307 results about "Vowel" patented technology

The invention concerns a high speed writing system and a high speed writing device with special menu selection for entering text by means of a pen and a touch-screen. This method of entering text is suitable for desktop PCs, laptop PCs, palmtop PCs, mobile phones (for SMS, WAP and e-mail), watches and other electronic devices. Significantly higher writing efficiency than on a QWERTY keyboard is reached with little investment in practicing time.

The monitor screen features a key section with all consonants of the alphabet, as well as one vowel key distinguished by its arrangement and function. All elements of the writing process defining the method can be generated by pen movements such as selection of a key or guiding it in one of eight stroke directions, as well as combinations of these pen movements

The high speed writing devices described here excel by their small and ergonomically arranged entry sections, whereby all keys for text entry can be reached from one single hand position that never needs re-setting.

A method for identifying voice emotion based on support vector computer includes characteristic picking up-analyzing to collate characteristic parameter selection of global structure and sex, as well as to collate characteristic parameter selection of time sequence structure and to collate sex and vowel number; support vector computer training to carry out identification on five emotions of happy, angry, sad, fear and surprise.

Improved skipping strategies for cochlear or other multi-channel neural stimulation implants selects N out of M channels for stimulation during a given stimulation frame. A microphone transduces acoustic energy into an electrical signal. The electrical signal is processed by a family of bandpass filters, or the equivalent, to produce a number of frequency channels. In a first embodiment, a probability based channel selection strategy computes a probably for each of the M channels based on the strength of each channel. N channels are probabilistically selected for stimulation based on their individual probability. The result is a randomized “stochastic” stimulus presentation to the patient. Such randomized stimulation reduces under representation of weaker channels for steady state input conditions such as vowels. In second, third and fourth embodiments, a variable threshold is adjusted to obtain the selection of N channels per frame.

Phoneme boundaries may be determined from a signal corresponding to recorded audio by extracting auditory attention features from the signal and extracting phoneme posteriors from the signal. The auditory attention features and phoneme posteriors may then be combined to detect boundaries in the signal.

A voice recognition system and method are provided. The voice recognition system includes a voice input unit configured to receive learning voice data and a target label including consonant and vowel (letter) information representing the learning voice data, and divide the learning voice data into windows having a predetermined size; a first voice recognition unit configured to learn features of the divided windows using a first neural network model and the target label; a second voice recognition unit configured to learn a time-series pattern of the extracted features using a second neural network model; and a text output unit configured to convert target voice data input to the voice input unit into a text based on learning results of the first voice recognition unit and the second voice recognition unit, and output the text.

The present invention provides a search apparatus that allows a user to execute search processing with ease without user's operating an operator block and checking information shown on a display block. The search apparatus has a name storage block, a vowel conversion block for converting name data stored in the name storage block into first vowel name data, a detection block for detecting an external impact applied by the user to the search apparatus or a myoelectric potential change caused by user movement as a user input signal, an analysis block for analyzing the user input signal to identify an input pattern, a vowel generation block for generating second vowel name data corresponding to the identified input pattern, an extraction block for making a comparison between the first vowel name data and the second vowel name data to extract one or more pieces of first vowel name data that match or are similar to the second vowel name data, and a list creation block for listing the name data corresponding to the extracted first vowel name data to create a candidate list.

A novel keyboard made up vowel daisies is used to learn to read, write and spell in English. A story is presented in which a specific set of words that can be generated emphasized. Upon hearing the story, a user enters a response which is received by the device when the specific word is highlighted in the story. A letter configuration, such as a hexagonal ring of letters corresponding to the specific word is displayed on the device. A phonic data relating to a letter in the specific word is manifested at the same time as another characteristic or attribute of the letter, specifically the shape of the letter, is also displayed or manifested to the user. These are done concurrently with displaying the letter configuration that corresponds to the word, wherein the letters are all in the same daisy array.

