Abstract: An apparatus for calculating acoustic score, a method of calculating acoustic score, an apparatus for speech recognition, a method of speech recognition, and an electronic device including the same are provided. An apparatus for calculating acoustic score includes a preprocessor configured to sequentially extract audio frames into windows and a score calculator configured to calculate an acoustic score of a window by using a deep neural network (DNN)-based acoustic model.

Abstract: A speech signal recognition method, apparatus, and system. The speech signal recognition method may include obtaining by or from a terminal an output of a personalization layer, with respect to a speech signal provided by a user of the terminal, having been implemented by input of the speech signal to the personalization layer, the personalization layer being previously trained based on speech features of the user, implementing a global model by providing the obtained output of the personalization layer to the global model, the global model being configured to output a phonemic signal indicating a phoneme included in the speech signal through the global model being previously trained based on speech features common to a plurality of users, and re-training the personalization layer based on the phonemic signal output from the global model, where the personalization layer and the global model collectively represent an acoustic model.

Abstract: An apparatus for notification of speech of interest to a user includes a voice analyzer configured to recognize speech, evaluate a relevance between a result of the speech recognition and a determined user's topic of interest, and determine whether to provide a notification; and an outputter configured to, in response to the voice analyzer determining to provide the notification, generate and output a notification message.

Abstract: A speech signal recognition method, apparatus, and system. The speech signal recognition method may include obtaining by or from a terminal an output of a personalization layer, with respect to a speech signal provided by a user of the terminal, having been implemented by input of the speech signal to the personalization layer, the personalization layer being previously trained based on speech features of the user, implementing a global model by providing the obtained output of the personalization layer to the global model, the global model being configured to output a phonemic signal indicating a phoneme included in the speech signal through the global model being previously trained based on speech features common to a plurality of users, and re-training the personalization layer based on the phonemic signal output from the global model, where the personalization layer and the global model collectively represent an acoustic model.

Abstract: A machine translation method includes converting a source sentence written in a first language to language-independent information using an encoder for the first language, and converting the language-independent information to a target sentence corresponding to the source sentence and written in a second language different from the first language using a decoder for the second language. The encoder for the first language is trained to output language-independent information corresponding to the target sentence in response to an input of the source sentence.

Abstract: A speech recognition method includes generating pieces of candidate text data from a speech signal of a user, determining a decoding condition corresponding to an utterance type of the user, and determining target text data among the pieces of candidate text data by performing decoding based on the determined decoding condition.

Abstract: An apparatus for normalizing input data of an acoustic model includes a window extractor configured to extract windows of frame data to be input to an acoustic model from frame data of a speech to be recognized, and a normalizer configured to normalize the frame data to be input to the acoustic model in units of the extracted windows.

Abstract: A voice command recognition apparatus and method thereof are described. The voice command recognition apparatus includes audio sensors placed at different locations; a context determiner configured to determine user context based on a voice received at the audio sensors, wherein the context comprises a vocalization from a user. A command recognizer in the voice command recognition apparatus is configured to activate to recognize a voice command or remain inactive according to the recognized context.

Abstract: An apparatus for extracting a peak image includes an image selector configured to select one of continuously photographed images; a base image determiner configured to determine at least one base image according to a predetermined criterion; a difference calculator configured to calculate a difference between the selected image and the at least one base image; and a peak image determiner configured to determine a peak image among the continuously photographed images based on the calculated difference.

Abstract: A machine translation method includes converting a source sentence written in a first language to language-independent information using an encoder for the first language, and converting the language-independent information to a target sentence corresponding to the source sentence and written in a second language different from the first language using a decoder for the second language. The encoder for the first language is trained to output language-independent information corresponding to the target sentence in response to an input of the source sentence.

Abstract: A method and a device of voice recognition are provided. The method involves receiving a voice signal, identifying a first voice recognition model in which context information associated with a situation at reception of the voice signal is not reflected and a second voice recognition model in which the context information is reflected, determining a weighted value of the first voice recognition model and a weighted value of the second voice recognition model, and recognizing a word in the voice signal by applying the determined weighted values to the first voice recognition model and the second voice recognition model.

Abstract: A method and apparatus for speech recognition and for generation of speech recognition engine, and a speech recognition engine are provided. The method of speech recognition involves receiving a speech input, transmitting the speech input to a speech recognition engine, and receiving a speech recognition result from the speech recognition engine, in which the speech recognition engine obtains a phoneme sequence from the speech input and provides the speech recognition result based on a phonetic distance of the phoneme sequence.

Abstract: An apparatus for normalizing input data of an acoustic model includes a window extractor configured to extract windows of frame data to be input to an acoustic model from frame data of a speech to be recognized, and a normalizer configured to normalize the frame data to be input to the acoustic model in units of the extracted windows.

Abstract: An apparatus and method for recognizing a speech, and an apparatus and method for generating a noise-speech recognition model are provided. The speech recognition apparatus includes a location determiner configured to determine a location of the apparatus, a noise model generator configured to generate a noise model corresponding to the location by collecting noise data related to the location, and a noise model transmitter configured to transmit the noise model to a server.

Abstract: An apparatus for calculating acoustic score, a method of calculating acoustic score, an apparatus for speech recognition, a method of speech recognition, and an electronic device including the same are provided. An apparatus for calculating acoustic score includes a preprocessor configured to sequentially extract audio frames into windows and a score calculator configured to calculate an acoustic score of a window by using a deep neural network (DNN)-based acoustic model.

Abstract: An apparatus for notification of speech of interest to a user includes a voice analyzer configured to recognize speech, evaluate a relevance between a result of the speech recognition and a determined user's topic of interest, and determine whether to provide a notification; and an outputter configured to, in response to the voice analyzer determining to provide the notification, generate and output a notification message.

Abstract: An apparatus for extracting a peak image includes an image selector configured to select one of continuously photographed images; a base image determiner configured to determine at least one base image according to a predetermined criterion; a difference calculator configured to calculate a difference between the selected image and the at least one base image; and a peak image determiner configured to determine a peak image among the continuously photographed images based on the calculated difference.

Abstract: A method and apparatus for speech recognition and for generation of speech recognition engine, and a speech recognition engine are provided. The method of speech recognition involves receiving a speech input, transmitting the speech input to a speech recognition engine, and receiving a speech recognition result from the speech recognition engine, in which the speech recognition engine obtains a phoneme sequence from the speech input and provides the speech recognition result based on a phonetic distance of the phoneme sequence.

Abstract: A method and a device of voice recognition are provided. The method involves receiving a voice signal, identifying a first voice recognition model in which context information associated with a situation at reception of the voice signal is not reflected and a second voice recognition model in which the context information is reflected, determining a weighted value of the first voice recognition model and a weighted value of the second voice recognition model, and recognizing a word in the voice signal by applying the determined weighted values to the first voice recognition model and the second voice recognition model.

Abstract: A method of providing a user interface (UI), includes generating first feature information indicating a feature of a voice signal, and converting the voice signal to a first text. The method further includes visually changing the first text based on the first feature information, and providing the UI displaying the changed first text.