Patent application number | Description | Published |
20090076817 | METHOD AND APPARATUS FOR RECOGNIZING SPEECH - Provided are an apparatus and method for recognizing speech, in which reliability with respect to phoneme-recognized phoneme sequences is calculated and performance of speech recognition is enhanced using the calculated results. The method of recognizing speech includes the steps of: determining a boundary between phonemes included in character sequences that are phonetically input to detect each phoneme interval; calculating reliability according to a probability that a phoneme indicated by the detected phoneme interval corresponds to a phoneme included in a predefined phoneme model; calculating a phoneme alignment cost with respect to the character sequences based on the calculated reliability and a pre-trained and stored phoneme recognition probability distribution; and performing phoneme alignment based on the calculated phoneme alignment cost to perform speech recognition on the input character sequences. As a result, reliability with respect to the phoneme-recognized phoneme sequences can be calculated, and the performance of speech recognition can be enhanced using the calculated results. | 03-19-2009 |
20100070274 | APPARATUS AND METHOD FOR SPEECH RECOGNITION BASED ON SOUND SOURCE SEPARATION AND SOUND SOURCE IDENTIFICATION - An apparatus for a speech recognition based on source separation and identification includes: a sound source separator for separating mixed signals, which are input to two or more microphones, into sound source signals by using independent component analysis (ICA), and estimating direction information of the separated sound source signals; and a speech recognizer for calculating normalized log likelihood probabilities of the separated sound source signals. The apparatus further includes a speech signal identifier identifying a sound source corresponding to a user's speech signal by using both of the estimated direction information and the reliability information based on the normalized log likelihood probabilities. | 03-18-2010 |
20100145680 | METHOD AND APPARATUS FOR SPEECH RECOGNITION USING DOMAIN ONTOLOGY - A speech recognition method using a domain ontology includes: constructing domain ontology DB; forming a speech recognition grammar using the formed domain ontology DB; extracting a feature vector from a speech signal; modeling the speech signal using an acoustic model. The method performs speech recognition by using the acoustic model, the speech recognition dictionary and the speech recognition grammar on the basis of the feature vector. | 06-10-2010 |
20110054883 | SPEECH UNDERSTANDING SYSTEM USING AN EXAMPLE-BASED SEMANTIC REPRESENTATION PATTERN - A speech understanding apparatus includes: a speech recognition unit for recognizing an input speech to produce a speech recognition result; a sentence analysis unit for performing morpheme analysis on a sentence corresponding to the speech recognition result, extracting additional information, and performing syntax analysis; a hierarchy describing unit for describing hierarchy of the sentence; a class transformation unit for performing class transformation on the sentence; a semantic representation determination unit for marking optional expressions for the sentence, deleting meaningless expressions and the additional information, converting the sentence into its base form, and deleting morphemic tags or symbols to determine a semantic representation; a semantic representation retrieval unit for retrieving the determined semantic representation from an example-based semantic representation pattern database; and a retrieval result processing unit for selectively producing a retrieved semantic representation. | 03-03-2011 |
20120109650 | APPARATUS AND METHOD FOR CREATING ACOUSTIC MODEL - Disclosed herein is an apparatus and method for creating an acoustic model. The apparatus includes a binary tree creation unit, an information creation unit, and a binary tree reduction unit. The binary tree creation unit creates a binary tree by repeatedly merging a plurality of Gaussian components for each Hidden Markov Model (HMM) state of an acoustic model based on a distance measure reflecting a variation in likelihood score. The information creation unit creates information about information about the largest size of the acoustic model in accordance with a platform including a speech recognizer. The binary tree reduction unit reduces the binary tree in accordance with the information about the largest size of the acoustic model. | 05-03-2012 |
20130138441 | METHOD AND SYSTEM FOR GENERATING SEARCH NETWORK FOR VOICE RECOGNITION - Disclosed is a method of generating a search network for voice recognition, the method including: generating a pronunciation transduction weighted finite state transducer by implementing a pronunciation transduction rule representing a phenomenon of pronunciation transduction between recognition units as a weighted finite state transducer; and composing the pronunciation transduction weighted finite state transducer and one or more weighted finite state transducers. | 05-30-2013 |
Patent application number | Description | Published |
20140145810 | COIL FOR ENHANCING THE DEGREE OF FREEDOM OF A MAGNETIC FIELD - A coil for forming an induced magnetic field may include a first coil bundle formed of a first conducting wire wound in a first direction, the first coil bundle having an inner space of a prescribed inner width, a second coil bundle formed of a second conducting wire wound in a second direction, the second coil bundle having a prescribed outer width that is smaller than the inner width of the first coil bundle, and a connector that electrically connects the first conducting wire and the second conducting wire to each other. The second coil bundle may be provided in the inner space of the first coil bundle. The conducting wires of the first and second coil bundles may be wound in opposite directions and gaps between coil bundles may be changed. Accordingly, the magnetic field can be more evenly distributed in a wider area while maintaining a constant inductance. | 05-29-2014 |
20150309323 | IMAGE PROJECTION APPARATUS - An image projection apparatus includes a light source for emitting a light bundle, a display element forming an image by using the light bundle, and a projection system having: a lens unit refracting the light bundle so as to magnify and project the image and including first and second aspheric lenses, which are spaced from each other and change the refraction of the light bundle, and at least one spherical lens disposed between the first and second aspheric lenses; and a mirror for reflecting, toward the outside, the light bundle delivered by the lens unit. | 10-29-2015 |
20160041457 | PROJECTOR WITH WAVE LENGTH WHEEL AND COLOR WHEEL IN ONE MODULE - A projector with a wave length wheel and a color wheel in one module is proposed, the projector comprising: a light source configured to generate a first wavelength band light; a dichroic filter configured to reflect the first wavelength band light irradiated from the light source, and to transmit a second wavelength band light and a third wavelength band light; integrated wavelength conversion wheel and color wheel modules configured to integrally form a wave length wheel and a color wheel each wheel in a parallel manner in order to allow transmitting the first wavelength band light reflected from the dichroic filter and to generate the second wavelength band light and the third wavelength band light through wavelength conversion using the first wavelength band light as an excited light and to reflect the generated second wavelength band light and the third wavelength band light to the dichroic filter; and a light tunnel configured to receive the first wavelength band light reflected from the dichroic filter by transmitting the integrally formed wave length wheel and color wheel, and the second wavelength band light and the third wavelength band light transmit through the dichroic filter by being generated by and reflected from the integrally formed wave length wheel and color wheel. | 02-11-2016 |
20160138780 | HEADLIGHTS HAVING ONE LIGHT SOURCE MODULE FOR A HIGH BEAM AND A LOW BEAM - A high beam and a low beam is disclosed, the headlight including: a first light source unit; a second light source unit; a first light output unit; a second light output unit; and a controller configured to adjust a light quantity irradiated from the light source in response to a low beam mode or a high beam mode, and to control a beam output of the first light output unit and the second light output unit by allowing the first optical unit to be arranged selectively on a light path between the light source unit and the second optical unit. | 05-19-2016 |