
Inventor
方敏
蔡雅莉
戚自力
惠寅华
彭书勇
林远东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Chisheng Information Technology Co Ltd
Original Assignee
Suzhou Chisheng Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Chisheng Information Technology Co Ltd filed Critical Suzhou Chisheng Information Technology Co Ltd
Priority to CN201910266722.4A priority Critical patent/CN110176249A/en
Publication of CN110176249A publication Critical patent/CN110176249A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The present invention relates to a kind of appraisal procedure of spoken language pronunciation and devices, which comprises the spoken content of text for answering result of the examinee of acquisition；Extract each word pronunciation character in the content of text；Based on the pronunciation character of each word, determine whether the pronunciation of each word is correct；Based on the quantity of orthoepic word, the spoken language pronunciation result of examinee is assessed.The spoken language of examinee is answered, the present invention can determine the quantity of orthoepic word based on the pronunciation character of each word, so that the spoken language pronunciation effect for assessing examinee is good or bad, thus the targetedly spoken language proficiency of promotion examinee.

Description

A kind of appraisal procedure and device of spoken language pronunciation
Technical field
The present invention relates to field of computer technology, more particularly to the appraisal procedure and device of a kind of spoken language pronunciation.
Background technique
As the important medium of interpersonal communication, conversational language occupies extremely important status in real life.With society The progress of continuous development and economical globalization tendency that can be economic, people are objective to the efficiency of language learning and language assessment Property, fairness and scale test propose increasingly higher demands.For example oral composition of Open-ended Question type in speaking test, story Repetition and picture talk etc. are to reflect an important topic type of the ability to express of examinee's spoken language.In general, teacher is in addition in terms of content Outside being judged, also judge the student pronunciation of words whether standard, and whole pronunciation situation.
Traditional speaking test points-scoring system is directly to learn Rating Model according to the total score labeled data of teacher's marking, is given A total score output out.And pronunciation of the student in oral expression whether standard, whole pronunciation what state has no way of learning.
Summary of the invention
Based on this, it is necessary to aiming at the problem that pronunciation of current speaking test is difficult to assess, provide a kind of commenting for spoken language pronunciation Estimate method and device.
A kind of appraisal procedure of spoken language pronunciation, which comprises
The spoken content of text for answering result of the examinee of acquisition；
Extract the pronunciation character of each word in the content of text；
Based on the pronunciation character of each word, determine whether the pronunciation of each word is correct；
Based on the quantity of orthoepic word, the spoken language pronunciation result of examinee is assessed.
In the present embodiment, the pronunciation character includes the acoustics likelihood feature of word, described to extract in the content of text often The pronunciation character of a word, comprising:
The frame of vowel and consonant based on each word is averaged likelihood score, determines the acoustics Likelihood Score of each word；
By the acoustics Likelihood Score to the acoustics likelihood feature that should be used as each word.
In the present embodiment, the pronunciation character includes gop feature, the pronunciation for extracting each word in the content of text Feature, comprising:
Obtain the gop marking of each word medial vowel and consonant；
It is given a mark based on the gop of each word medial vowel and consonant and determines the gop marking of corresponding each word；
Gop feature by the gop marking of each word as equivalent.
In the present embodiment, the pronunciation character includes the consistency feature of pronunciation, described to extract in the content of text often The pronunciation character of a word, comprising:
Determine the number of each word medial vowel and the consonant frame consistent with standard pronunciation；
The consistency feature that the number for the frame that each word medial vowel is consistent with consonant is pronounced as the equivalent.
In the present embodiment, the pronunciation character includes the accuracy feature of pronunciation, described to extract in the content of text often The pronunciation character of a word, comprising:
Obtain the number of each word medial vowel and the correct frame of consonant；
Number based on each word medial vowel and the correct frame of consonant determines that each word medial vowel and consonant articulation are correct Frame accuracy；
Each word medial vowel and the correct frame accuracy of consonant articulation are being determined as the pronunciation of each word just True rate feature.
A kind of assessment device of spoken language pronunciation, described device include:
Module is obtained, the spoken content of text for answering result of the examinee for acquisition；
Extraction module, for extracting the pronunciation character of each word in the content of text；
Determining module determines whether the pronunciation of each word is correct for the pronunciation character based on each word；
Evaluation module assesses the spoken language pronunciation result of examinee for the quantity based on orthoepic word.
In the present embodiment, the pronunciation character includes the acoustics likelihood feature of word, and the extraction module is used for:
The frame of vowel and consonant based on each word is averaged likelihood score, determines the acoustics Likelihood Score of each word；
By the acoustics Likelihood Score to the acoustics likelihood feature that should be used as each word.
In the present embodiment, the pronunciation character includes gop feature, and the extraction module is used for:
Obtain the gop marking of each word medial vowel and consonant；
It is given a mark based on the gop of each word medial vowel and consonant and determines the gop marking of corresponding each word；
Gop feature by the gop marking of each word as equivalent.
In the present embodiment, the pronunciation character includes the consistency feature of pronunciation, and the extraction module is used for:
Determine the number of each word medial vowel and the consonant frame consistent with standard pronunciation；
The consistency feature that the number for the frame that each word medial vowel is consistent with consonant is pronounced as the equivalent.
In the present embodiment, the pronunciation character includes the accuracy feature of pronunciation, and the extraction module is used for:
Obtain the number of each word medial vowel and the correct frame of consonant；
Number based on each word medial vowel and the correct frame of consonant determines that each word medial vowel and consonant articulation are correct Frame accuracy；
Each word medial vowel and the correct frame accuracy of consonant articulation are being determined as the pronunciation of each word just True rate feature.
In the present invention, after the spoken content of text for answering result of the examinee of acquisition, the content of text can be extracted In each word pronunciation character；Based on the pronunciation character of each word, determine whether the pronunciation of each word is correct；Just based on pronunciation The quantity of true word assesses the spoken language pronunciation result of examinee.It is answered accordingly, for the spoken language of examinee, the present invention can be based on every The pronunciation character of a word, determines the quantity of orthoepic word, thus the spoken language pronunciation effect for assessing examinee be it is good or bad, from And targetedly promote the spoken language proficiency of examinee.
Detailed description of the invention
Fig. 1 is the flow chart of the appraisal procedure of the spoken language pronunciation of an embodiment；
Fig. 2 is the structure chart of the assessment device of the spoken language pronunciation of an embodiment.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and It is not used in the restriction present invention.
Fig. 1 is the flow chart of the appraisal procedure of the spoken language pronunciation of an embodiment.As shown in Figure 1, this method comprises:
Step 110, the spoken content of text for answering result of the examinee of acquisition；
Step 120, the pronunciation character of each word in content of text is extracted；
Step 130, the pronunciation character based on each word determines whether the pronunciation of each word is correct；
Step 140, the quantity based on orthoepic word assesses the spoken language pronunciation result of examinee.
In the present invention, after the spoken content of text for answering result of the examinee of acquisition, the content of text can be extracted In each word pronunciation character；Based on the pronunciation character of each word, determine whether the pronunciation of each word is correct；Just based on pronunciation The quantity of true word assesses the spoken language pronunciation result of examinee.It is answered accordingly, for the spoken language of examinee, the present invention can be based on every The pronunciation character of a word, determines the quantity of orthoepic word, thus the spoken language pronunciation effect for assessing examinee be it is good or bad, from And targetedly promote the spoken language proficiency of examinee.
