Electronics and Telecommunications Research Institute

Yun Keun Lee

Jeon Gue Park

Ho Young Jung

Byung Ok Kang

Hoon Chung

Sung Joo Lee

Eui Sok Chung

Hwa Jeon Song

Hyun Woo Kim

Hyung Bae Jeon

Jeom Ja Kang

Ki Young Park

Young Kil Kim

Sang Kyu Park

Jong Jin Kim

Chang Hyun Kim

Sang Hun Kim

Oh Woog Kwon

Seung Yun

Min Kyu Lee

Ji Hyun Wang

Kap Kee Kim

Ho-Young Jung

Hyung-Bae Jeon

Mu Yeol Choi

Ki-young Park

Yoo Rhee Oh

Yeo Jeong Kim

Hoon Young Cho

Provided are an apparatus and method for providing a personal assistant service based on automatic translation. The apparatus for providing a personal assistant service based on automatic translation includes an input section configured to receive a command of a user, a memory in which a program for providing a personal assistant service according to the command of the user is stored, and a processor configured to execute the program. The processor updates at least one of a speech recognition model, an automatic interpretation model, and an automatic translation model on the basis of an intention of the command of the user using a recognition result of the command of the user and provides the personal assistant service on the basis of an automatic translation call.

Apparatus and method for providing personal assistant service based on automatic translation

Provided are an apparatus and method for a statistical memory network. The apparatus includes a stochastic memory, an uncertainty estimator configured to estimate uncertainty information of external input signals from the input signals and provide the uncertainty information of the input signals, a writing controller configured to generate parameters for writing in the stochastic memory using the external input signals and the uncertainty information and generate additional statistics by converting statistics of the external input signals, a writing probability calculator configured to calculate a probability of a writing position of the stochastic memory using the parameters for writing, and a statistic updater configured to update stochastic values composed of an average and a variance of signals in the stochastic memory using the probability of a writing position, the parameters for writing, and the additional statistics.

Apparatus and method for statistical memory network

Provided are sentence embedding method and apparatus based on subword embedding and skip-thoughts. To integrate skip-thought sentence embedding learning methodology with a subword embedding technique, a skip-thought sentence embedding learning method based on subword embedding and methodology for simultaneously learning subword embedding learning and skip-thought sentence embedding learning, that is, multitask learning methodology, are provided as methodology for applying intra-sentence contextual information to subword embedding in the case of subword embedding learning. This makes it possible to apply a sentence embedding approach to agglutinative languages such as Korean in a bag-of-words form. Also, skip-thought sentence embedding learning methodology is integrated with a subword embedding technique such that intra-sentence contextual information can be used in the case of subword embedding learning. A proposed model minimizes additional training parameters based on sentence embedding such that most training results may be accumulated in a subword embedding parameter.

Sentence embedding method and apparatus based on subword embedding and skip-thoughts

Provided are an apparatus and method for linearly approximating a deep neural network (DNN) model which is a non-linear function. In general, a DNN model shows good performance in generation or classification tasks. However, the DNN fundamentally has non-linear characteristics, and therefore it is difficult to interpret how a result from inputs given to a black box model has been derived. To solve this problem, linear approximation of a DNN is proposed. The method for linearly approximating a DNN model includes 1) converting a neuron constituting a DNN into a polynomial, and 2) classifying the obtained polynomial as a polynomial of input signals and a polynomial of weights.

Apparatus and method for linearly approximating deep neural network model

Provided is a method of automatically expanding input text. The method includes receiving input text composed of a plurality of documents, extracting a sentence pair that is present in different documents among the plurality of documents, setting the extracted sentence pair as an input of an encoder of a sequence-to-sequence model, setting an output of the encoder as an output of a decoder of the sequence-to-sequence model and generating a sentence corresponding to the input, and generating expanded text based on the generated sentence.

System and method for automatically expanding input text

The present invention relates to a method and apparatus for improving spontaneous speech recognition performance. The present invention is directed to providing a method and apparatus for improving spontaneous speech recognition performance by extracting a phase feature as well as a magnitude feature of a voice signal transformed to the frequency domain, detecting a syllabic nucleus on the basis of a deep neural network using a multi-frame output, determining a speaking rate by dividing the number of syllabic nuclei by a voice section interval detected by a voice detector, calculating a length variation or an overlap factor according to the speaking rate, and performing cepstrum length normalization or time scale modification with a voice length appropriate for an acoustic model.

Method and apparatus for improving spontaneous speech recognition performance

The present invention relates to a device of simultaneous interpretation based on real-time extraction of an interpretation unit, the device including a voice recognition module configured to recognize voice units as sentence units or translation units from vocalized speech that is input in real time, a real-time interpretation unit extraction module configured to form one or more of the voice units into an interpretation unit, and a real-time interpretation module configured to perform an interpretation task for each interpretation unit formed by the real-time interpretation unit extraction module.

