103 results about "Speech recording" patented technology

The invention discloses a method and an apparatus for constructing a speech decoding network in digital speech recognition. The method includes the following steps: acquiring training data obtained from digital speech recording, the training data including a plurality of speech sections; extracting acoustic features from the training data so as to obtain a feature sequence which corresponding with each speech section; based on the feature sequences and phonemes corresponding with digits in the training data, conducting progressive training beginning with a single phoneme acoustic model to obtain an acoustic model; acquiring a language model, constructing a speech decoding network through the language model and the acoustic model obtained in the training, the language model being obtained by modeling matching relationship of digits in the training data. According to the invention, the method and the apparatus can effectively increase recognition accuracy of digital speech.

The invention relates to a voice song-selecting method, which belongs to song-selection application technology. The invention is characterized in that a data initialization module containing files of Chinese character database and a similarity metric value chart of initials and finals of Chinese syllables, a song database character pre-processing module containing character strings of target syllable chains corresponding to the name of the song or the name of the singer, a voice recognition module for converting the voice recording data of the name of the song or the name of the singer input from the sound card into the corresponding character strings of Chinese characters, a recognition result post-processing module for converting the character strings of Chinese characters into the character strings of source syllable chains, and a searching and matching module for calculating the difference value based on the metric of the similarity between initials and finals according to the character strings of target syllable chains corresponding to the name of the song or the name of the singer and the character strings of source syllable chains obtained from the recognition result post-processing module, Besides calculating the integral difference by using the dynamic programming method and outputting the result of the minimum difference value. The average button pressing time and the average operating time of song-selection are reduced, and the efficiency of song-selection operation is greatly enhanced.

A media production system includes a textual alignment module aligning multiple speech recordings to textual lines of a script based on speech recognition results. A navigation module responds to user navigation selections respective of the textual lines of the script by communicating to the user corresponding, line-specific portions of the multiple speech recordings. An editing module responds to user associations of multiple speech recordings with textual lines by accumulating line-specific portions of the multiple speech recordings in a combination recording based on at least one of relationships of textual lines in the script to the combination recording, and temporal alignments between the multiple speech recordings and the combination recording.

The invention discloses an electronic card system which comprises a speech acquisition module, a speech analysis module, a speech characteristic extraction module, a keyword recognition module, an electronic card manager and an electronic card database, wherein the speech acquisition module is used for acquiring speech; the speech analysis module is used for transmitting an effective speech signal to the speech characteristic extraction module; the speech characteristic extraction module is used for extracting speech characteristics according to the received speech signal; the keyword recognition module is used for carrying out keyword recognition on the speech characteristics and outputting a keyword; the electronic card manager is used for establishing an electronic card in the electronic card database according to the keyword or browsing, retrieving, deleting and correcting the electronic card established in the electric card database; and the electronic card database stores the electronic card. The invention also discloses a speech recording method and a speech retrieval method of the electronic card, and also discloses an effective speech judgment method. According to the invention, contact information can be conveniently recorded and the electronic card is established, and multiple electronic cards can be rapidly retrieved.

The invention relates to a binary channel magnetism-free secretive electronic payment system based on voice and Internet and a payment method thereof. Potential safety exists in the modes of traditional on-line payment and telephone payment both of which require simultaneously inputting card number and password, and the card number and the password are likely to be stolen by means of wooden procedure or voice record, and the like. In the invention, a computer, wireless communication, voice processing technique and telephone signal digitization are integrated under a unified platform based on an IVR (Interactive Voice Response) technique of CTI (Computer Telephony Integration), and smooth junction with an external network and the platform is realized through an adaptive gateway. Users and merchants transmit account order information through an Internet digital channel or an IVR voice channel and transmit password confirming information through another IVR voice channel so as to ensure asynchronous transmission of the account order information and the password confirming information through two independent channels. The invention ensures the payment safety, provides multiple rapid and safe payment manners for users, improves the working efficiency and enhances the service quality of users.

The invention discloses an adult hearing and speaking rehabilitation system comprising an information management module, a parameter setting module, a single character pronouncing assessment module, a single character pronouncement training module, a word reading training module, a speech recording and playing module, an automatic speaking assessment module and a random sequence producing module. The system is applied to speaking and reading training for aphasia patients with repetition impediment or loud reading impediment and dysarthria during speaking rehabilitation, the speaking feedback ability of the aphasia patient is improved, the pronouncing accuracy level of the dysarthria patient is raised, the continuous pronouncing coordinate ability is improved, and the work intensity is reduce significantly for speaking therapists. Multisensory reinforcing stimulation is performed on the patient in multimedia interacting manners of graphs, texts, dynamic images and voices, the subjective initiation of the patient for the rehabilitation training is improved, and the rehabilitation training effect is improved; the simple, boring and repeated work can be reduced for the therapists.

