CN101034498A - Language environment transform method, system and device - Google Patents
Language environment transform method, system and device Download PDFInfo
- Publication number
- CN101034498A CN101034498A CNA200610080052XA CN200610080052A CN101034498A CN 101034498 A CN101034498 A CN 101034498A CN A200610080052X A CNA200610080052X A CN A200610080052XA CN 200610080052 A CN200610080052 A CN 200610080052A CN 101034498 A CN101034498 A CN 101034498A
- Authority
- CN
- China
- Prior art keywords
- mother
- pronunciation
- language
- voice
- foreign language
- 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
Landscapes
- Machine Translation (AREA)
Abstract
The invention relates to according to this invention language environment transformation method, system and the equipment, the person which speaks the mother tongue in the mother language environment (hereafter refers to as: The mother tongue side) sends out the mother tongue pronunciation (hereafter refers to as: The mother pronunciation) translates and transforms into the foreign language pronunciation of same meaning or the close (hereafter refers to as: foreign language pronunciation), broadcasts to the study foreign language person(hereafter refers to as: The study side) listens, also the study side send out states the foreign language the foreign language pronunciation translation to transform for the meaning same or is close the mother tongue pronunciation, the broadcast gives the mother tongue side to listen; In the mother tongue language environment, the study side will be able through this installment, to speak the mother tongue with the foreign language in the mother tongue side to carry on the dialogue and exchange, the studied foreign language will enhance during the practical life utilization, thus form the study side individual foreign language language environment; And this installment also can translate and transform the mother tongue into the foreign language, carries on the foreign language teaching and the study.
Description
Technical field
The present invention relates to a kind of language environment transform method, system and device,, in the foreign language studying process, can engage in the dialogue and the device that exchanges with the people who speaks one's mother tongue with foreign language especially for for living in the people in the mother tongue language environment.
Background technology
At present, the electronic product of foreign language studying has a variety of, as digital learning machine, the re-reading learning machine of magnetic tape type, magnetic tape type recording playback sound learning machine, the textbook or the like of can speaking, and these learning devices can only be used for listening, with read, mechanical man-machine respective session one by one, face can not be used for foreign language among the real life; Foreign language studying the most important thing is that the foreign language language environment will be arranged, and can use in real life; Child lives in the foreign language language environment, and association says foreign language naturally; Student and adult learn a foreign language, and constantly practice and raising just can be said the fluent foreign language of a bite in the foreign language language environment; And now we overwhelming majority from the nursery class to the university, learn two more than ten years foreign language and can not say foreign language, be because the foreign language language environment of foreign language not being studied in order to practise among our daily life.
Summary of the invention
For this reason, the invention provides a kind of language environment transform method, system and device.
According to language environment transform method of the present invention, system and device, with the people who says mother tongue in the mother tongue language environment (hereinafter to be referred as: the mother tongue pronunciation of mother tongue side) sending (hereinafter to be referred as: mother pronunciation) translation be converted to equivalent in meaning or close foreign language voice (hereinafter to be referred as: outer voice), play to foreign language studying the people (hereinafter to be referred as: study side) listen, the outer voice translation of the described foreign language that described study side is sent is converted to the mother pronunciation of equivalent in meaning or close described mother tongue again, plays to described mother tongue side and listens; In the mother tongue language environment, study can engage in the dialogue with the mother tongue side that speaks one's mother tongue and exchange with foreign language by this device, with foreign language raising among the real life utilization of study, thus the individual foreign language language environment of formation study side; And this device can also be used for native language translation is converted to foreign language, carries out foreign language teaching and study.
According to an aspect of the present invention, the invention provides a kind of language environment transform method, comprising:
The mother pronunciation that mother tongue side is sent is imported;
Described mother pronunciation is carried out speech recognition, produce described mother pronunciation recognition result;
According to described mother pronunciation recognition result, described mother pronunciation is translated as foreign language;
The outer voice of described foreign language are played to study side to be listened;
Further comprise:
The outer voice input of the described foreign language that described study side is sent;
Described outer voice are carried out speech recognition, produce described outer voice recognition result;
According to described outer voice recognition result, described outer voice are translated as described mother tongue;
The mother pronunciation of described mother tongue is played to described mother tongue side listens;
When a described mother pronunciation is imported, disconnect other phonetic entry passage;
When one described outside voice when input, disconnect other phonetic entry passage;
Judge that a described mother pronunciation carries out whether success of speech recognition, when successful, play the check and correction sound of described mother pronunciation to described mother tongue side or all or part of or other mother tongue side with described mother tongue, otherwise, with described mother tongue to described mother tongue side playing alert tones;
Judge that described outer voice carry out whether success of speech recognition, when successful, with the check and correction sound of described foreign language voice outside described study side or all or part of or other study side's broadcast are described, otherwise, with described foreign language to described study side playing alert tones;
Carry out speech recognition when success when a described mother pronunciation, described mother pronunciation is translated as described foreign language, the outer voice of described foreign language are played to all or part of described study side tin;
When one described outside voice carry out speech recognition when success, described outer voice are translated as described mother tongue, the mother pronunciation of described mother tongue is played to all or part of described mother tongue side listens;
Described mother tongue is meant mother tongue or the dialect or the mother tongue of described study side, and described foreign language is meant the described mother tongue of described study side or a kind of language or the multilingual outside described dialect or the described mother tongue;
For Chinese, described mother tongue is meant mandarin or various places dialect or minority language, and described foreign language is meant the language outside one or more foreign language or this minority language;
According to a further aspect in the invention, the invention provides a kind of language environment converting system, comprising:
The mother pronunciation input media is used to import the mother pronunciation that mother tongue side is sent, and converts described mother pronunciation to described mother pronunciation signal;
The mother pronunciation recognition device is used for described mother pronunciation signal templates in described mother pronunciation signal and the mother tongue acoustic model is mated, and produces described mother pronunciation recognition result;
The foreign language translation device is used for according to described mother pronunciation recognition result described mother pronunciation being translated as foreign language;
Outer voice playing device is used for outer voice with described foreign language and plays to study side and listen;
Further comprise:
Outer voice input media is used to import the outer voice that described study side sends, and converts described outer voice to described outer voice signal;
Outer voice recognition device is used for described outer voice signal template in described outer voice signal and the foreign language acoustic model is mated, and produces described outer voice recognition result;
The native language translation device is used for according to described outer voice recognition result described outer voice being translated as described mother tongue;