Device and method of simultaneous interpretation based on real-time extraction of interpretation unit

An incremental self-learning based dialogue apparatus for dialogue knowledge includes a dialogue processing unit configured to determine a intention of a user utterance by using a knowledge base and perform processing or a response suitable for the user intention, a dialogue establishment unit configured to automatically learn a user intention stored in a intention annotated learning corpus, store information about the learned user intention in the knowledge base, and edit and manage the knowledge base and the intention annotated learning corpus, and a self-knowledge augmentation unit configured to store a log of a dialogue performed by the dialogue processing unit, detect and classify an error in the stored dialogue log, automatically tag a user intention for the detected and classified error, and store the tagged user intention in the intention annotated learning corpus.

Self-learning based dialogue apparatus and method for incremental dialogue knowledge

Provided are a signal processing algorithm-integrated deep neural network (DNN)-based speech recognition apparatus and a learning method thereof. A model parameter learning method in a deep neural network (DNN)-based speech recognition apparatus implementable by a computer includes converting a signal processing algorithm for extracting a feature parameter from a speech input signal of a time domain into signal processing deep neural network (DNN), fusing the signal processing DNN and a classification DNN, and learning a model parameter in a deep learning model in which the signal processing DNN and the classification DNN are fused.

Signal processing algorithm-integrated deep neural network-based speech recognition apparatus and learning method thereof

A speech recognition apparatus based on a deep-neural-network (DNN) sound model includes a memory and a processor. As the processor executes a program stored in the memory, the processor generates sound-model state sets corresponding to a plurality of pieces of set training speech data included in multi-set training speech data, generates a multi-set state cluster from the sound-model state sets, and sets the multi-set training speech data as an input node and the multi-set state cluster as output nodes so as to learn a DNN structured parameter.

Apparatus and method for recognizing speech based on a deep-neural-network (DNN) sound model

Provided is an apparatus for large vocabulary continuous speech recognition (LVCSR) based on a context-dependent deep neural network hidden Markov model (CD-DNN-HMM) algorithm. The apparatus may include an extractor configured to extract acoustic model-state level information corresponding to an input speech signal from a training data model set using at least one of a first feature vector based on a gammatone filterbank signal analysis algorithm and a second feature vector based on a bottleneck algorithm, and a speech recognizer configured to provide a result of recognizing the input speech signal based on the extracted acoustic model-state level information.

Apparatus and method for large vocabulary continuous speech recognition

A feature compensation apparatus includes a feature extractor configured to extract corrupt speech features from a corrupt speech signal with additive noise that consists of two or more frames; a noise estimator configured to estimate noise features based on the extracted corrupt speech features and compensated speech features; a probability calculator configured to calculate a correlation between adjacent frames of the corrupt speech signal; and a speech feature compensator configured to generate compensated speech features by eliminating noise features of the extracted corrupt speech features while taking into consideration the correlation between adjacent frames of the corrupt speech signal and the estimated noise features, and to transmit the generated compensated speech features to the noise estimator.

Feature compensation apparatus and method for speech recognition in noisy environment

Disclosed are a personalized advertisement device based on speech recognition SMS services and a personalized advertisement exposure method based on speech recognition SMS services. The present invention provides a personalized advertisement device based on speech recognition SMS services and a personalized advertisement exposure method based on speech recognition SMS services capable of maximizing an effect of advertisement by grasping user's intention, an emotion state, and positional information from speech data uttered by a user during a process of providing speech recognition SMS services, configuring advertisements from when speech data begins conversion to when it has been completely converted by the speech recognition into character strings, and exposing the configured advertisements to a user.

Personalized advertisement device based on speech recognition SMS service, and personalized advertisement exposure method based on partial speech recognition SMS service

Provided is a mobile communication terminal including: a camera module which captures an image of a set area; a microphone module which, when a sound including a voice of a user is input, extracts a sound level corresponding to the sound and a sound generating position; and a control module which estimates a position of a lip of the user from the image, extracts a voice level from the sound level corresponding to the position of the lip of the user and a voice generating position from the sound generating position, and recognizes the voice of the user based on at least one of the voice level and the voice generating position.

Mobile communication terminal and operating method thereof

Method of the present invention may include receiving speech feature vector converted from speech signal, performing first search by applying first language model to the received speech feature vector, and outputting word lattice and first acoustic score of the word lattice as continuous speech recognition result, outputting second acoustic score as phoneme recognition result by applying an acoustic model to the speech feature vector, comparing the first acoustic score of the continuous speech recognition result with the second acoustic score of the phoneme recognition result, outputting first language model weight when the first coustic score of the continuous speech recognition result is better than the second acoustic score of the phoneme recognition result and performing a second search by applying a second language model weight, which is the same as the output first language model, to the word lattice.

Growing community of inventors

Daejeon, South Korea

Yun Keun Lee