A voice quality conversion device converts voice quality of an input speech using information of the speech. The device includes: a target vowel vocal tract information hold unit (101) holding target vowel vocal tract information of each vowel indicating target voice quality; a vowel conversion unit (103) receiving vocal tract information with phoneme boundary information of the speech including information of phonemes and phoneme durations, (ii) approximating a temporal change of vocal tract information of a vowel in the vocal tract information with phoneme boundary information applying a first function, (iii) approximating a temporal change of vocal tract information of the same vowel held in the target vowel vocal tract information hold unit (101) applying a second function, (iv) calculating a third function by combining the first function with the second function, and (v) converting the vocal tract information of the vowel applying the third function; and a synthesis unit (103) synthesizing a speech using the converted information (102).

According to one aspect of the invention, a method is provided in which knowledge about tone characteristics of a tonal syllabic language is used to model speech at various levels in a bottom-up speech recognition structure. The various levels in the bottom-up recognition structure include the acoustic level, the phonetic level, the work level, and the sentence level. At the acoustic level, pitch is treated as a continuous acoustic variable and pitch information extracted from the speech signal is included as feature component of feature vectors. At the phonetic level, main vowels having the same phonetic structure but different tones are defined and modeled as different phonemes. At the word level, as set of tone changes rules is used to build transcription for training data and pronunciation lattice for decoding. At sentence level, a set of sentence ending words with light tone are also added to the system vocabulary.

A plurality of voice segments, each including one or more phonemes are acquired in a time-serial manner, in correspondence with desired singing or speaking words. As necessary, a boundary is designated between start and end points of a vowel phoneme included in any one of the acquired voice segments. Voice is synthesized for a region of the vowel phoneme that precedes the designated boundary vowel phoneme, or a region of the vowel phoneme that succeeds the designated boundary in the vowel phoneme. By synthesizing a voice for the region preceding the designated boundary, it is possible to synthesize a voice imitative of a vowel sound that is uttered by a person and then stopped to sound with his or her mouth kept opened. Further, by synthesizing a voice for the region succeeding the designated boundary, it is possible to synthesize a voice imitative of a vowel sound that is started to sound with the mouth opened.

The invention discloses a Chinese medicine sound diagnosis acquisition and analysis system. The Chinese medicine sound diagnosis acquisition and analysis system is formed by sequentially connecting a pronunciation table, a sound acquisition device and a voice processing system, wherein the pronunciation table is formed by combining vowels, poetry of the Tang Dynasty and Chinese characters corresponding to five tones; the sound acquisition device consists of a microphone and an audio card and is used for acquiring a sound signal; the microphone is connected with the audio card; the audio card converts an analogue signal acquired by the microphone into a digital signal; the voice processing system is arranged on a computer and comprises a voice recording system, a voice signal preprocessing system and a voice signal analysis system; and the voice recording system can prompt a testee to read after the content prompted in the pronunciation table. After the recorded voice signals are preprocessed, the voice signal analysis system distinguishes exterior and interior, cold and heat, and deficiency and excess of medical card type and viscera disease location by analyzing the sound information of the testee.

The invention provides a resonance peak automatic matching method for voiceprint identification. The method comprises the following steps that: phoneme boundary positions in an inspection material and a sample in the voiceprint identification can be automatically marked through using continuous speech recognition-based forced alignment (FA) technology; as for identical vowel phoneme segments of the inspection material and the sample, whether a current phoneme is a valid analysable phoneme is automatically judged through using fundamental frequencies, resonance peaks and power spectrum density parameters; and deviation ratios of corresponding resonance peak time-frequency areas can be automatically rendered through using a dynamic time warping (DTW) algorithm and are adopted as analysis basis of final manual voiceprint identification. With the resonance peak automatic matching method for the voiceprint identification of the invention adopted, the boundaries of phonemes can be automatically marked, and whether the pronunciation of the phonemes is valid is judged, and therefore, processing efficiency can be greatly improved; and at the same time, an automatic resonance peak deviation alignment algorithm is performed on effective phoneme pairs, and therefore, the accuracy of resonance peak alignment can be improved.