Wherein, the spoken result of answering of examinee can be by the audio file etc. of voice acquisition system acquisition.
Content of text can be speech recognition system from the spoken word content answered and extracted in result.It is appreciated that this Embodiment is not limited to the spoken acquisition modes for answering result and content of text.
In the present embodiment, pronunciation character can be acoustics likelihood feature, gop feature, the consistency feature of pronunciation, pronunciation At least one of accuracy feature etc..
In one implementation of the present embodiment, pronunciation character includes the acoustics likelihood feature of word, is extracted every in content of text A word pronunciation character, comprising:
The frame of vowel and consonant based on each word is averaged likelihood score, determines the acoustics Likelihood Score of each word；
By acoustics Likelihood Score to the acoustics likelihood feature that should be used as each word.
Wherein it is possible to count the acoustics Likelihood Score of word in content of text, and consider the difference of vowel, consonant, specifically may be used To be based on following data:
The frame of word grade is averaged likelihood score (mean, max, min)
The frame of word medial vowel is averaged likelihood score (mean, max, min)
The frame of consonant is averaged likelihood score (mean, max, min) in word
Word medial vowel number, consonant number, phone total number
In one implementation of the present embodiment, pronunciation character includes gop feature, and it is special to extract each word pronunciation in content of text Sign, comprising:
Obtain the gop marking of each word medial vowel and consonant；
It is given a mark based on the gop of each word medial vowel and consonant and determines the gop marking of corresponding each word；
Gop feature by the gop marking of each word as equivalent.
Wherein, the phone grade gop marking of word in content of text is counted, and considers the difference of vowel, consonant, it can be specific It is as follows:
The mean, max, min of the gop marking of word medial vowel；
The mean, max, min of the gop marking of consonant in word；
The mean, max, min of the gop marking of phone in word.
In one implementation of the present embodiment, pronunciation character includes the consistency feature of pronunciation, is extracted every in content of text A word pronunciation character, comprising:
Determine the number of each word medial vowel and the consonant frame consistent with standard pronunciation；
The consistency feature that the number for the frame that each word medial vowel is consistent with consonant is pronounced as equivalent.
Wherein it is possible to count the consistency of the vowel of fa, rec of input word $ word_i $, consonant, all in content of text (unit: frame)
All pronunciation consistency:
agrall=sum(HitFramesphonex)/NumFramesAll；
Vowel consistency:
agrvowels=sum(HitFramesvowelsx)/NumFramesVow；
Consonant consistency:
agrconsonants=sum(Hitframesconsonants)/NumFramesCon；
HitFrames_x indicates the number that the consistent frame of phone is corresponded in rec and fa；NumFramesX indicates word's All or part of frame number.
In one implementation of the present embodiment, pronunciation character includes the accuracy feature of pronunciation, is extracted each in content of text Word pronunciation character, comprising:
Obtain the number of each word medial vowel and the correct frame of consonant；
Number based on each word medial vowel and the correct frame of consonant determines that each word medial vowel and consonant articulation are correct Frame accuracy；
Each word medial vowel and the correct frame accuracy of consonant articulation are determined as to the accuracy feature of the pronunciation of each word.
Count the accounting (unit: a of the consistent number of vowel, consonant, all of fa, rec of input word in content of text Number):
The accuracy of all pronunciations:
CountsAccall=sum(Hitphonex)/NumCountsAll；
The accuracy of vowel:
CountsAcclvowels=sum (Hitvowelsx)/NumCountsVow；
The accuracy of consonant:
CountsAccconsonants=sum (Hitconsonants)/NumCountsCon；
Hit_x indicates to be 1 if fa is more than or equal to some threshold value (0.5) with the consistency of the corresponding phone of rec, otherwise It is 0；After NumCountsX indicates the phone number of some or all of word, input word in content of text can be counted Fa, rec accuracy (unit: frame) of vowel, consonant, all:
The frame accuracy of all pronunciations:
FramesAccall=sum (FramesHitPhonex)/NumFramesAll；
The frame accuracy of vowel:
FramesAccvowels=sum (FramesHitVowelsx)/NumFramesVow；