The mother pronunciation playing device is used for mother pronunciation with described mother tongue and plays to described mother tongue side and listen;
Further comprise:
The phonetic entry channel controller, be used for when a described mother pronunciation input media or one described outside the voice input media when carrying out phonetic entry, forbid other speech input device input voice;
The voice output channel controller, be used to control described outer voice playing device with the check and correction sound of described foreign language voice outside the outer voice study side of input or all or part of or other study side broadcast are described and with described foreign language to import described outside the voice side of study playing alert tones and be translated as the outer voice of described foreign language with described foreign language to the described mother pronunciation of all or part of study side's broadcast;
Described voice output channel controller, also be used to control described mother pronunciation playing device plays described mother pronunciation to input mother pronunciation mother tongue side or all or part of or other mother tongue side with described mother tongue check and correction sound with described mother tongue to importing described mother pronunciation mother tongue side playing alert tones and being translated as the mother pronunciation of described mother tongue with described mother tongue voice outside all or part of mother tongue side broadcast is described;
Described foreign language translation device is the phonetic representation mode that a cover has stored described foreign language, and these expression waies are corresponding with each described mother pronunciation recognition result, or described foreign language translation device is the Text To Speech translating equipment;
Described native language translation device is the phonetic representation mode that a cover has stored described mother tongue, and these expression waies are corresponding with each described outer voice recognition result, or described native language translation device is the Text To Speech translating equipment;
Described foreign language translation device and described native language translation device are that a cover has stored described foreign language or comprised the multiple foreign language of described foreign language and the phonetic representation mode of described mother tongue, and these expression waies are corresponding with each described outer voice recognition result and/or each described mother pronunciation recognition result; Or described foreign language translation device and described native language translation device are the Text To Speech translating equipments;
Described mother pronunciation recognition device and the shared speech recognition engine of described outer voice recognition device and/or the acoustic model that mixes of a shared described mother tongue and described foreign language;
Described mother tongue is meant mother tongue or the dialect or the mother tongue of described study side, and described foreign language is meant the described mother tongue of described study side or a kind of language or the multilingual outside described dialect or the described mother tongue;
For Chinese, described mother tongue is meant mandarin or various places dialect or minority language, and described foreign language is meant the language outside one or more foreign language or this minority language.
According to a further aspect in the invention, the invention provides a kind of language environment conversion equipment, comprising:
One or more mother pronunciation input medias are used to import the mother pronunciation that mother tongue side is sent, and convert described mother pronunciation to described mother pronunciation signal;
One or more outer voice playing devices are used for voice outside study side plays;
Each described mother pronunciation input media is connected main frame respectively with each described outer voice playing device;
Described main frame is used to receive the described mother pronunciation signal of a described mother pronunciation input media, and described mother pronunciation translation is converted to described foreign language, and the outer voice of described foreign language are played to described study side tin from all or part of described outer voice playing device;
Further comprise:
One or more outer voice input medias are used to import the outer voice that described study side sends, and convert described outer voice to described outer voice signal;
One or more mother pronunciation playing devices are used for playing mother pronunciation to described mother tongue side;
Each described outer voice input media is connected described main frame respectively with each described mother pronunciation playing device;
Described main frame also is used to receive the described outer voice signal of a described outer voice input media, and described outer voice translation is converted to described mother tongue, the mother pronunciation of described mother tongue is played to described mother tongue side from all or part of described mother pronunciation playing device listen;
Described main frame comprises wireless transmitter, is used for voice signal wireless telecommunications between described main frame and described mother pronunciation input media and/or described outer voice playing device and/or described outer voice input media and/or the described mother pronunciation playing device;
All or part of described mother pronunciation input media connects wireless transmitter, is used for voice signal wireless telecommunications between described mother pronunciation input media and the described main frame;
All or part of described outer voice input media connects wireless transmitter, is used for voice signal wireless telecommunications between described outer voice input media and the described main frame;
All or part of described outer voice playing device connects wireless transmitter, is used for voice signal wireless telecommunications between described outer voice playing device and the described main frame;
All or part of described mother pronunciation playing device connects wireless transmitter, is used for voice signal wireless telecommunications between described mother pronunciation playing device and the described main frame;
Described mother tongue is meant mother tongue or the dialect or the mother tongue of described study side, and described foreign language is meant the described mother tongue of described study side or a kind of language or the multilingual outside described dialect or the described mother tongue;
For Chinese, described mother tongue is meant mandarin or various places dialect or minority language, and described foreign language is meant the language outside one or more foreign language or this minority language;
Comprise one or more wearable devices.
The invention will be further described below in conjunction with drawings and Examples, and target of the present invention and advantage are clearer, and be convenient to understand.
Description of drawings
Fig. 1 is the theory diagram according to language environment converting system of the present invention;
Fig. 2 A translates according to the mother pronunciation of language environment transform method of the present invention to be converted to one of process flow diagram of outer voice;
Fig. 2 B translates according to the outer voice of language environment transform method of the present invention to be converted to one of process flow diagram of mother pronunciation;
Fig. 3 A is two of translation is converted to outer voice according to the mother pronunciation of a language environment transform method of the present invention process flow diagram;
Fig. 3 B is two of the process flow diagram that is converted to mother pronunciation of the outer voice translation according to language environment transform method of the present invention;
Fig. 4 A is three of translation is converted to outer voice according to the mother pronunciation of a language environment transform method of the present invention process flow diagram;
Fig. 4 B is three of the process flow diagram that is converted to mother pronunciation of the outer voice translation according to language environment transform method of the present invention;
Fig. 5 a and Fig. 5 b are the general operation workflow figure according to language environment transform method of the present invention;
Fig. 6 is the block scheme according to the embodiment one of language environment converting system of the present invention;
Fig. 7 is the speech recognition process flow diagram according to the embodiment one of language environment converting system of the present invention;
Fig. 8 is the block scheme according to the embodiment two of language environment converting system of the present invention;
Fig. 9 is the speech recognition process flow diagram according to the embodiment two of language environment converting system of the present invention;
Figure 10 is the block scheme according to the embodiment three of language environment converting system of the present invention;
