Samsung Electronics Co., Ltd.

Seoul National University

Jung-Hoe Kim

Eun-mi Oh

Ki-hyun Choo

Ho-sang Sung

Yeong-Kyeong Seong

Baek-Hwan Cho

Ki Hyun Choo

Miyoung Kim

Eunmi Oh

Eun Mi Oh

Mi-young Kim

Konstantly Osipov

Kyoung Gu Woo

Anton Porov

Ye-hoon Kim

Moon-ho Park

Jehun Jeon

Sin-Sang Yu

Konstantin Sergeevich Osipov

Boris D Kudryashov

Chang Yong Son

Kihyun Choo

Ho-Sang Sung

Myung-Eun Lee

Jong-Hyo Kim

Hyeong-Min Jin

Olga Prokofyeva

Ki-Hyun Choo

Ho Sang Subg

Lei Miao

Chang-Yong Son

Kang-Eun Lee

Seung-Tai Kim

Eun-Mi Oh

A voice recognition apparatus and corresponding method include a processor configured to calculate a probability distribution corresponding to an intent associated with an utterance of a user by applying pre-stored training data to an input voice signal input based on the utterance. The processor is also configured to select a target feature extractor including either one or both of a training-based feature extractor and a rule-based feature extractor using the calculated probability distribution, and extract a feature associated with the utterance based on the selected target feature extractor.

Voice recognition apparatus and method

An intention analysis apparatus includes an extractor configured to extract a feature value from a text input corresponding to machine recognition of an audio signal, a verifier configured to verify at least one state value associated with at least one of the text input or the audio signal, and a trained calculator configured to calculate a probability distribution of a user intention corresponding to the audio signal based on the feature value and the at least one state value.

A method and apparatus to encoding or decoding an audio signal is provided. In the method and apparatus, a noise-floor level to use in encoding or decoding a high frequency signal is updated according to the degree of a voiced or unvoiced sound included in the signal.

Apparatus, medium and method to encode and decode high frequency signal

An apparatus and method for medical diagnostics includes receiving three-dimensional (3D) volume data of a part of a patient's body, and generating two-dimensional (2D) slices including cross-sections of the 3D volume data cut from a cross-section cutting direction. The apparatus and the method also determine whether a lesion in each of the 2D slices is benign or malignant and output results indicative thereof, select a number of the 2D slices based on the results, and make a final determination whether the lesion is benign or malignant based on the selected 2D slices.

Apparatus and method for computer-aided diagnosis

A context-based arithmetic encoding apparatus and method and a context-based arithmetic decoding apparatus and method are provided. The context-based arithmetic decoding apparatus may determine a context of a current N-tuple to be decoded, determine a Most Significant Bit (MSB) context corresponding to an MSB symbol of the current N-tuple, and determine a probability model using the context of the N-tuple and the MSB context. Subsequently, the context-based arithmetic decoding apparatus may perform a decoding on an MSB based on the determined probability model, and perform a decoding on a Least Significant Bit (LSB) based on a bit depth of the LSB derived from a process of decoding on an escape code.

Context-based arithmetic encoding apparatus and method and context-based arithmetic decoding apparatus and method

Provided is an encoding/decoding apparatus and method of multi-channel signals. The encoding apparatus and method of multi-channel signals may encode phase information of the multi-channel signals using a quantization scheme and a lossless encoding scheme, and the decoding apparatus and method of multi-channel signals may decode the phase information using an inverse-quantization scheme and a lossless decoding scheme.

Apparatus for encoding/decoding multichannel signal and method thereof

An apparatus and method are provided including a first segmenter and a second segmenter. The first segmenter is configured to generate a first segmentation result from a medical image using a first segmentation parameter for a candidate lesion. The second segmenter is configured to determine a target lesion to segment from among the candidate lesion based on the first segmentation result, and generate a second segmentation result using a second segmentation parameter to segment the target lesion.

Apparatus and method for lesion segmentation and detection in medical images

Provided are an encoding apparatus and a decoding apparatus of a multi-channel signal. The encoding apparatus of the multi-channel signal may process a phase parameter associated with phase information between a plurality of channels constituting the multi-channel signal, based on a characteristic of the multi-channel signal. The encoding apparatus may generate an encoded bitstream with respect to the multi-channel signal using the processed phase parameter and a mono signal extracted from the multi-channel signal.

Apparatus and method for encoding and decoding multi-channel signal

An apparatus and method for detecting a lesion, which enables to adaptively determine a parameter value of a lesion detection process using a feature value extracted from a received medical image and a parameter prediction model to improve accuracy in lesion detection and lesion diagnosis. The apparatus and the method include a model generator configured to generate a parameter prediction model based on pre-collected medical images, an extractor configured to extract a feature value from a received medical image, and a determiner configured to determine a parameter value of a lesion detection process using the extracted feature value and the parameter prediction model.

Apparatus and method for detecting lesion

Disclosed are a context-based arithmetic encoding apparatus and method and a context-based arithmetic decoding apparatus and method. The context-based arithmetic decoding apparatus may determine a context of a current N-tuple to be decoded, determine a Most Significant Bit (MSB) context corresponding to an MSB symbol of the current N-tuple, and determine a probability model using the context of the N-tuple and the MSB context. Subsequently, the context-based arithmetic decoding apparatus may perform a decoding on an MSB based on the determined probability model, and perform a decoding on a Least Significant Bit (LSB) based on a bit depth of the LSB derived from a process of decoding on an escape code.

Growing community of inventors

Seongnam-si, South Korea

Jung-Hoe Kim