The frame accuracy of consonant:
FramesAccconsonants=sum (FramesHitConsonants)/NumFramesCon；
Frames_HitX is indicated Otherwise frame number of the phone in fa is 0；NumFramesX indicates the frame number of some or all of word
It, can when determining whether the pronunciation of each word is correct based on the pronunciation character of each word in one embodiment of this implementation To use Multilayer Perception classifier (MLP) algorithm.Mainly consider that its model complexity is controllable, supports the training of high-volume data.
It can will be in the above acoustics likelihood feature, gop feature, the consistency feature of pronunciation, accuracy feature of pronunciation etc. At least one be input in MLP model, so that it is determined that whether the pronunciation of each word correct.
Quantity later based on orthoepic word, it can be estimated that the spoken language pronunciation result of examinee.Specifically, can be based on It is divided by with total word quantity, obtains a ratio, can determine examinee's sheet based on the ratio by the quantity of orthoepic word The secondary spoken overall marking answered.Ratio and overall marking are proportional, and therefore, overall marking is based on whole section of spoken Open-ended Question type The measurement of the word accuracy of sample, i.e. accuracy is higher, then shows that the whole pronunciation situation of the sample is better.
Fig. 2 is the structure chart of the assessment device of the spoken language pronunciation of an embodiment.As shown in Fig. 2, the device includes:
Module 210 is obtained, the spoken content of text for answering result of the examinee for acquisition；
Extraction module 220, for extracting the pronunciation character of each word in content of text；
Determining module 230 determines whether the pronunciation of each word is correct for the pronunciation character based on each word；
Evaluation module 240 assesses the spoken language pronunciation result of examinee for the quantity based on orthoepic word.
In the present invention, after the spoken content of text for answering result of the examinee of acquisition, the content of text can be extracted In each word pronunciation character；Based on the pronunciation character of each word, determine whether the pronunciation of each word is correct；Just based on pronunciation The quantity of true word assesses the spoken language pronunciation result of examinee.It is answered accordingly, for the spoken language of examinee, the present invention can be based on every The pronunciation character of a word, determines the quantity of orthoepic word, thus the spoken language pronunciation effect for assessing examinee be it is good or bad, from And targetedly promote the spoken language proficiency of examinee.
In one implementation of the present embodiment, pronunciation character includes the acoustics likelihood feature of word, and extraction module is used for:
The frame of vowel and consonant based on each word is averaged likelihood score, determines the acoustics Likelihood Score of each word；
By acoustics Likelihood Score to the acoustics likelihood feature that should be used as each word.
In one implementation of the present embodiment, pronunciation character includes gop feature, and extraction module is used for:
Obtain the gop marking of each word medial vowel and consonant；
It is given a mark based on the gop of each word medial vowel and consonant and determines the gop marking of corresponding each word；
Gop feature by the gop marking of each word as equivalent.
In one implementation of the present embodiment, pronunciation character includes the consistency feature of pronunciation, and extraction module is used for:
Determine the number of each word medial vowel and the consonant frame consistent with standard pronunciation；
The consistency feature that the number for the frame that each word medial vowel is consistent with consonant is pronounced as equivalent.
In one implementation of the present embodiment, pronunciation character includes the accuracy feature of pronunciation, and extraction module is used for:
Obtain the number of each word medial vowel and the correct frame of consonant；
Number based on each word medial vowel and the correct frame of consonant determines that each word medial vowel and consonant articulation are correct Frame accuracy；
Each word medial vowel and the correct frame accuracy of consonant articulation are determined as to the accuracy feature of the pronunciation of each word.
The realization process of apparatus above of the present invention and the realization process of above method are identical, are specifically referred to above method The detailed process of embodiment, the present invention are no longer specifically described.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.