Figure 11 is the block scheme according to the embodiment four of language environment converting system of the present invention;
Figure 12 is the block scheme according to the embodiment one of language environment conversion equipment of the present invention;
Figure 13 is the block scheme according to the embodiment two of language environment conversion equipment of the present invention;
Figure 14 is the synoptic diagram according to artificial foreign language language environment of the present invention;
Figure 15 is the synoptic diagram according to the wearable device of utilization embodiment one of the present invention;
Figure 16 is the synoptic diagram according to the wearable device of utilization embodiment two of the present invention;
Figure 17 is the synoptic diagram according to the wearable device of utilization embodiment three of the present invention;
Figure 18 is the synoptic diagram according to the wearable device of utilization embodiment four of the present invention;
Figure 19 is the synoptic diagram according to the wearable device of utilization embodiment five of the present invention;
Embodiment
As shown in Figure 1, language environment converting system according to the present invention comprises: mother pronunciation input media 101, mother pronunciation recognition device 102, mother tongue acoustic model 103, foreign language translation device 104, outer voice playing device 105;
Wherein, the mother pronunciation that mother pronunciation input media 101 input mother tongue side are sent, convert mother pronunciation to the mother pronunciation signal, input to mother pronunciation recognition device 102, mother pronunciation recognition device 102 mates mother pronunciation signal templates in mother pronunciation signal and the mother tongue acoustic model 103, produce the mother pronunciation recognition result, foreign language translation device 104 is according to the mother pronunciation recognition result, mother pronunciation translation is converted to equivalent in meaning or close foreign language, and outer voice playing device 105 plays to study side tin with the outer voice of foreign language;
Language environment converting system of the present invention further comprises: outer voice input media 111, outer voice recognition device
Wherein, the outer voice that outer voice input media 111 input study sides send, convert outer voice to outer voice signal, input to outer voice recognition device 112, outer voice recognition device 112 mates outer voice signal and foreign language acoustic model 113 inside and outside voice signal templates, produce outer voice recognition result, native language translation device 114 is according to outer voice recognition result, the translation of outer voice is converted to equivalent in meaning or close mother tongue, and mother pronunciation playing device 115 plays to mother tongue side with the mother pronunciation of mother tongue and listens;
Mother tongue is meant mother tongue or the dialect or the mother tongue of study side, foreign language is meant the mother tongue of study side or a kind of language or the multilingual outside dialect or the mother tongue, as British mother tongue is English, and foreign language is French, German, Italian or the like;
Chinese mother tongue is mandarin or various places dialect or minority language, and the various places dialect can be Guangdong language, Shanghai native language, the south of Fujian Province words ... or the like, minority language can be Tibetan language, Mongolian, strong language, Uighur ... or the like;
Chinese foreign language is the language outside one or more foreign language or this minority language; One or more foreign language are meant the language of country outside the China, can be English, Japanese, French, German, Italian, Russian, Spanish, Korean, Dard ... or the like; Language outside this minority language is for the people of ethnic group, as: mandarin is the language outside Tibetan language, the Mongolian;
Unspecified person model or specific speaker's model are adopted in speech recognition of the present invention;
Automatic speech recognition (ASR) engine of speech recognition employing of unspecified person model and speaker-independent is as automatic speech recognition (ASR) engine of IBM Corporation, automatic speech recognition (ASR) engine of Dragon System company;
The acoustic model that the speech recognition of unspecified person model is adopted can be concealed Markov model;
Specific speaker's model speech recognition is carried out voice registration to acoustic model before requiring the user to use, set up the user voice template model after, just can carry out speech recognition;
Foreign language translation device 104 can be the Text To Speech translating equipment with native language translation device 114; Can adopt the TTS technology; The Text To Speech translating equipment can be a letter-pronunciation converter;
Foreign language translation device 104 can be the phonetic representation mode that a cover has stored foreign language, these expression waies are corresponding with each mother pronunciation recognition result, as: " How are you? " outer voice expression way with " you? " the mother pronunciation recognition result corresponding;
Native language translation device 114 can be the phonetic representation mode that a cover has stored mother tongue, and these expression waies are corresponding with each outer voice recognition result, as: " I am fine, thanks." the mother pronunciation expression way corresponding with the outer voice recognition result of " I ' mvery well, thank you. ";
Below having stored the phonetic representation mode of foreign language can be stored in the single memory by subregion with the phonetic representation mode that stores mother tongue;
Foreign language translation device 104 can be that a shared cover has stored one or more foreign language voice and mother tongue pronunciation expression way with native language translation device 114, and these expression waies are corresponding with each voice identification result, as: with " I am fine, thanks." (identification code: 0005C) with " I ' m very well, thank you. " (identification code: 0005E) be stored together convenient translation sound and the check and correction sound of extracting simultaneously in pairs;
Above phonetic representation mode can adopt true man's expression way of pronouncing, and the true man of mother pronunciation expression way and the true man of the outer voice expression way of pronouncing of pronouncing is corresponding; True man's expression way of pronouncing can be in short or phrase or word or word;
But foreign language translation device 104 and 114 1 bilingual two-way translation devices of native language translation device also can shared multi-lingual multidirectional translaters.
Shown in Fig. 2 A, step 200: mother tongue side is sent mother pronunciation; Step 201: mother pronunciation is imported; Step 202: carry out speech recognition; Step 203: generate the mother pronunciation recognition result; Step 204: by the mother pronunciation recognition result from outer speech data storehouse 207 speech datas that extract equivalent in meaning or close foreign language; Step 205: play the foreign language voice; Step 206: listen for study side; Here the mother pronunciation recognition result service definition that can be employed program is the storage address or the identity code of the speech data of the foreign language equivalent in meaning or close with the input mother pronunciation, and these speech datas can be true man's expression waies of pronouncing.
Shown in Fig. 2 B, step 210: study side sends outer voice; Step 211: with outer voice input; Step 212: carry out speech recognition; Step 213: generate outer voice recognition result; Step 214: the speech data that extracts equivalent in meaning or close mother tongue by outer voice recognition result from mother pronunciation database 217; Step 215: play mother tongue pronunciation; Step 216: listen to mother tongue side; The service definition that outer here voice recognition result can be employed program is the storage address or the identity code of the speech data of the mother tongue equivalent in meaning or close with the outer voice of input, and these speech datas can be true man's expression waies of pronouncing.
As shown in Figure 3A, step 300: mother tongue side is sent mother pronunciation; Step 301: mother pronunciation is imported; Step 302: carry out speech recognition; Step 303: generate the mother pronunciation recognition result; Step 304: generate common text according to the mother pronunciation recognition result; Step 305: according to the equivalent in meaning or close foreign language voice signal of common text generation; Step 306: play the foreign language voice; Step 307: listen for study side.
Shown in Fig. 3 B, step 310: study side sends outer voice; Step 311: with outer voice input; Step 312: carry out speech recognition; Step 313: generate outer voice recognition result; Step 314: generate common text according to outer voice recognition result; Step 315: according to the equivalent in meaning or close mother tongue pronunciation signal of common text generation; Step 316: play mother tongue pronunciation; Step 317: listen to mother tongue side.