The invention provides a system and a method for controlling a set-top box by voice, relating to the digital television set-top box and the IPTV set-top box fields. The system of the invention comprises a voice control module. In a voice recording mode, the voice control module inputs voice recording of a user, processes the voice recording and cods and saves the processed voice recording of the user; in a voice control mode, the voice control module receives an operation command from the user, compares the operation command with the saved voice recording of the user to find out an address corresponding to a matching recording when the matching recording is found, and sends a command for changing channel to a set-top box channel control circuit according to a channel corresponding to the address. The invention comprises a voice inputting step and a voice controlling step. The system of the voice control set-top box and a method thereof ensures that disable users and other users with work in hands can control the set-top box by voice, thereby operating the set-top box more conveniently and increasing the satisfaction of users.

To automatically detect and automatically correct in a reproduced speech, defective portions related to plosives such as existence or absence of plosive portions, phoneme lengths of aspirated portions that continue after the plosive portions or defective portions related to amplitude variations of fricatives. Speech wherein consonants and unvoiced vowels are unclear and discordant is input into a speech enhancement apparatus according to the present invention. In the speech enhancement apparatus, the speech is split into phonemes and each phoneme is classified into any one of an unvoiced plosive, a voiced plosive, an unvoiced fricative, a voiced fricative, an affricate, and an unvoiced vowel. Each phoneme is corrected according to a determination of necessity of correction of each phoneme to obtain an output of the speech wherein the consonants and the unvoiced vowels are clear and not discordant.

The invention discloses a speech content extracting method and a speech content extracting device based on a cloud platform. The speech content extracting method is characterized in that audio materials and video materials of a speech are acquired, and are cached in a PC for a pretreatment; the pretreated audio materials, the pretreated video materials, related data including speech slides, and related reading materials are transmitted to a server; the server is used for voice segmentation of the received audio materials, and is used for segmenting the audio materials according to speakers; automatic voice identification is used for converting the segmented audio materials into words, and adopts acoustic self-adaption and language model self-adaption; key words are extracted from texts after the voice identification, and content notes are generated. By adopting the speech content extracting method, the audio materials are converted into the text form, which can be read repeatedly, by the audio identification, and the language model self-adaption and the acoustic model self-adaption are used to improve the identification accuracy. Because of knowledge integration, time for reading redundant information is saved. The invention also discloses the speech content extracting device based on the cloud platform. The s speech content extracting device comprises a speech recording module, a material transmitting module, a voice segmenting module, a voice identifying module, and a key word and a content note extracting module.

The invention discloses a speech input authentication device, which comprises an authentication code display module (1), a speech recording module (2), a speech analysis and recognition module (3) and an authentication code authentication module (4). The device is characterized in that the authentication code display module (1) is used for displaying a picture or video with an authentication code; the speech recording module (2) is used for recording a speech made by a user according to the authentication code seen in the picture or video; the speech analysis and recognition module (3) performs analytical and recognition operation according to related algorithms to obtain a speech recognition result; and the authentication code authentication module (4) carries out comparison according to currently displayed authentication code information and speech recognition result, and if the authentication code information is consistent with the speech recognition result, the authentication succeeds, otherwise, the authentication is failed. The invention also discloses a speech input authentication method. By adopting the speech input authentication device and method provided by the invention, authentication code authentication can be performed conveniently and quickly, and various disadvantages of manual input are overcome.

The invention discloses a speech processing method. The method comprises the following steps: cutting non-speech part in the voice through end point detection to acquire a plurality of first speech fragments; performing Bayes information criterion BIC detection on the plurality of first speech fragments to acquire a speaker transition point; serving the speaker transition point as a break point tobreak the plurality of speech fragments, thereby acquiring a plurality of second speech fragments; extracting speech characteristics of the second speech signal fragments to form characteristic vector, classifying the second speech fragments; and correcting the category of the second speech fragments according to a preset keyword. Therefore, the problem that the algorithm processing effect is non-ideal for the telephone speech recording on the complex service scene by the existing speaker segmentation clustering algorithm can be improved, and an effect of accurately and quickly recognizing the speaker of the speech can be improved.

A system and method for searching for an element in speech related documents may include transcribing a set of speech recordings to a set of phoneme strings and including the phoneme strings in a set of phonetic transcriptions. A system and method may reverse-index the phonetic transcriptions according to one or more phonemes such that the one or more phonemes can be used as a search key for searching the phoneme in the phonetic transcriptions. A system and method may transcribe a textual search term into a set of search phoneme strings and use the set of search phoneme strings to search for an element in the set of phonetic transcriptions.

The invention relates to a speech recognition washing machine, which comprises a control mainboard and is characterized by also comprising a speech recognition system. The speech recognition system comprises a speech recording module and a signal transformation module, and is arranged on a panel of the washing machine, the speed recording module is connected with the signal transformation module by a signal wire, and the signal transformation module is connected with the control mainboard by a signal wire. The speech recognition washing machine can be controlled by the speed of an operator, liberates the hands of the operator and allows the operator to do other things at the same time, and has convenient use and simple structure.

