37results about How to "Correct pronunciation" patented technology

The invention belongs to learning appliance technology field, and relates to an electronic teaching method for deaf people to learn speaking, including: audio-video data and time synchronization information thereof during the period of learners' pronunciation practicing, are obtained through a microphone and a camera; audio feature parameters are extracted; visual features related to shapes of mouth are extracted; the extracted audio feature parameters are compared with corresponding feature parameters pre-stored in a feature parameter template library of standard pronunciation, and are classified so as to determine whether the learners' pronunciation is correct; if the learners' pronunciation is greatly different from that in the feature parameter template library of standard pronunciation, the audio features and the visual features related to shapes of mouth of the learners are compared with that in the feature parameter template library of common wrong pronunciation so as to determine that the errors of the learners belong to which types of the common errors, the comparison between wrong pronunciation manners of the learners and standard pronunciation manners being indicated through images, animations and video content. The method provided in the invention can automatically analyze whether the learners' pronunciation is standard, and correct errors, thereby basically requiring no intervention of teaching staffs in a learning process.

The present invention is user's interface, system and method for automatically marking phonetic symbol to correct pronunciation. Graphic interface is utilized in comparing and displaying the difference of the language learner and the teacher in pronunciation to correct pronunciation, and the computer system includes a user's interface and system. After the user provides one text character string and corresponding pronunciation signal, the present invention will mark corresponding phonetic symbols in corresponding sections and give the difference of the language learner and the teacher in the sound signals, such as pronunciation, pitch, strength, length, etc. before giving score and improvement recommendation.

The present disclosure relates to a foreign language teaching evaluation information generating method, a foreign language teaching evaluation information generating device, an electronic apparatus, and a storage medium. The method includes the following steps that: foreign language test information is outputted, video signals collected by a video capture device are detected, video picture information and audio information in the video signals are extracted; the lips of a user in the video picture information are positioned, and the mouth shape features of the lips of the user are captured; pronunciation information corresponding to the foreign language test information is matched with information in a pre-established foreign language test information and pronunciation information model, wherein the pronunciation information contains standard pronunciations and standard mouth shape features; and the first feature deviation value of the deviation of the mouth shape features of the lipsof the user from the standard mouth shape features which are obtained by means matching is calculated, and teaching evaluation information is generated according to the first feature deviation value.According to the method of the invention, the evaluation of foreign language teaching is realized on the basis of the positioning and comparison of the mouth shape features in the foreign language test information.

Disclosed are methods for disambiguating an input phrase or group of words. An implementation may include receiving a phrase as an input to a processor. The received phrase may be presented on a display device. The received phrase may be determined to be ambiguous based on a threshold uncertainty in either a definition or a pronunciation related to the phrase. An indication may be provided that a word in the phrase is the cause of the ambiguity. A menu of words with each word incorporating at least one diacritic mark to a word in the received phrase to disambiguate the received phrase may be presented. A word from the menu of words may be selected and presented on the display device.

Provided are a foreign language learning apparatus and method using a function of reading an input sentence in voice via a Text To Speech (TTS) engine. The foreign language learning apparatus and method correct pronunciation through sentence input. The foreign language learning apparatus includes a sentence input unit for receiving a first sentence from a user; a linked letter detection unit for detecting at least one letter corresponding to at least one linking rule; a linked letter removal unit for removing the letter and generating a second sentence by inserting a linking code; a partial waveform generation unit for generating one or more partial waveforms using the TTS engine; an input waveform generation unit for converting a voice corresponding to the first sentence into an input waveform; and a matching degree calculation unit for calculating a matching degree and a partial matching degree.

The invention discloses an English pronunciation matching correction system. The system comprises a standard pronunciation acquisition module, a test pronunciation acquisition module, an information storage module, a comparison processing module, an information export module, an information display module and a sound module, wherein the output end of the standard pronunciation acquisition module is in signal connection with the input end of the information storage module; the output end of the test pronunciation acquisition module is in signal connection with the input end of the information storage module; the output end of the information storage module is in signal connection with the input end of the comparison processing module; the output end of the comparison processing module is insignal connection with the input end of the information export module; the output end of the information export module is in signal connection with the input end of the information display module andthe input end of the sound module. The English pronunciation matching correction system can be used for detecting pronunciation conditions of students from multiple aspects, so that mastering conditions of the students in various aspects can be conveniently and clearly observed, and later-stage key enhancement of correction and extra tutoring can be facilitated.