Shown in Fig. 4 A, step 400: mother tongue side is sent mother pronunciation; Step 401: mother pronunciation is imported; Step 402: carry out speech recognition; Step 403: generate the mother pronunciation recognition result; Step 404: generate the mother tongue text according to the mother pronunciation recognition result; Step 405: with the mother tongue text translation is equivalent in meaning or close foreign language text; Step 406: according to foreign language text generation foreign language voice signal; Step 407: play the foreign language voice; Step 408: listen for study side.
Shown in Fig. 4 B, step 410: study side sends outer voice; Step 411: with outer voice input; Step 412: carry out speech recognition; Step 413: generate outer voice recognition result; Step 414: generate the foreign language text according to outer voice recognition result; Step 415: with the foreign language text translation is equivalent in meaning or close mother tongue text; Step 416: according to mother tongue text generation mother tongue pronunciation signal; Step 417: play mother tongue pronunciation; Step 418: listen to mother tongue side.
Shown in Fig. 5 a and Fig. 5 b, describe the general operation workflow of language environment transform method of the present invention in detail:
Step 500: when voice outside a mother pronunciation or are imported;
Step 501: disconnect other phonetic entry passage;
Described disconnection phonetic entry passage is meant: do not allow voice enter speech recognition equipment by this passage;
This step effect have following some:
1. when the shared speech recognition engine of a mother pronunciation input channel and foreign language input channel, when mother pronunciation is carried out speech recognition in input, forbid outer voice input, accurately discern to guarantee voice, or outer voice are when speech recognition is carried out in input, forbid the mother pronunciation input, accurately discern to guarantee voice;
2. when the shared speech recognition engine of many mother pronunciation input channels, when wherein mother pronunciation input channel input voice carry out speech recognition, forbid the phonetic entry of other mother pronunciation input channel;
3. when the shared speech recognition engine of voice input channel outside many, when wherein outer voice input channel input voice carry out speech recognition, forbid the phonetic entry of other outer voice input channel;
4. when the shared speech recognition engine of voice input channel outside one or more and one or more mother pronunciation input channel, when wherein phonetic entry passage input voice carry out speech recognition, forbid the phonetic entry of other phonetic entry passage;
5. when the not shared speech recognition engine of female, outer voice identification (as shown in Figure 1), carry out for dialogue both sides speech is replaced in turn, when a side when the speech recognition broadcast is carried out in speech, can forbid the phonetic entry of the other side's phonetic entry passage;
Here, a speech input device is a phonetic entry passage;
Step 502: carry out speech recognition;
Step 503: judge whether speech recognition is successful; If generate this voice identification result, step 504; Otherwise, enter step 513, judge whether it is the mother pronunciation input; If, with the mother tongue side playing alert tones of mother tongue, for example: be mandarin input, send " pardon " prompt tone such as " please speak standard Chinese pronunciation ", step 514A to speech; Otherwise, with the study side playing alert tones of foreign language, for example: be the English input, send " Please say that again " prompt tone, step 514B to speech;
Step 505: judge whether it is that mother pronunciation is discerned successfully; If use mother tongue to input mother pronunciation mother tongue side or check and correction sound all or part of or other mother tongue side broadcast input mother pronunciation, step 506A; Otherwise, with the check and correction sound of foreign language voice outside the outer voice study side of input or all or part of or other study side's broadcast are imported, step 506B;
The effect of playing the check and correction sound of input voice have following some:
1. for input voice side, can know that whether oneself is by correct speech recognition;
2. for all or part of mother tongue side, can know the meaning that a mother tongue side is wherein spoken and expressed;
3. for all or part of study side, can know the meaning of speaking and express in a study side wherein;
4. for other our personnel, when the phonetic recognization rate height is accurate, can continuity express for making speaker, do not need to play the check and correction sound, and only play the check and correction sound, with the meaning of passing on he (she) to speak to he (she) our personnel outside me to speaker;
5. not only can talk with and exchange between mother tongue side and the study side, can make simultaneously to engage in the dialogue between the study side or between the mother tongue side and exchange;
Step 507:, will import voiced translation and be converted to the other side's language according to voice identification result;
Step 508: judge whether it is mother tongue output; If play the mother pronunciation that translates to all or part of mother tongue side, step 509A: otherwise, the outer voice that translate, step 509B play to all or part of study side;
Step 510: when voice that translate when playing, disconnect all or other phonetic entry passage, or this step can be when voice when playing, disconnect all or other phonetic entry passage;
This step effect have following some:
1. during with the loudspeaker plays voice, disconnecting all phonetic entry passages, is to prevent that the voice of playing from re-entering identification and producing broadcast;
2. during with the loudspeaker plays voice, disconnecting other phonetic entry passage, is to prevent that the voice of playing from re-entering the ongoing speech recognition of interference;
3. could import voice after playing, mother tongue side and the dialogue of study side can be carried out smoothly;
Step 511: judge whether speech play finishes; If connect all phonetic entry paths, step 512; Otherwise, continue execution in step 510.
As shown in Figure 6, the embodiment one of language environment converting system of the present invention:
Mother pronunciation input media 101 is used to import the mother pronunciation that mother tongue side is sent;
Outer voice input media 111 is used to import the outer voice that study side sends;
Female, outer voice input media (101,111) can be a microphone;
Phonetic entry channel controller 501 is used to switch mother pronunciation and outer voice input; Mother pronunciation input media 101 is connected phonetic entry channel controller 501 respectively with outer voice input media 111;
Translating equipment 503 connects speech recognition equipment 502; Be used for according to voice identification result, carry out translating between mother tongue and the foreign language; Translating equipment 503 is female, the independent separately translater of foreign language or mother, the shared two-way translation device of foreign language;
Voice output channel controller 504 connects translating equipment 503; Be used for control from outer voice playing device 105 voice outside study side plays, play mother pronunciation to mother tongue side from mother pronunciation playing device 115;
Outer voice playing device 105 connects voice output channel controller 504; Be used for voice outside study side plays;
Mother pronunciation playing device 115 connects voice output channel controller 504; Be used for playing mother pronunciation to mother tongue side;
Female, outer voice playing device (105,115) can be loudspeaker or earphone.
