30 results about "Speech reading" patented technology

An Internet accessed server that on demand downloads and activates text-to-speech program elements to a subscriber's computer. Program elements are customized to match the operating system of the subscriber's computer. Upon termination of the text-to-speech session, the server deactivates all program elements and the subscriber becomes free to reinitiate over the Internet the text-to-speech program on the same or another computer system.

There is disclosed a method and system for preparing a document to be read by a text-to-speech reader. The method can include identifying two or more voice types available to the text-to-speech reader, identifying the text elements within the document, grouping related text elements together, and classifying the text elements according to voice types available to the text-to-speech reader. The method of grouping the related text elements together can include syntactic and intelligent clustering. The classification of text elements can include performing latent semantic analysis on the text elements and characteristics of the available voice types.

The invention discloses a voice reading device and a cellphone which uses the voice reading device to realize the voice reading function of the cellphone. The voice reading device comprises a text gaining module for gaining text of text format, a text recognition module for gaining text of text format from the text gaining module and gaining text information of digital format, a voice switch module for gaining text information of digital format from the text recognition module, and switching the text information to voice information, a voice broadcast module for broadcasting the voice information which is generated by the voice switch module. Adopting the technical proposal of the invention, text content which is photographed or downloaded is broadcasted by pronunciation devices of the cellphone through the network interface and the photo function of the cellphone. The invention has extremely extensive application prospect, in particular to white-collars who work for a long time before a computer, and blur-collars, students, the old aged, travelers, and visual-disables whose jobs are not affected by the listening.

A system and method for using semantic analysis to configure a voice reader is presented. A text file includes a plurality of text blocks, such as paragraphs. Processing performs semantic analysis on each text block in order to match the text block's semantic content with a semantic identifier. Once processing matches a semantic identifier with the text block, processing retrieves voice attributes that correspond to the semantic identifier (i.e. pitch value, loudness value, and pace value) and provides the voice attributes to a voice reader. The voice reader uses the text block to produce a synthesized voice signal with properties that correspond to the voice attributes. The text block may include semantic tags whereby processing performs latent semantic indexing on the semantic tags in order to match semantic identifiers to the semantic tags.

The invention belongs to the field of educational informatization, and provides a voice robot device for assisting primary school Chinese vocabulary learning and a working method thereof. The device of the present invention includes a speech recognition module, an intelligent retrieval module, and a speech synthesis module; the speech recognition module is used to process students' speech input, that is, input specified words, convert the input speech into text information, and feed back recognition results to students, and The result is passed to the intelligent retrieval module; the intelligent retrieval module automatically combines the local database and the network search results to match the returned data according to the speech recognition result; the speech synthesis module is used to convert the text into voice reading. The present invention allows students to retrieve information such as vocabulary and related near-antonyms and example sentences through voice input, avoiding the problem that primary school students are not suitable for the virtual keyboard of mobile devices, and at the same time, it can read text content for students to enhance students' Putonghua pronunciation practice and improve its accuracy.

The invention provides an electronic reading apparatus and a voice reading loading method. The voice reading loading method includes the following steps: a typesetting engine conducting type setting on an analyzed text, and the type setting includes: segmenting the text in according with preset sentence segmenting rules and recording in successive order coordinate information of each sentence and a corresponding sentence number; conducting sentence segmenting on the text which has been subject to the type setting in accordance with the preset sentence segmenting rules and adding a only identifier at the end of each sentence that has been segmented so as to form a new sentence with the only identifier; sending the newly segmented sentence to a voice synthesizing engine so as to form audio data and recording the position of a starting character corresponding with the new sentence and also recording the number of the synthesized sentences; executing voice reading from the selected sentence.

The invention relates to an electronic reader used for indicating position of the current reading text, the electronic reader comprises a display unit, an audio output device, a memory cell, a text capturing module, a text display module, a text analysis module, a synchronization control module, a text highlighting display processing module, a speech synthesis module and a player module, wherein the text capturing module is used for capturing a text from a text source and saving the text in the memory cell; the text display module is used for displaying the text in the memory cell to the display unit; the text highlighting display processing module is used for highlighting the text read by the text analysis module to the display unit; the speech synthesis module is used for converting the text read by the text analysis module into speech; and the player module is used for outputting the speech converted and generated by the speech synthesis module to the audio output device for play. According to the technical scheme of the invention, the electronic reader can highlight the current read text at the same time of the speech reading, thus a user can keep up with the schedule of the speech reading and obtain preferable use experience.