The invention discloses a spoken English learning machine based on audios and videos. The spoken English learning machine comprises a central processing unit, a database, a touch screen, a loudspeaker, a somatosensory camera and an audio sampling unit, wherein the database, the touch screen and the loudspeaker are connected with the central processing unit. The somatosensory camera is further connected with the central processing unit through a video processing unit; and the audio sampling unit is further connected with the central processing unit through an audio processing unit. By means of the spoken English learning machine, a user can conveniently and effectively learn the spoken English; and the mouth shape and pronunciation are corrected.

The invention discloses a method and an apparatus for generating and displaying lyrics, an electronic device and a storage medium, and belongs to the technical field of the internet. The method comprises the steps of acquiring the lyrics of a target song and an audio file of the target song; according to a to-be-labeled character in a plurality of characters in the lyrics and an audio clip corresponding to the plurality of the characters in the audio file, determining candidate pronunciations of the to-be-labeled character; if the to-be-labeled character has a candidate pronunciation, determining the candidate pronunciation as a corresponding pronunciation of the to-be-labeled character in the target song; if the to-be-labeled character has at least two candidate pronunciations, determining the candidate pronunciations semantically matched with the to-be-labeled character as corresponding pronunciations of the to-be-labeled character in the target song; and generating a first lyric file of the target song according to the plurality of the characters and the corresponding pronunciations of the to-be-labeled character in the target song. When the lyrics are displayed subsequently, the pronunciations can be synchronously displayed, so that a user can be guaranteed to sing the pronunciations of all the characters correctly.

The embodiment of the invention provides a pronunciation correction system. The system comprises: a test module configured to output test content determined based on user learning data and collect first test data input by a user according to the test content, the first test data comprising facial image data and voice data; and a pronunciation correction module which is configured to extract user pronunciation characteristics from the first test data, match corresponding pronunciation correction strategies and feed back pronunciation correction content to the user based on the pronunciation correction strategies, and the pronunciation correction content is used for indicating pronunciation difference types and the corresponding pronunciation correction strategies. The targeted pronunciationcorrection strategy is obtained based on the user test data, and the corresponding pronunciation correction content is matched, so that targeted pronunciation correction feedback is realized, the pronunciation problem of the user can be corrected, the pronunciation correction effect is improved, and the learning experience of the user is improved. In addition, the invention further provides a language pronunciation correction method, a medium and computing equipment.

The invention discloses a method for inputting Chinese characters with sound and tone definition by using simplified pinyin, comprising the following steps: as for a pinyin formed by an initial consonant and a final, a standard keyboard is used for inputting an initial consonant character and then inputting a final character after inputting the initial consonant character, or as for a pinyin formed by a single final, the standard keyboard is used for inputting a single final character, wherein a vowel character on the keyboard is defined to be a vowel letter of light tone or first tone after the initial consonant character or the single final character is input; the initial consonant character on the keyboard is defined to be a vowel letter of second tone, third tone and fourth tone afterthe initial consonant character or the single final character is input; and then the vowel character and/or the initial consonant character which is newly defined is input after the initial consonantcharacter or the single final character is input, therefore, the final and a tone are combined to form a whole body to accurately pronounce and cause the Chinese characters to be fast and accurately input, and even people who can not completely accurately recognize Chinese character fonts and strokes are convenient to use the pinyin.

The invention provides a storage and retrieval method of language resource audio data.The storage method comprises the steps that voice, explanatory texts, images and cartoons of multiple words are composited into an audio video to be integrally saved, and a playing tool with retrieving and playing functions is built for the audio video, so that the playing tool can perform quick retrieving and playing of the words on multiple media.According to the method, the language resource audio data is processed in the mode that voice data is adopted and combined with the corresponding explanatory texts, images and cartoons, and therefore explanation for the voice is more accurate; the voice data and the corresponding explanatory texts, images and cartoons are composited into the video to be stored, the video can be propagated in the different media such as a computer, a mobile phone, a network and a television, and meanwhile the data is not prone to be modified by people; after the voice data and the corresponding explanatory texts, images and cartoons are composited into the video to be stored, the simple retrieving and playing tool can be made for the computer, the mobile phone and the like, therefore, the words are retrieved and played in the computer and the mobile phone, the retrieving speed is high, and a learner can use the tool very conveniently.

A device for generating a speech video according to an embodiment has one or more processor and a memory storing one or more programs executable by the one or more processors, and the device includes a video part generator configured to receive a person background image of a person and generate a video part of a speech video of the person; and an audio part generator configured to receive text, generate an audio part of the speech video of the person, and provide speech-related information occurring during the generation of the audio part to the video part generator.