As shown in Figure 7, the speech recognition process flow diagram of Fig. 6 embodiment:
Fig. 6 embodiment speech recognition equipment 502 has only a speech recognition engine, and independently mother tongue acoustic model 103 and foreign language acoustic model 113 before speech recognition, judge that the mother pronunciation input still is outer voice inputs (step 701); Be the mother pronunciation input, voice mated identification (step 702) with the mother tongue acoustic model; Be outer voice input, voice mated identification (step 703) with the foreign language acoustic model; Down to Fig. 5 step 503: judge whether success of speech recognition;
Definite mother pronunciation input media 101 input voice are discerned with mother tongue acoustic model 103 couplings in system, and outer voice input media 111 input voice are discerned with foreign language acoustic model 113 couplings; Perhaps machine judges it is mother pronunciation input or the input of outer voice automatically, and reinstates the sort of acoustic model.
As shown in Figure 8, the embodiment two of language environment converting system of the present invention:
Embodiment two is with embodiment one difference: the acoustic model that mixes of a shared speech recognition engine and mother tongue and foreign language discerned in mother pronunciation identification and outer voice, and before speech recognition, not needing judgement is that mother pronunciation is imported or outer voice are imported; Be the mother pronunciation input, be translated as foreign language; Be outer voice input, be translated as mother tongue; Like this, mother pronunciation input media 101 and outer voice input media 111 can be in mother tongue side and study square tube usefulness, and not denominator, outer voice input media, equally, voice playing device is denominator, outer voice playing device not; Mix acoustic model and be used under the bigger situation of bilingual pronunciation difference, as: mandarin can be with mixing acoustic model with English.
As shown in Figure 9, the speech recognition process flow diagram of Fig. 8 embodiment:
When phonetic entry, speech recognition (step 502) is not all carried out in denominator, outer voice input, down to Fig. 5 step 503: judge whether successfully speech recognition.
As shown in figure 10, the embodiment three of language environment converting system of the present invention:
Embodiment three is with embodiment one, embodiment two difference:
One or more mother pronunciation input medias 101 are connected phonetic entry channel controller 501 respectively with one or more outer voice input medias 111; Phonetic entry channel controller 501 is used for forbidding other speech input device input voice when wherein a speech input device is at the input voice;
One or more outer voice playing devices 105 are connected voice output channel controller 504 respectively with one or more mother pronunciation playing devices 115;
Voice output channel controller 504 is used to control the check and correction sound of outer voice playing device 105 usefulness foreign languages voice outside the outer voice study side of input or all or part of or other study side broadcast and with the foreign language voice side of study playing alert tones and be translated as the outer voice of foreign language with foreign language to all or part of study side's broadcast mother pronunciation outside importing;
Voice output channel controller 504 also be used to control mother pronunciation playing device 115 usefulness mother tongues play mother pronunciation to input mother pronunciation mother tongue side or all or part of or other mother tongue side check and correction sound with mother tongue to importing mother pronunciation mother tongue side playing alert tones and being translated as the mother pronunciation of mother tongue with mother tongue voice outside all or part of mother tongue side broadcast;
If speech recognition is adopted when mixing acoustic model, speech input device and voice playing device are regardless of mother tongue side and use with study side, and general.
As shown in figure 11, the embodiment four of language environment converting system of the present invention:
Embodiment four is with above-mentioned three embodiment difference:
Mother tongue pronunciation identification and foreign language speech recognition be with independently speech recognition engine and acoustic model separately, and translating equipment independently, helps that translation accuracy rate and efficient improve between mother, the foreign language, and female, foreign language two-way translation can carry out simultaneously;
Phonetic entry channel controller 501 is used for control when a mother pronunciation input media is imported voice and carried out speech recognition, forbids the input voice of other mother pronunciation input media or forbids the input voice of other speech input device; Also be used for control when voice input media outside is imported voice and carried out speech recognition, forbid the input voice of other outer voice input media or forbid the input voice of other speech input device;
Voice output channel controller 504 is used to control the check and correction sound of outer voice playing device 105 usefulness foreign languages voice outside the outer voice study side of input or all or part of or other study side broadcast and with the foreign language voice side of study playing alert tones and be translated as the outer voice of foreign language with foreign language to all or part of study side's broadcast mother pronunciation outside importing;
Voice output channel controller 504 also be used to control mother pronunciation playing device 115 usefulness mother tongues play mother pronunciation to input mother pronunciation mother tongue side or all or part of or other mother tongue side check and correction sound with mother tongue to importing mother pronunciation mother tongue side playing alert tones and being translated as the mother pronunciation of mother tongue with mother tongue voice outside all or part of mother tongue side broadcast;
As shown in figure 12, the embodiment one of language environment conversion equipment of the present invention:
Phonetic entry channel controller, speech recognition equipment, translating equipment, storage buffer 508, voice output channel controller are combined into a language conversion module 506, and are combined into main frame 505 with other functional unit { as power supply unit, function key unit, audio power amplifier unit (unreceipted) };
One or more mother pronunciation input medias 101 are connected main frame 505 respectively with one or more outer voice input medias 111;
One or more outer voice playing devices 105 are connected main frame 505 respectively with one or more mother pronunciation playing devices 115;
As shown in figure 13, the embodiment two of language environment conversion equipment of the present invention:
One or more mother pronunciation input medias 101 and one or more outer voice input medias 111 are connected wireless transmitter 507 separately respectively;
One or more outer voice playing devices 105 and one or more mother pronunciation playing devices 115 are connected wireless transmitter 507 separately respectively;
Wireless telecommunications are adopted in the voice signal transmission between main frame 505 and mother pronunciation input media 101, outer voice input media 111, outer voice playing device 105, the mother pronunciation playing device 115;
But the embodiment one and embodiment two integrated uses of language environment conversion equipment, direct connected mode (as: lead is connected) is adopted in the voice signal transmission between part speech input device, voice playing device and the main frame 505, and voice signal transmits the employing wireless communication transmission between part speech input device, voice playing device and the main frame 505 in addition;
Wireless telecommunications can be adopted " bluetooth " communication, radio-frequency communication, radio communication or infrared-ray communication.
As shown in figure 14, the objective of the invention is: the mother pronunciation translation that the mother tongue side of saying mother tongue in the mother tongue language environment is sent is converted to equivalent in meaning or close outer voice, the people who plays to foreign language studying listens, the outer voice translation of again people who learns foreign languages being sent is converted to equivalent in meaning or close mother pronunciation, plays to mother tongue side and listens; In the mother tongue language environment, the people of foreign language studying can engage in the dialogue with the mother tongue side that speaks one's mother tongue and exchange with foreign language by this device.