Claims (10)

1. a kind of appraisal procedure of spoken language pronunciation, which is characterized in that the described method includes:
The spoken content of text for answering result of the examinee of acquisition；
Extract the pronunciation character of each word in the content of text；
Based on the pronunciation character of each word, determine whether the pronunciation of each word is correct；
Based on the quantity of orthoepic word, the spoken language pronunciation result of examinee is assessed.
2. the method according to claim 1, wherein the pronunciation character includes the acoustics likelihood feature of word, institute It states and extracts word pronunciation character each in the content of text, comprising:
The frame of vowel and consonant based on each word is averaged likelihood score, determines the acoustics Likelihood Score of each word；
By the acoustics Likelihood Score to the acoustics likelihood feature that should be used as each word.
3. the method according to claim 1, wherein the pronunciation character includes gop feature, described in the extraction The pronunciation character of each word in content of text, comprising:
Obtain the gop marking of each word medial vowel and consonant；
It is given a mark based on the gop of each word medial vowel and consonant and determines the gop marking of corresponding each word；
Gop feature by the gop marking of each word as equivalent.
4. the method according to claim 1, wherein the pronunciation character includes the consistency feature of pronunciation, institute State the pronunciation character for extracting each word in the content of text, comprising:
Determine the number of each word medial vowel and the consonant frame consistent with standard pronunciation；
The consistency feature that the number for the frame that each word medial vowel is consistent with consonant is pronounced as the equivalent.
5. the method according to claim 1, wherein the pronunciation character includes the accuracy feature of pronunciation, institute State the pronunciation character for extracting each word in the content of text, comprising:
Obtain the number of each word medial vowel and the correct frame of consonant；
Number based on each word medial vowel and the correct frame of consonant is determining each word medial vowel and the correct frame of consonant articulation just True rate；
Each word medial vowel and the correct frame accuracy of consonant articulation are determined as to the accuracy of the pronunciation of each word Feature.
6. a kind of assessment device of spoken language pronunciation, which is characterized in that described device includes:
Module is obtained, the spoken content of text for answering result of the examinee for acquisition；
Extraction module, for extracting the pronunciation character of each word in the content of text；
Determining module determines whether the pronunciation of each word is correct for the pronunciation character based on each word；
Evaluation module assesses the spoken language pronunciation result of examinee for the quantity based on orthoepic word.
7. device according to claim 7, which is characterized in that the pronunciation character includes the acoustics likelihood feature of word, institute Extraction module is stated to be used for:
The frame of vowel and consonant based on each word is averaged likelihood score, determines the acoustics Likelihood Score of each word；
By the acoustics Likelihood Score to the acoustics likelihood feature that should be used as each word.
8. device according to claim 6, which is characterized in that the pronunciation character includes gop feature, the extraction module For:
Obtain the gop marking of each word medial vowel and consonant；
It is given a mark based on the gop of each word medial vowel and consonant and determines the gop marking of corresponding each word；
Gop feature by the gop marking of each word as equivalent.
9. device according to claim 6, which is characterized in that the pronunciation character includes the consistency feature of pronunciation, institute Extraction module is stated to be used for:
Determine the number of each word medial vowel and the consonant frame consistent with standard pronunciation；
The consistency feature that the number for the frame that each word medial vowel is consistent with consonant is pronounced as the equivalent.
10. device according to claim 6, which is characterized in that the pronunciation character includes the accuracy feature of pronunciation, institute Extraction module is stated to be used for:
Obtain the number of each word medial vowel and the correct frame of consonant；
Number based on each word medial vowel and the correct frame of consonant is determining each word medial vowel and the correct frame of consonant articulation just True rate；
Each word medial vowel and the correct frame accuracy of consonant articulation are determined as to the accuracy of the pronunciation of each word Feature.
CN201910266722.4A 2019-04-03 2019-04-03 A kind of appraisal procedure and device of spoken language pronunciation Pending CN110176249A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910266722.4A CN110176249A (en) 2019-04-03 2019-04-03 A kind of appraisal procedure and device of spoken language pronunciation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910266722.4A CN110176249A (en) 2019-04-03 2019-04-03 A kind of appraisal procedure and device of spoken language pronunciation