The invention provides a method for identifying all languages by voice and inputting individual characters by voice. The invention is characterized by representing m inhomogeneities with a group of m unknown or known different monotones; pronouncing common single words once; converting the pronunciation of each single word into a linearity preestimate coding cepstrum matrix; classifying the common words into one type in m types by a bayesian classification method or a distance classification method; looking for F most similar unknown monotones from the m unknown monotones by the bayesian classification method or the distance classification method after a user pronounces a single word tone; and arranging all single words according to the degree of similarity and letters (or stroke number) of the single word to be pronounced in F types represented by the F similar unknown monotones; and the words required can be found quickly after the user pronounced. The invention has the advantages that the method is simple, a sample is not required, typewriting is not required, each person can be qualified, the words with non-standard pronunciation or mispronunciation also can be input, the speed is rapid, and the accuracy rate is high.

The invention discloses a text phonetic notation method, electronic equipment and a storage medium. The method comprises the steps: carrying out the matching of an obtained to-be-phonetic notation text with a preset polyphone list, and recognizing a target polyphone contained in the to-be-phonetic notation text according to a matching result; acquiring context information of the target polyphone in the text to be subjected to phonetic notation, and generating a prediction feature vector corresponding to the target polyphone according to the context information; querying a polyphone model corresponding to the target polyphone from a polyphone model set obtained by pre-training, and inputting the prediction feature vector into the queried polyphone model; and performing phonetic notation on the target polyphone according to an output result of the polyphone model. According to the method, the pronunciation of the polyphone can be accurately predicted by fully utilizing the context information of the polyphone, and the labeling accuracy is remarkably improved.

The application relates to an electronic musical instrument. A current sensor group among all sensor groups is triggered to work and a first signal is emitted; when a corresponding first return signalis received, a first beat distance is obtained according to the receiving time of the first return signal and emission time of the first signal; a second beat distance is obtained based on receivingtime of a second return signal and emission time of a second signal; on the basis of the first beat distance, the second beat distance, and a preset threshold value, a beat speed is obtained and thusthe sound that has a volume corresponding to the beat speed and has the tone corresponding to an identity label of a non-contact sensor receiving the first return signal is made. When the timing length reaches a preset period of time, a next sensor group among all sensor groups is used as a current sensor group and execution the work of triggering the current sensor group is done again, so that all sensor groups are triggered in turn. Therefore, a problem that the interference is easy to cause when all sensors work simultaneously is solved; and the sensing accuracy is improved.

The invention relates to a personal handphone system and photovoltaic charging Chinese handwriting palmtop learning machine, which relates to a personal handphone system and photovoltaic charging palmtop learning machine. The personal handphone system and photovoltaic charging Chinese handwriting palmtop learning machine comprises a personal handphone system body, wherein power switch keystrokes are arranged on the personal handphone system body; a silicon solar panel is arranged on the top of the personal handphone system body; a Chinese handwriting recognition intelligent module circuit is electrically connected with a Chinese-English translation engine circuit; and the recognition range comprises Chinese, English and various symbols. The personal handphone system and photovoltaic charging Chinese handwriting palmtop learning machine has the function of intelligent stroke connection, does not limit stroke orders, can quickly and accurately recognize even cramped handwriting, realizes free handwriting, is very convenient to learn Chinese and input Chinese and English through handwriting, strengthens the memory effect of handwriting thought, makes voice be incapable of becoming a communication barrier, uses environment-friendly solar photovoltaic power, has a compact structure, and is convenient to carry.

The invention discloses an autonomic learning intelligent adjustment headgear including: a headgear body, and a near-infrared collection module, a control circuit, a bone conduction earphone module and a power supply, which are installed on the headgear body. The near-infrared collection module includes a plurality of infrared sensors, which are uniformly distributed on the inner side of the headgear body in order to collect the concentrations of oxyhemoglobin and deoxyhemoglobin in cerebral cortex at prefrontal lobe of human body. The control circuit is connected to the near-infrared collection module for receiving the concentrations of the oxyhemoglobin and deoxyhemoglobin, is connected with the bone conduction earphone module, and controls the bone conduction earphone module to make different sounds according to the concentrations of the oxyhemoglobin and deoxyhemoglobin. The bone conduction earphone module is installed on the lower end of the headgear body to contact with the headof a user and send sounds. The power supply is used for supplying power. The autonomic learning intelligent adjustment headgear can control the bone conduction earphone module to make different soundsin order to alleviate fatigue or over-excitation of brain, thus regulating learning state.