A method (and system) which autonomously generates a cohesive script from a text database for creating a speech corpus for concatenative text-to-speech, and more particularly, which generates cohesive scripts having fluency and natural prosody that can be used to generate compact text-to-speech recordings that cover a plurality of phonetic events.

A method for recording pronunciation used in track locomotive includes carrying out A / D conversion on radio station pronunciation signal under control internal logic control unit in FPGA logic buffer with its output end being connected to corresponding port of DSP pronunciation coding / decoding operation controller, carrying out data exchange with internal double port RAM of FPGA by DPS data port, storing audio data in pronunciation file mode into NAND FLASH storage circuit under control of ARM master control module. The device for realizing said method is also disclosed.

The present invention sets TTS and ASR equipment in fixed network short message system first. The short message is stored and calling normal phone at the time of sending short message from fixed network terminal (FNT) to normal phone terminal (NPT). TTS is used boardcast the short message when calling is connected through. At the time of sending short message from NPT to FNT, the short message isrecorded and to keep it in voice nail-box, then to send short message to inform it to receive the short message. At the time of using fixed network short message service provided by ICP at NPT, ASR reminds the user to use voice selection information and the short message request is sent to ICP, ASR receives written information from ICP and to broadcast it to calling or called user through TTS.

A talking medicine label, bottle, system and method for their manufacture are described. The system and method include use of a recording device by speaking into a microphone and then affixing the talking label to the side of a conventional pill bottle to transform it into a talking pill bottle. The system and method alternatively may include a point of sale (POS) terminal and a speech synthesis device for programming the label with a synthetic-speech recording.

The invention discloses a voice response processing method and device based on artificial intelligence, equipment and a medium. The method comprises the following steps: acquiring a to-be-processed voice stream acquired by a voice recording module in real time; performing statement integrity analysis on the to-be-processed voice stream to obtain a to-be-analyzed voice stream; executing a first processing process and a second processing process in parallel, controlling a voice playing module to play the target mood word recording based on the first processing process, and identifying the to-be-analyzed voice stream based on the second processing process to obtain target response voice; and monitoring the playing state of the target mood word recording played by the voice playing module in real time, and if the playing state is that playing is finished, controlling the voice playing module to play the target response voice. According to the method, intelligent interaction equipment can respond in real time in a man-machine interaction process, and the response time and the response effect of voice interaction are improved.

Methods and computer programs for recording infant-directed speech, including: guiding a parent as to which sound to record; showing the parent an image of her infant, or asking the parent to look at an image of her infant, in order to encourage the parent to speak in an infant-directed manner; and recording the parent.

The invention provides a non-key electron time telling clock utilizing a speech recognition technology. An outer shell of the non-key electron time telling clock is not provided with any keys. An electronic timer circuit which is managed by a microcontroller, a speech recording and broadcast circuit and a speech recognition circuit are arranged inside the clock shell. The non-key electron time telling clock utilizing the speech recognition technology is characterized in that when a user of the non-key electron time telling clock needs to obtain the current time, the user just needs to say 'time' nearby the non-key electron time telling clock, and the non-key electron time telling clock can then achieve a time telling function. When the user of the non-key electron time telling clock needs to modify the time of the non-key electron time telling clock and set a speech timing warning, the user of the non-key electron time telling clock can further achieve the modification of the time of the non-key electron time telling clock and the set of the speech timing warning under a voice prompt of a control circuit in a speaking mode.

The invention discloses a call communication recording method and device. The method is based on a mobile terminal, wherein the back surface of the mobile terminal is provided with a distance sensor. The method includes the following steps that: whether the mobile terminal is in a call communication state is judged; when the mobile terminal is in the call communication state, a distance value detected by the distance sensor is detected; when the detected distance value is smaller than a set distance threshold value, call communication speech is acquired and recorded; in a recording process, if it is detected that the detected distance value is greater than the set distance threshold value, the recording of the call communication speech is terminated. The present invention correspondingly discloses a call communication recording device. With the call communication recording method and device provided by the embodiments of the invention adopted, the operation process of speech recording in a call communication process can be simplified, and sectional type recording of the call communication speech can be realized, and the reading of recorded content can be facilitated, and use convenience can be improved for the user.

The invention relates to a voice recorder and relative voice coder/decoder, wherein it comprises multiplexer, sequential analogue/digit converter, and pulse modulation digit circuit; the multiplexer via the first clock signal alternatively output left and right channel input signals; the converter is connected to the multiplexer, while its operation frequency is second clock signal, to convert the left and right channel input signals into digit signals; the pulse modulation digit circuit converts the output signal of converter from serial digit code into parallel digit code.