The invention, which relates to the field of auxiliary reading, discloses a text conversion method for assisting the blind in reading. The method comprises the following steps: training a character position detection network and an identification network separately; detecting the position of a to-be-read character by using the trained character position detection network and guiding a blind user to move the view based on a voice guidance algorithm to obtain character information at different positions; and identifying characters at different positions by using the trained character position detection network, splicing identification results of different positions into a complete semantic content based on a character splicing algorithm, and then converting the content into voice reading. Therefore, character detection and recognition are carried out by using deep learning and the speed is fast. The high precision is kept in a complex scene. The complete content of the whole page is spliced automatically by means of voice prompting and voice playing is carried out; the limitation on the page size is eliminated; and a phenomenon that the blind feel puzzles due to the incomplete reading information is avoided. In addition, the invention also discloses a text conversion system for assisting the blind in reading.

The invention discloses a speech reading method and a speech reading device of a vehicle-mounted system. A customer is informed of information which is required to be known in a speech reporting mode, so the convenience and safety of driving are improved. The technical scheme of the invention is characterized in that: the method comprises the following steps of: transmitting file data in a text format to a text-to-speech conversion module; converting the input file data in the text format into an audio data stream by the text-to-speech conversion module, and outputting; and playing the converted audio data stream in a speech reading mode.

The invention relates to the field of devices for the disabled, and especially relates to multifunctional blindman's glasses. The multifunctional blindman's glasses comprise a glasses frame, glasses legs and a nose beam, the glasses frame is symmetrically provided with two miniature cameras along the vertical midline of the nose beam, the nose beam is provided with a tilt angle sensor, and one of the glasses legs is provided with an information processing device and a battery for powering up the information processing device; the information processing device comprises a microprocessor, and an alarm unit, a data storage unit, an acoustic control identification system, an SIM card, a voice coder and a TTS voice generator which are connected with the microprocessor; and the information processing device also comprises a voice player, a microphone and a function button which are communicated with the microprocessor. The glasses are provided with the camera and the image processing device, so a reading material is converted to a voice played for a blindman user, the multifunctional blindman's glasses are convenient to wear and use, and the voice reading accuracy is guaranteed through tilt angle measurement and distance measurement, so the reading efficiency is improved.

The present invention provides a digital broadcast receiving apparatus, characterized by comprises a receiving and selecting unit (3) which receives and selects a digital broadcast wave, an acquisition unit (4, 8) which decodes a data broadcast stream included in the received and selected digital broadcast wave and acquiring character data and image data for data broadcast, a memory unit (22) which stores graphics patterns and reading data of the graphics patterns, a unit (23) which collates the acquired image data with information stored in the storage memory (22) and retrieves reading data of graphics patterns included in the image data, a unit (24) which creates sentence data for voice reading based on the acquired character data and the retrieved reading data, and a unit (25) which converts the created sentence data into voice data.

The invention discloses a method and device for voice reading, wherein the method includes: receiving a trigger instruction input by a user, acquiring text information according to a preset method; converting the acquired text information into voice information, and converting the acquired text information into voice information; to play the above voice information. In the present invention, when the font of the text information is small, the text information can be read by voice according to the needs of the user, which is convenient for the user.

A ultrasonic thickness gage with voice fetching function is used in non - destructive testing field, comprising principal machine and probe parts which is ultrasonic wave impulse transmitting unit and receiving unit and principal machine part consists of CPU, ultrasonic wave transmitting circuit, thickness wave forming circuit, counter circuit, display circuit and keyboard, with its properties: voice circuit and storage circuit both linked to CPU and USB general purpose serial bus interface circuit are added; USB interface circuit is consisted of USB interface integrated circuit with parallel bus and CPU linking together; CPU is used to receive signal sent by other circuits, and creates controlling signal to control them; CPU controls ultrasonic ultrasonic thickness circuit and calculates thickness value of object tested, the result can be shown or read by CPU controlling control voice circuit and put out by CPU to be stored in storage then uploaded to PU for data collection and analysis. It has excellent practicability.

The invention provides a short message reading method and mobile terminal equipment. During the startup initialization process, the brightness sensor and the environmental brightness judging module of the mobile terminal equipment are turned on. The brightness sensor detects the brightness of the environment of the mobile terminal equipment, obtains environmental brightness signals and transmits the environmental brightness signals to the environmental brightness judging module. The environmental brightness judging module judges whether the mobile terminal equipment is in a strong-light environment or not according to the environmental brightness signals and a strong-light environment judging strategy. If so, a speech mode switching signal is transmitted to a short message module and the short message module enters a short message speech reading working mode according to the speech mode switching signal. By adopting the short message reading method and the mobile terminal equipment provided by the invention, the mobile terminal equipment can be switched to the short message speech reading working mode when the mobile terminal equipment is in the strong-light environment, and the accuracy of reading the short message can be improved.