As shown in figure 15, utilization embodiment one of the present invention:
Study square toes wearable device comprises:
Outer voice playing device (earphone) 105 is used for voice outside study side plays;
Mother pronunciation input media (MIC) 101 is used to import the mother pronunciation that mother tongue side is sent;
Outer voice input media (MIC) 111 is used to import the outer voice that study side sends;
Mother pronunciation playing device (loudspeaker) 115 is used for playing mother pronunciation than loud noise to mother tongue side;
Study square toes wearable device can be used for the mother pronunciation that the sense of hearing and the mother tongue side of study side are sent is kept apart; Purpose is to make study side not hear that mother tongue side says that sound insulation has the physics soundproofing, with concrete sound barrier sound insulation (as: sound insulation earphone cover); Also have the electrical isolation method, when mother tongue side was sent voice, outer voice playing device (earphone) 105 sends a kind of slight sound made study side not hear the words that mother tongue side is said;
This study square toes wearable device can be used for study side and talks face to face with mother tongue side, as: do shopping in the shop, and friend talk etc.
As shown in figure 16, utilization embodiment two of the present invention:
Mother tongue square toes wearable device comprises:
Mother pronunciation input media (MIC) 101 is used to import the mother pronunciation that mother tongue side is sent;
Outer voice playing device (loudspeaker) 105 is used for than loud noise voice outside study side plays;
Mother pronunciation playing device (earphone) 115 is used for playing mother pronunciation to mother tongue side;
Outer voice input media (MIC) 111 is used to import the outer voice that study side sends;
Mother tongue square toes wearable device, the mother pronunciation that can be used for mother tongue side is sent is kept apart with the sense of hearing of study side; Purpose is to make study side not hear that mother tongue side says that sound insulation has the physics soundproofing, with concrete sound barrier sound insulation (as: special-purpose sound insulation respirator, in be furnished with MIC);
This mother tongue square toes wearable device can be used for child, child, pupil, and mother tongue side is said foreign language with mother tongue to child, child, pupil, from little a foreign language language environment is just arranged.
As shown in figure 17, utilization embodiment three of the present invention:
A mother tongue square toes wearable device comprises:
Mother pronunciation input media (MIC) 101 is used to import the mother pronunciation that mother tongue side is sent;
Mother pronunciation playing device (earphone) 115 is used for playing mother pronunciation to mother tongue side;
One or more study square toes wearable devices, each study square toes wearable device comprises:
Outer voice playing device (earphone) 105 is used for voice outside study side plays;
Outer voice input media (MIC) 111 is used to import the outer voice that study side sends;
This utilization embodiment can be used for imparting knowledge to students between teacher and the student, as kindergarten, school etc.
As shown in figure 18, utilization embodiment four of the present invention:
A study square toes wearable device comprises:
Outer voice playing device (earphone) 105 is used for voice outside study side plays;
Outer voice input media (MIC) 111 is used to import the outer voice that study side sends;
One or more mother tongue square toes wearable devices, each mother tongue square toes wearable device comprises:
Mother pronunciation input media (MIC) 101 is used to import the mother pronunciation that mother tongue side is sent;
Mother pronunciation playing device (earphone) 115 is used for playing mother pronunciation to mother tongue side;
This utilization embodiment can be used for family, as between child and father, the mother with female, foreign language talk, formation family foreign language language environment etc.
As shown in figure 19, utilization embodiment five of the present invention:
One or more mother tongue square toes wearable devices, each mother tongue square toes wearable device comprises:
Mother pronunciation input media (MIC) 101 is used to import the mother pronunciation that mother tongue side is sent;
Mother pronunciation playing device (earphone) 115 is used for playing mother pronunciation to mother tongue side;
Mother tongue square toes wearable device can be the Bluetooth earphone device of band MIC;
One or more study square toes wearable devices, each study square toes wearable device comprises:
Outer voice playing device (earphone) 105 is used for voice outside study side plays;
Outer voice input media (MIC) 111 is used to import the outer voice that study side sends;
Study square toes wearable device can be the Bluetooth earphone device of band MIC;
This utilization embodiment can be used for talking between a plurality of study sides and a plurality of mother tongue side etc., talks formation family foreign language language environment etc. with mother, foreign language as between: two children and father, the mother.
When the above study square toes wearable device and described mother tongue square toes wearable device can be discerned the dark chorus model of a shared speech recognition engine and mother, foreign language by female, outer switch key or mother, outer voice, can reach learn the square toes wearable device and mother tongue square toes wearable device general.
The above study square toes wearable device and described mother tongue square toes wearable device are referred to as a wearable device, and described wearable device is meant and speech input device can be fixed on the mouth and voice playing device is fixed in one's ear device; Wearable device also can be the device that MIC is arranged on Bluetooth earphone device or the earphone plug of band MIC or Headphone device that has MIC or the earphone cord.
The present invention describes by above-mentioned specific embodiment, it will be appreciated by those skilled in the art that, without departing from the present invention, can also carry out various conversion and be equal to alternative the present invention.In addition, at particular condition or concrete condition, can make various modifications to the present invention, and not depart from the scope of the present invention.Therefore, the present invention is not limited to disclosed specific embodiment, and should comprise the whole embodiments that fall in the claim scope of the present invention.
Claims (25)
1, a kind of language environment transform method comprises:
The mother pronunciation that mother tongue side is sent is imported;
Described mother pronunciation is carried out speech recognition, produce described mother pronunciation recognition result;
According to described mother pronunciation recognition result, described mother pronunciation is translated as foreign language;
The outer voice of described foreign language are played to study side to be listened.
2. language environment transform method according to claim 1 is characterized in that, also comprises:
The outer voice input of the described foreign language that described study side is sent;
Described outer voice are carried out speech recognition, produce described outer voice recognition result;
According to described outer voice recognition result, described outer voice are translated as described mother tongue;
The mother pronunciation of described mother tongue is played to described mother tongue side listens.
3. language environment transform method according to claim 1 is characterized in that,
When a described mother pronunciation is imported, disconnect other phonetic entry passage.
4. language environment transform method according to claim 2 is characterized in that,
When one described outside voice when input, disconnect other phonetic entry passage.
5. language environment transform method according to claim 1, it is characterized in that, judge whether a described mother pronunciation is carried out speech recognition successful, when successful, play the check and correction sound of described mother pronunciation to described mother tongue side or all or part of or other mother tongue side with described mother tongue, otherwise, with described mother tongue to described mother tongue side playing alert tones.
6. language environment transform method according to claim 2, it is characterized in that, judge whether described outer voice carry out speech recognition successful, when successful, with described foreign language to described study side or all or part of or other study side play described outside the check and correction sound of voice, otherwise, with described foreign language to described study side playing alert tones.