A keyboard used with information terminals/devices and key arrangement on the keyboard. The keyboard comprises a high click frequency key group chain consisting of at least four of the five vowel keys and the ‘N’ key. Within the key group chain, each member key is next to at least one another member key along a row or along a column. The five vowel keys are A, E, I, 0, U. The keyboard can be operated by a single hand, and can have an alphabet input region with 4 to 6 columns of keys, depending on the particular usage requirement, but still maintain a same central module. The keyboard is convenient for inputting Chinese phonetic letters and alphabets of Western languages.

A book-like reading teaching tool having a plurality of columns wherein each column contains each letter of the alphabet in ascending format, which are simultaneously viewable, a picture corresponding to each sound of each letter in the alphabet and structure for interchanging, mixing and matching letters and identifying and selecting long vowel and short vowel sounds. The reading tool includes a front cover, back cover, spiral binder, instructions, alphabet indicia, plurality of pictures corresponding to each letter and sound in the alphabet, plurality of windows or cutouts corresponding to selected letters and sounds, short vowel sound indicia, long vowel sound indicia and plurality of flip panels arranged in columns wherein each panel in each column contains a letter indicia. The covers, pages and panels have a plurality of apertures that are joined at coinciding ends by the spiral binder. The windows are formed in the second page over pictures corresponding to letters having only one sound or one common sound, such as the letter “B.” The instructions indicate how to form words and sounds using the panels and also include suggested beginning sounds, set of suggested complex beginning sounds, set of suggested ending sounds and set of suggested complex ending sounds.

Method, system, and program product for measuring audio video synchronization. This is done by first acquiring audio video information into an audio video synchronization system. The step of data acquisition is followed by analyzing the audio information, and analyzing the video information. Next, the audio information is analyzed to locate the presence of sounds therein related to a speaker's personal voice characteristics. In Analysis Phase Audio and Video MuEv-s are calculated from the audio and video information, and the audio and video information is classified into vowel sounds including AA, EE, OO, B, V, TH, F, silence, other sounds, and unclassified phonemes. The inner space between the lips are also identified and determined. This information is used to determine and associate a dominant audio class in a video frame. Matching locations are determined, and the offset of video and audio is determined.

The invention provides an electronic larynx speech reconstructing method and a system thereof. The method comprises the following steps of: firstly, extracting model parameters form collected speech as a parameter library; secondly, collecting the face image of a sounder, and transmitting the face image to an image analysis and processing module to obtain the sounding start moment, the sounding stop moment and the sounding vowel category; thirdly, synthesizing a voice source wave form through a voice source synthesizing module; and finally, outputting the voice source wave form through an electronic larynx vibration output module. Wherein the voice source synthesizing module is used for firstly setting the model parameters of a glottis voice source to synthesize the glottis voice source wave form, then simulating the transmission of the sound in the vocal tract by using a waveguide model and selecting the form parameters of the vocal tract according to the sounding vowel category so as to synthesize the electronic larynx voice source wave form. The speech reconstructed by the method and the system is closer to the sound of the sounder per se.

A rule based speech synthesis apparatus by which concatenation distortion may be less than a preset value without dependency on utterance, wherein a parameter correction unit reads out a target parameter for a vowel from a target parameter storage, responsive to the phoneme at the a leading end and at a trailing end of a speech element and acoustic feature parameters output from a speech element selector, and accordingly corrects the acoustic feature parameters of the speech element. The parameter correction unit corrects the parameters, so that the parameters ahead and behind the speech element are equal to the target parameter for the vowel of the corresponding phoneme, and outputs the so corrected parameters.

When an input section is actuated by a user, a character is inputted, and a storage section stores therein the inputted character. On this occasion, when the inputted character is a vowel character, a control section causes the storage section to store therein the inputted vowel character and an intonation associated therewith. In a case where a vowel character identical to the inputted vowel character is successively inputted by the input section, the control section causes the storage section to store therein the vowel character and the initial intonation in association with each other, for a first input. At second and subsequent inputs, the control section does not cause the storage section to store therein the identical vowel character anew, but it alters only the intonation associated with the vowel character which has been already stored in the storage section.