The invention relates to the technical field of blind reading, in particular to an intelligent electronic book for blind reading based on magnetic fluid and a displaying method thereof. The book comprises a base shell, a coil collection plate, a magnetic fluid collection plate and thin film which are connected in sequence; a plurality of magnetic fluid boxes which are arrayed in order are arrangedon the magnetic fluid collection plate, magnetic fluid is arranged in the magnetic fluid boxes, and a plurality of coils which can act on the magnetic fluid and make the magnetic fluid in a protruding state are arranged on the coil collection plate; when a coil is alive, a magnetic field is generated nearby the coil, so that the magnetic fluid in the corresponding the magnetic fluid boxes is in aprotruding state. According to the intelligent electronic book, the magnetic fluid is used as a braille pattern response device, the intelligent electronic book has the advantages of sensitive reaction, small size and low energy consumption, and compared with other blind electronic book systems on the market, the intelligent electronic book is low in manufacturing cost and is carried by a user conveniently; the blind can select voice reading, touch reading or combination of voice reading and touch reading as a reading mode, and the electronic book is used in different occasions conveniently.

An Internet accessed server that on demand downloads and activates text-to-speech program elements to a subscriber's computer. Program elements are customized to match the operating system of the subscriber's computer. Upon termination of the text-to-speech session, the server deactivates all program elements and the subscriber becomes free to reinitiate over the Internet the text-to-speech program on the same or another computer system.

An electronically accessible server that on demand provisions program elements to be locally controlled by a subscriber's device. Upon termination of work session the server deactivates all provisioned elements and the subscriber becomes free to reinitiate program elements to be controlled by the same or another computer.

The invention provides an intelligent reading method. The intelligent reading method comprises the following steps: S10, acquiring data; s20, selecting a reading mode, wherein the reading mode comprises paper reading, video reading and audio reading; s30, adjusting the position of the display module, the sitting posture of the reader and the brightness of the illumination module; and S40, judgingwhether rest or interference is needed or not according to the image data. According to the intelligent reading system provided by the invention, reading becomes more flexible through switching of three reading modes, and the reading pleasure of a reader is increased. Meanwhile, due to the fact that a voice reading mode is set, the blind can read with common paper books, and the reading range of the blind is widened.

The audio data download and display technique comprises: with speech recognition, extracting rhythm information from text file by speech recognition, embedding extracted information into the text file to form file stored in server for download; downloading the file from server by the client terminal, and synthesizing the final voice by test information for display. This invention is fit to program-ordering service.

This disclosure generally relates to a system and method for assessing reading quality during a reading session. In one embodiment, system is disclosed that analyzes speech that corresponds to a reading session for the duration of the reading session, the consistency of the reading sessions, the speed of the speech during the reading session, the engagement level of the parent during the reading session, and the environment in which the reading session takes place in another embodiment, a method is disclosed for calculating an objective score for a reading session, communicating the score to a parent, and providing suggestions and challenges for improving future reading sessions.

A digital broadcast receiving device, characterized in that it includes a receiving and selecting unit (3) for receiving and selecting digital broadcast waves, and for decoding data broadcast streams included in the received and selected digital broadcast waves , and obtain a transport stream decoder and a data broadcast decoder (4, 8) for character data and image data for data broadcasting, a character recognition dictionary memory (22) for storing patterns and reading data of the patterns, for An image recognition unit (23) that compares the obtained image data with information stored in the character recognition dictionary memory (22), and obtains reading data of patterns contained in the image data, for The obtained character data and the acquired reading data generate a reading sentence generating unit (24) for sentence data of phonetic reading, and a speech synthesis unit for converting the generated sentence data into phonetic data (25).

The invention discloses a segment segmentation detection method and system, the method comprising: obtaining the segment segmentation result obtained by segmenting the reading voice; performing voice recognition on the reading voice to obtain the recognition result; according to the The reading text corresponding to the reading voice calculates the recognition rate of the segmentation result and the recognition rate of the recognition result respectively; if the recognition rate of the segmentation result is higher than the recognition rate of the recognition result, then determine that the segmentation result is normal; otherwise It is determined that the segmentation result is abnormal. The invention also discloses a spoken language evaluation method and system. The present invention can effectively detect whether the segment segmentation result is abnormal, thereby ensuring the accuracy of the evaluation result.

The invention relates to the field of auxiliary reading, and discloses a text conversion method for assisting blind reading. It includes the following processes: train the text position detection network and the recognition network respectively; use the trained text position detection network to detect the position of the text to be read, and guide the blind to move the field of vision through the voice guidance algorithm to obtain text information at different positions; use training The text position recognition network of the company recognizes the text in different positions, and through the text splicing algorithm, the recognition results of different positions are spliced ​​into complete semantic content and then converted into voice reading. This solution uses deep learning for text detection and recognition, which is fast and maintains high accuracy in complex scenarios; it uses voice prompts to automatically splicing out the complete content of the entire page and performs voice playback. There is no limit to the size of the page, avoiding reading Incomplete information creates confusion for blind people. The invention also discloses a text conversion system for assisting blind reading.