7. language environment transform method according to claim 1 is characterized in that, carries out speech recognition when success when a described mother pronunciation, and described mother pronunciation is translated as described foreign language, and the outer voice of described foreign language are played to all or part of described study side tin.
8. language environment transform method according to claim 2 is characterized in that, when one described outside voice carry out speech recognition when success, described outer voice are translated as described mother tongue, the mother pronunciation of described mother tongue is played to all or part of described mother tongue side listens.
9. according to each described language environment transform method of claim 1-8, it is characterized in that, described mother tongue is meant mother tongue or the dialect or the mother tongue of described study side, and described foreign language is meant the described mother tongue of described study side or a kind of language or the multilingual outside described dialect or the described mother tongue.
10. according to each described language environment transform method of claim 1-8, it is characterized in that, for Chinese, described mother tongue is meant mandarin or various places dialect or minority language, and described foreign language is meant the language outside one or more foreign language or this minority language.
11. a language environment converting system comprises:
The mother pronunciation input media is used to import the mother pronunciation that mother tongue side is sent, and converts described mother pronunciation to described mother pronunciation signal;
The mother pronunciation recognition device is used for described mother pronunciation signal templates in described mother pronunciation signal and the mother tongue acoustic model is mated, and produces described mother pronunciation recognition result;
The foreign language translation device is used for according to described mother pronunciation recognition result described mother pronunciation being translated as foreign language;
Outer voice playing device is used for outer voice with described foreign language and plays to study side and listen.
12. language environment converting system according to claim 11 is characterized in that, also comprises:
Outer voice input media is used to import the outer voice that described study side sends, and converts described outer voice to described outer voice signal;
Outer voice recognition device is used for described outer voice signal template in described outer voice signal and the foreign language acoustic model is mated, and produces described outer voice recognition result;
The native language translation device is used for according to described outer voice recognition result described outer voice being translated as described mother tongue;
The mother pronunciation playing device is used for mother pronunciation with described mother tongue and plays to described mother tongue side and listen.
13. according to claim 11,12 described language environment converting systems, it is characterized in that, also comprise:
The phonetic entry channel controller, be used for when a described mother pronunciation input media or one described outside the voice input media when carrying out phonetic entry, forbid other speech input device input voice;
The voice output channel controller, be used to control described outer voice playing device with the check and correction sound of described foreign language voice outside the outer voice study side of input or all or part of or other study side broadcast are described and with described foreign language to import described outside the voice side of study playing alert tones and be translated as the outer voice of described foreign language with described foreign language to the described mother pronunciation of all or part of study side's broadcast;
Described voice output channel controller, also be used to control described mother pronunciation playing device plays described mother pronunciation to input mother pronunciation mother tongue side or all or part of or other mother tongue side with described mother tongue check and correction sound with described mother tongue to importing described mother pronunciation mother tongue side playing alert tones and being translated as the mother pronunciation of described mother tongue with described mother tongue voice outside all or part of mother tongue side broadcast is described.
14. language environment converting system according to claim 11, it is characterized in that, described foreign language translation device is the phonetic representation mode that a cover has stored described foreign language, these expression waies are corresponding with each described mother pronunciation recognition result, or described foreign language translation device is the Text To Speech translating equipment.
15. language environment converting system according to claim 12, it is characterized in that, described native language translation device is the phonetic representation mode that a cover has stored described mother tongue, these expression waies are corresponding with each described outer voice recognition result, or described native language translation device is the Text To Speech translating equipment.
16. according to claim 11,12 described language environment converting systems, it is characterized in that, described foreign language translation device and described native language translation device are that a cover has stored described foreign language or comprised the multiple foreign language of described foreign language and the phonetic representation mode of described mother tongue, and these expression waies are corresponding with each described outer voice recognition result and/or each described mother pronunciation recognition result; Or described foreign language translation device and described native language translation device are the Text To Speech translating equipments.
17. according to claim 11,12 described language environment converting systems, it is characterized in that described mother pronunciation recognition device and the shared speech recognition engine of described outer voice recognition device and/or the acoustic model that mixes of a shared described mother tongue and described foreign language.
18. according to each described language environment converting system of claim 11-17, it is characterized in that, described mother tongue is meant mother tongue or the dialect or the mother tongue of described study side, and described foreign language is meant the described mother tongue of described study side or a kind of language or the multilingual outside described dialect or the described mother tongue.
19. according to each described language environment converting system of claim 11-17, it is characterized in that, for Chinese, described mother tongue is meant mandarin or various places dialect or minority language, and described foreign language is meant the language outside one or more foreign language or this minority language.
20. a language environment conversion equipment comprises:
One or more mother pronunciation input medias are used to import the mother pronunciation that mother tongue side is sent, and convert described mother pronunciation to described mother pronunciation signal;
One or more outer voice playing devices are used for voice outside study side plays;
Each described mother pronunciation input media is connected main frame respectively with each described outer voice playing device;
Described main frame is used to receive the described mother pronunciation signal of described mother pronunciation input media, and described mother pronunciation translation is converted to described foreign language, and the outer voice of described foreign language are played to described study side tin from all or part of described outer voice playing device.
21. language environment conversion equipment according to claim 20 is characterized in that, also comprises:
One or more outer voice input medias are used to import the outer voice that described study side sends, and convert described outer voice to described outer voice signal;
One or more mother pronunciation playing devices are used for playing mother pronunciation to described mother tongue side;
Each described outer voice input media is connected described main frame respectively with each described mother pronunciation playing device;
Described main frame also is used to receive the described outer voice signal of described outer voice input media, and described outer voice translation is converted to described mother tongue, the mother pronunciation of described mother tongue is played to described mother tongue side from all or part of described mother pronunciation playing device listen.
22. according to claim 20,21 described language environment conversion equipments, it is characterized in that,
Described main frame comprises wireless transmitter, is used for voice signal wireless telecommunications between described main frame and described mother pronunciation input media and/or described outer voice playing device and/or described outer voice input media and/or the described mother pronunciation playing device;
All or part of described mother pronunciation input media connects wireless transmitter, is used for voice signal wireless telecommunications between described mother pronunciation input media and the described main frame;
All or part of described outer voice input media connects wireless transmitter, is used for voice signal wireless telecommunications between described outer voice input media and the described main frame;
All or part of described outer voice playing device connects wireless transmitter, is used for voice signal wireless telecommunications between described outer voice playing device and the described main frame;
All or part of described mother pronunciation playing device connects wireless transmitter, is used for voice signal wireless telecommunications between described mother pronunciation playing device and the described main frame;
23. according to each described language environment conversion equipment of claim 20-22, it is characterized in that, described mother tongue is meant mother tongue or the dialect or the mother tongue of described study side, and described foreign language is meant the described mother tongue of described study side or a kind of language or the multilingual outside described dialect or the described mother tongue.