Publications (1)

Publication Number Publication Date
CN110176249A true CN110176249A (en) 2019-08-27

Family

ID=67689392

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910266722.4A Pending CN110176249A (en) 2019-04-03 2019-04-03 A kind of appraisal procedure and device of spoken language pronunciation

Country Status (1)

Country Link
CN (1) CN110176249A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110648690A (en) * 2019-09-26 2020-01-03 广州三人行壹佰教育科技有限公司 Audio evaluation method and server
CN110782921A (en) * 2019-09-19 2020-02-11 腾讯科技（深圳）有限公司 Voice evaluation method and device, storage medium and electronic device
CN112614510A (en) * 2020-12-23 2021-04-06 北京猿力未来科技有限公司 Audio quality evaluation method and device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101887725A (en) * 2010-04-30 2010-11-17 中国科学院声学研究所 Phoneme confusion network-based phoneme posterior probability calculation method
CN104485115A (en) * 2014-12-04 2015-04-01 上海流利说信息技术有限公司 Pronunciation evaluation equipment, method and system
CN108682437A (en) * 2018-05-18 2018-10-19 网易乐得科技有限公司 Information processing method, device, medium and computing device
CN108711319A (en) * 2018-05-24 2018-10-26 李炜 A kind of international professional Chinese teaching method and system
CN109545243A (en) * 2019-01-23 2019-03-29 北京猎户星空科技有限公司 Pronunciation quality evaluating method, device, electronic equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101887725A (en) * 2010-04-30 2010-11-17 中国科学院声学研究所 Phoneme confusion network-based phoneme posterior probability calculation method
CN104485115A (en) * 2014-12-04 2015-04-01 上海流利说信息技术有限公司 Pronunciation evaluation equipment, method and system
CN108682437A (en) * 2018-05-18 2018-10-19 网易乐得科技有限公司 Information processing method, device, medium and computing device
CN108711319A (en) * 2018-05-24 2018-10-26 李炜 A kind of international professional Chinese teaching method and system
CN109545243A (en) * 2019-01-23 2019-03-29 北京猎户星空科技有限公司 Pronunciation quality evaluating method, device, electronic equipment and storage medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110782921A (en) * 2019-09-19 2020-02-11 腾讯科技（深圳）有限公司 Voice evaluation method and device, storage medium and electronic device
CN110782921B (en) * 2019-09-19 2023-09-22 腾讯科技（深圳）有限公司 Voice evaluation method and device, storage medium and electronic device
CN110648690A (en) * 2019-09-26 2020-01-03 广州三人行壹佰教育科技有限公司 Audio evaluation method and server
CN112614510A (en) * 2020-12-23 2021-04-06 北京猿力未来科技有限公司 Audio quality evaluation method and device
CN112614510B (en) * 2020-12-23 2024-04-30 北京猿力未来科技有限公司 Audio quality assessment method and device

Similar Documents

Publication Publication Date Title
CN110782921B (en) Voice evaluation method and device, storage medium and electronic device
CN109545244A (en) Speech evaluating method, device, electronic equipment and storage medium
US8226416B2 (en) Method and apparatus for reading education
Richards Conversation
CN110176249A (en) A kind of appraisal procedure and device of spoken language pronunciation
JP2005321817A (en) Method and apparatus for obtaining combining information from speech signals for adaptive interaction in teaching and testing
KR20010074705A (en) Automated language assessment using speech recognition modeling
JP2009503563A (en) Assessment of spoken language proficiency by computer
Uchanski et al. Automatic speech recognition to aid the hearing impaired: prospects for the automatic generation of cued speech.
CN101393694A (en) Chinese character pronunciation studying device with pronunciation correcting function of Chinese characters, and method therefor
Inoue et al. A Study of Objective Measurement of Comprehensibility through Native Speakers' Shadowing of Learners' Utterances.
CN110164422A (en) A kind of the various dimensions appraisal procedure and device of speaking test
CN107910059A (en) A kind of language ability obstacle hierarchy system and its implementation
CN109584906A (en) Spoken language pronunciation evaluating method, device, equipment and storage equipment
US11138379B2 (en) Determination of transcription accuracy
Cámara Arenas et al. Automatic pronunciation assessment vs. automatic speech recognition: A study of conflicting conditions for L2-English
KR100997255B1 (en) Language learning system of simultaneous interpretation type using voice recognition
KR102407055B1 (en) Apparatus and method for measuring dialogue quality index through natural language processing after speech recognition
CN113327615B (en) Voice evaluation method, device, equipment and storage medium
CN115099222A (en) Punctuation mark misuse detection and correction method, device, equipment and storage medium
Davies Language assessment in call centres: The case of the customer service representative
CN114708854A (en) Voice recognition method and device, electronic equipment and storage medium
Jun et al. Factors in Raters’ Perceptions of Comprehensibility and Accentedness
US20210304628A1 (en) Systems and Methods for Automatic Video to Curriculum Generation
Nath Towards naturally responsive spoken dialog systems by modelling pragmatic-prosody correlations of discourse markers

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190827