The invention provides an intelligent reading system. The intelligent reading system comprises an illumination module; a display module which is internally provided with a camera, a distance sensor and a loudspeaker; a household data processing module which is electrically connected with the display module and the illumination module; a remote data processing module which is connected with the household data processing module through a wireless network, wherein the reading mode comprises paper reading, video reading and audio reading. According to the intelligent reading system provided by theinvention, the reading becomes more flexible through the switching of three reading modes, and the reading pleasure of a reader is increased. Meanwhile, by setting a voice reading mode, the blind person can also read the common paper books, the reading range of the blind person is not limited to the existing braille books any more, and the reading range of the blind person is widened.

An ultrasonic thickness gauge with voice reading function is used in the field of non-destructive testing. It includes two parts, the host and the probe. The probe part is the ultrasonic pulse transmitting unit and the receiving unit. The host part includes a CPU, an ultrasonic transmitting circuit, a signal receiving and amplifying circuit, a thickness wave forming circuit, a memory circuit, a counter circuit, a display circuit and a keyboard. , memory circuit is used for storing thickness value, is characterized in that: also be provided with the voice circuit that is connected with CPU, USB universal serial bus interface circuit; USB interface circuit is made up of the USB interface integrated circuit with parallel bus and CPU connection, voice circuit It is used to realize the voice reporting; the CPU controls the ultrasonic thickness measuring circuit, and the thickness value of the measured object is obtained through calculation and processing, which can be displayed, and the measurement data can also be read out by the CPU controlling the voice circuit. All measurement data are finally uploaded to the PC through the USB interface for data analysis and collection. The instrument is practical.

The invention provides an electronic reading apparatus and a voice reading loading method. The voice reading loading method includes the following steps: a typesetting engine conducting type setting on an analyzed text, and the type setting includes: segmenting the text in according with preset sentence segmenting rules and recording in successive order coordinate information of each sentence and a corresponding sentence number; conducting sentence segmenting on the text which has been subject to the type setting in accordance with the preset sentence segmenting rules and adding a only identifier at the end of each sentence that has been segmented so as to form a new sentence with the only identifier; sending the newly segmented sentence to a voice synthesizing engine so as to form audio data and recording the position of a starting character corresponding with the new sentence and also recording the number of the synthesized sentences; executing voice reading from the selected sentence.

The invention discloses a voice map reading method and system based on a smart TV. The method comprises the following steps: receiving a picture and character information corresponding to the picture sent by a front end device; displaying the picture on the smart TV, and obtaining the corresponding character information according to the picture; and converting the character information into voice information, and synchronously playing the character information with the picture. By adoption of the voice map reading method and system disclosed by the invention, the smart TV increases a picture voice reading function, the character information corresponding to the picture is converted into the voice information, and the voice information is synchronously played with the picture by human voice, thereby being convenient for users to read the character information corresponding to the picture and bringing convenience to the use of the users.

The invention discloses a three-stage medical service mode and service platform for ahead acute treatment. The service mode comprises a community front-end disposal unit, a 120 emergency unit and a rear end emergency center, wherein the community front-end disposal unit is equipped with a life index monitoring device and a speech reading mobile terminal with trained community securities as disposal personnel, a camera and a vide tape recorder are arranged in an ambulance, images of a patient are stored in the video tape recorder or conveyed into a medical command center in real time through the camera in the ambulance, medical staff in the ambulance send out a request to experts in a medical group of the medical command center through the mobile terminal, the remote guidance of the expertsof the medical group in a hospital is obtained, and the rear end emergency center is equipped with a speech reading monitor and used for receiving a communication request remotely sent by the community front-end disposal unit and the 120 emergency unit and receiving audio and video images conveyed in real time so that remote guidance can be provided for the medical staff on site at the front endby the experts of the medical group. Through the three-stage medical service mode, the emergency treatment is effectively conducted ahead of time, and the emergency reaction time can be shortened.

The invention discloses an end-to-end intelligent voice reading evaluation method, which includes: collecting the data processing flow of reading voice, target pronunciation, error code, and speaker information used for training and evaluating the neural network; Auxiliary training; according to the target pronunciation to be evaluated and the pronunciation to be evaluated, the evaluation results are directly output from the neural network end-to-end, from the input of the target pronunciation and the pronunciation to be evaluated to the output of the evaluation results, the entire process can be differentiated, and can be directly targeted at the evaluation indicators optimization. The present invention directly constructs an end-to-end evaluation mode in which the input is speech and text to be evaluated, and the output is feedback results. It can be jointly trained with each module in the method to make the overall effect better. In addition, the auxiliary tasks constructed by the method can more accurately extract Evaluate related features to make feedback evaluation results more accurate.