24. according to each described language environment conversion equipment of claim 20-22, it is characterized in that, for Chinese, described mother tongue is meant mandarin or various places dialect or minority language, and described foreign language is meant the language outside one or more foreign language or this minority language.
25. according to each described language environment conversion equipment of claim 20-24, it is characterized in that, comprise one or more wearable devices.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA200610080052XA CN101034498A (en) | 2006-03-07 | 2006-04-29 | Language environment transform method, system and device |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200610067718.8 | 2006-03-07 | ||
| CN200610067718 | 2006-03-07 | ||
| CNA200610080052XA CN101034498A (en) | 2006-03-07 | 2006-04-29 | Language environment transform method, system and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101034498A true CN101034498A (en) | 2007-09-12 |
Family
ID=38731034
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA200610080052XA Pending CN101034498A (en) | 2006-03-07 | 2006-04-29 | Language environment transform method, system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101034498A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103038816A (en) * | 2010-10-01 | 2013-04-10 | 三菱电机株式会社 | Speech recognition device |
| CN103179481A (en) * | 2013-01-12 | 2013-06-26 | 德州学院 | Earphone capable of improving English listening comprehension of user |
| CN103699519A (en) * | 2013-12-04 | 2014-04-02 | 何玉春 | Intelligentized language management system |
| CN104598443A (en) * | 2013-10-31 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Language service providing method, device and system |
| CN105208479A (en) * | 2015-10-27 | 2015-12-30 | 黑龙江聚拢华玺智能科技有限公司 | Bluetooth earphone with automatic translation function |
| CN105825730A (en) * | 2016-06-06 | 2016-08-03 | 袁亚蒙 | Bilingual broadcasting system for foreign language learning |
| CN106951417A (en) * | 2017-05-05 | 2017-07-14 | 李宗展 | Recognize the multi-lingual inter-translation method and portable machine of Chinese dialects |
| CN112560512A (en) * | 2021-02-24 | 2021-03-26 | 南京酷朗电子有限公司 | Intelligent voice analysis and auxiliary communication method for foreign language learning |
| CN112669654A (en) * | 2021-01-05 | 2021-04-16 | 李京肽 | Foreign language learning bilingual broadcasting device and system |
| CN112991845A (en) * | 2020-07-20 | 2021-06-18 | 律世刚 | Foreign language learning device |
| CN113160633A (en) * | 2021-03-24 | 2021-07-23 | 无锡职业技术学院 | Intelligent voice training equipment with interaction function for Japanese teaching |
-
2006
- 2006-04-29 CN CNA200610080052XA patent/CN101034498A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103038816A (en) * | 2010-10-01 | 2013-04-10 | 三菱电机株式会社 | Speech recognition device |
| CN103038816B (en) * | 2010-10-01 | 2015-02-25 | 三菱电机株式会社 | Speech recognition device |
| CN103179481A (en) * | 2013-01-12 | 2013-06-26 | 德州学院 | Earphone capable of improving English listening comprehension of user |
| CN104598443A (en) * | 2013-10-31 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Language service providing method, device and system |
| CN103699519A (en) * | 2013-12-04 | 2014-04-02 | 何玉春 | Intelligentized language management system |
| CN105208479A (en) * | 2015-10-27 | 2015-12-30 | 黑龙江聚拢华玺智能科技有限公司 | Bluetooth earphone with automatic translation function |
| CN105825730A (en) * | 2016-06-06 | 2016-08-03 | 袁亚蒙 | Bilingual broadcasting system for foreign language learning |
| CN106951417A (en) * | 2017-05-05 | 2017-07-14 | 李宗展 | Recognize the multi-lingual inter-translation method and portable machine of Chinese dialects |
| CN112991845A (en) * | 2020-07-20 | 2021-06-18 | 律世刚 | Foreign language learning device |
| CN112669654A (en) * | 2021-01-05 | 2021-04-16 | 李京肽 | Foreign language learning bilingual broadcasting device and system |
| CN112560512A (en) * | 2021-02-24 | 2021-03-26 | 南京酷朗电子有限公司 | Intelligent voice analysis and auxiliary communication method for foreign language learning |
| CN113160633A (en) * | 2021-03-24 | 2021-07-23 | 无锡职业技术学院 | Intelligent voice training equipment with interaction function for Japanese teaching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101034498A (en) | Language environment transform method, system and device | |
| CN1228762C (en) | Method, module, device and server for voice recognition | |
| CN1238833C (en) | Voice idnetifying device and voice identifying method | |
| CN101901599B (en) | System and method for rapid prototyping of existing speech recognition solutions in different languages | |
| CN101046960A (en) | Apparatus and method for processing voice in speech | |
| CN100347741C (en) | Mobile speech synthesis method | |
| CN1242376C (en) | Sound recognition system, device, sound recognition method and sound recognition program | |
| CN1941077A (en) | Apparatus and method speech recognition of character string in speech input | |
| CN1602483A (en) | Real time translator and method of performing real time translation of a plurality of spoken word languages | |
| CN1253812C (en) | Information processing apparatus and information processing method | |
| CN1409527A (en) | Terminal device, server and voice identification method | |
| CN1679371A (en) | Microphone and communication interface system | |
| CN1183510C (en) | Method and device for recognizing acoustic language according to base sound information | |
| CN1171396C (en) | Speech voice communication system | |
| CN1277180C (en) | Apparatus and method for adapting audio signal | |
| CN1842788A (en) | Dialog supporting apparatus | |
| CN1728816A (en) | Information-processing apparatus, information-processing methods, recording mediums, and programs | |
| CN1879147A (en) | Text-to-speech method and system, computer program product therefor | |
| CN1685698A (en) | Video telephone interpretation system and video telephone interpretation method | |
| CN1316083A (en) | Automated language assessment using speech recognition modeling | |
| CN1311881A (en) | Language conversion rule preparing device, language conversion device and program recording medium | |
| CN101060553A (en) | Communication system, information processing device, information processing method, and program | |
| CN1601604A (en) | Speaking period detection device and method, and speech information recognition device | |
| CN1975857A (en) | Conversation control apparatus | |
| CN1119760C (en) | Natural language processing device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |