Abstract: Provided is a speech recognition method using machine learning, including: receiving a speech signal as an input, performing speech recognition to generate speech recognition result information including multiple candidate sentences and ranks of the respective candidate sentences; processing the multiple candidate sentences included in the speech recognition result information according to a machine learning model which is learned in advance and changing the ranks of the multiple candidate sentences to re-rank the multiple candidate sentences; and selecting the highest-rank candidate sentence among the re-ranked multiple candidate sentences as a speech recognition result.

Abstract: Provided is a speech recognition method using machine learning, including: receiving a speech signal as an input, performing speech recognition to generate speech recognition result information including multiple candidate sentences and ranks of the respective candidate sentences; processing the multiple candidate sentences included in the speech recognition result information according to a machine learning model which is learned in advance and changing the ranks of the multiple candidate sentences to re-rank the multiple candidate sentences; and selecting the highest-rank candidate sentence among the re-ranked multiple candidate sentences as a speech recognition result.

Abstract: According to certain embodiments, a method and apparatus for preventing incorrect input in a portable terminal includes identifying an input character string and, among previously registered candidate words, searching among a plurality of candidate words recommended for the input character string, calculating a similarity between the input character string and each of the searched candidate words, and presenting one or more of the searched candidate words in order of descending similarity associated with the one or more searched candidate words.

Abstract: A spelling correction system and method automatically recognizes and corrects misspelled inputs in an electronic device with relatively lower computing power. In a learning process, a misspelling correction dictionary is constructed on the basis of a corpus of accepted words, and context-sensitive strings are selected from among all the strings registered in the dictionary. Context information about the context-sensitive strings is acquired. In an applying process, at least one target string is selected from among all the strings in a user's input sentence through the dictionary. If the target string is one of the context-sensitive strings, the target string is corrected by use of the context information.

Abstract: According to certain embodiments, a method and apparatus for preventing incorrect input in a portable terminal includes identifying an input character string and, among previously registered candidate words, searching among a plurality of candidate words recommended for the input character string, calculating a similarity between the input character string and each of the searched candidate words, and presenting one or more of the searched candidate words in order of descending similarity associated with the one or more searched candidate words.

Abstract: A word-spacing correction system and method are provided to automatically recognize and correct errors in the spacing of word inputs in an electronic device with relatively low computing power. In a learning process, probability information about each feature is created from a corpus of correct words, and then error correction rules are created by applying the probability information to a corpus of incorrect words from which all spaces between words of the corpus of correct words are removed. In an applying process, word-spacing in a user's input sentence is corrected by applying the probability information and the error correction rules to the user's input sentence.

Abstract: A host apparatus for wirelessly communicating with a headset by Bluetooth® is provided. An audio Digital Signal Processor (DSP) performs Pulse Code Modulation (PCM) on sound source data when a type of the headset is a mono headset. The audio DSP performs Universal Asynchronous Receiver Transmitter (UART) modulation on the sound source data when a type of the headset is not a mono headset. A Bluetooth® communication unit transmits the data modulated by the audio DSP to the headset.

Abstract: A word-spacing correction system and method are provided to automatically recognize and correct errors in the spacing of word inputs in an electronic device with relatively low computing power. In a learning process, probability information about each feature is created from a corpus of correct words, and then error correction rules are created by applying the probability information to a corpus of incorrect words from which all spaces between words of the corpus of correct words are removed. In an applying process, word-spacing in a user's input sentence is corrected by applying the probability information and the error correction rules to the user's input sentence.

Abstract: A spelling correction system and method automatically recognizes and corrects misspelled inputs in an electronic device with relatively lower computing power. In a learning process, a misspelling correction dictionary is constructed on the basis of a corpus of accepted words, and context-sensitive strings are selected from among all the strings registered in the dictionary. Context information about the context-sensitive strings is acquired. In an applying process, at least one target string is selected from among all the strings in a user's input sentence through the dictionary. If the target string is one of the context-sensitive strings, the target string is corrected by use of the context information.

Abstract: An apparatus and method for controlling automatic reserved recording in a broadcast-receiving terminal, in which a reserved recording function can be performed at accurate time based on a time difference between communication time for communication and broadcasting time, is provided.

Abstract: An audio output apparatus having an audio codec for generating audio signals delivered to a speaker is provided with a device for preventing an audio pop noise caused by the bias voltage output from the audio codec, which includes a capacitor connected between an output end of the audio codec and the speaker, a capacitor charger for smoothly charging the capacitor to a predetermined voltage level, a switch arranged between the junction of the output end of the audio codec and the capacitor and the capacitor charger, and a control unit for controlling the codec, wherein the control unit turns on the switch and drives the capacitor charger before activating the audio codec, and then turns off the switch and terminates the operation of the capacitor charger if a predetermined charging time has elapsed.

Abstract: There is provided a power rate enhancement circuit for a power amplifier in a dual mode mobile phone including an RF power amplifier for amplifying an RF input signal, a duplexer connected to an antenna, and an isolator connected to the duplexer. The power enhancement circuit also comprises: a CDMA matching circuit connected to an output end of the RF power amplifier, for matching an output impedance of the RF power amplifier in a CDMA mode of operation; an AMPS matching circuit connected to the output end of the RF power amplifier, for matching the output impedance of the RF power amplifier in an AMPS mode of operation; and an RF switch for selecting the CDMA matching circuit or the AMPS matching circuit according to a mode control signal. The CDMA matching circuit comprises an inductor connected between the output end of the RF power amplifier and the isolator. The AMPS matching circuit comprises a capacitor connected between the RF switch and a contact point formed between the inductor and the isolator.

Abstract: There is provided a power rate enhancement circuit for a power amplifier in a dual mode mobile phone including an RF power amplifier for amplifying an RF input signal, a duplexer connected to an antenna, and an isolator connected to the duplexer. The power enhancement circuit also comprises: a CDMA matching circuit connected to an output end of the RF power amplifier, for matching an output impedance of the RF power amplifier in a CDMA mode of operation; an AMPS matching circuit connected to the output end of the RF power amplifier, for matching the output impedance of the RF power amplifier in an AMPS mode of operation; and an RF switch for selecting the CDMA matching circuit or the AMPS matching circuit according to a mode control signal. The CDMA matching circuit comprises an inductor connected between the output end of the RF power amplifier and the isolator. The AMPS matching circuit comprises a capacitor connected between the RF switch and a contact point formed between the inductor and the isolator.