An apparatus and method for detecting a named-entity. The apparatus includes a candidate-named-entity extraction module that detects a candidate-named-entity based on an initial learning example and feature information regarding morphemes constituting an inputted sentence, the candidate-named-entity extraction module providing a tagged sentence including the detected candidate-named-entity; a storage module that stores information regarding a named-entity dictionary and a rule; and a learning-example-regeneration module for finally determining whether the candidate-named-entity included in the provided sentence is a valid named-entity, based on the named-entity dictionary and the rule, the learning-example-regeneration module providing the sentence as a learning example, based on a determination result, so that a probability of candidate-named-entity detection is gradually updated.

Apparatus and method for detecting named entity

Purpose To provide a brief history of speech comprehension training systems and an overview of research on auditory and cognitive aging as background to recommendations for future directions for re...

Speech Comprehension Training and Auditory and Cognitive Processing in Older Adults

Systems and methods for multi-sourced noise suppression are provided. An example system may receive streams of audio data including a voice signal and noise, the voice signal including a spoken word. The streams of audio data are provided by distributed audio devices. The system can assign weights to the audio streams based at least partially on quality of the audio streams. The weights of audio streams can be determined based on signal-to-noise ratios (SNRs). The system may further process, based on the weights, the audio stream to generate cleaned speech. Each audio device comprises microphone(s) and can be associated with the Internet of Things (IoT), such that the audio devices are Internet of Things devices. The processing can include noise suppression and reduction and echo cancellation. The cleaned speech can be provided to a remote device for further processing which may include Automatic Speech Recognition (ASR).

Multi-Sourced Noise Suppression

A “Sensor Array Post-Filter” provides an adaptive post-filter that accurately models and suppresses both diffuse and directional noise sources as well as interfering speech sources. The post-filter is applied to an output signal produced by a beamformer used to process signals produced by a sensor array. As a result, the Sensor Array Post-Filter operates to improve the signal-to-noise ratio (SNR) of beamformer output signals by providing adaptive post-filtering of the output signals. The post-filter is generated based on a generative statistical model for modeling signal and noise sources at distinct regions in a signal field that considers prior distributions trained to model an instantaneous direction of arrival for signals captured by sensors in the array.

Sensor array post-filter for tracking spatial distributions of signals and noise

Described are noise suppression techniques applicable to various systems including automatic speech processing systems in digital audio pre-processing. The noise suppression techniques utilize a machine-learning framework trained on cues pertaining to reference clean and noisy speech signals, and a corresponding synthetic noisy speech signal combining the clean and noisy speech signals. The machine-learning technique is further used to process audio signals in real time by extracting and analyzing cues pertaining to noisy speech to dynamically generate an appropriate gain mask, which may eliminate the noise components from the input audio signal. The audio signal pre-processed in such a manner may be applied to an automatic speech processing engine for corresponding interpretation or processing. The machine-learning technique may enable extraction of cues associated with clean automatic speech processing features, which may be used by the automatic speech processing engine for various automatic speech processing.

Noise suppression for speech processing based on machine-learning mask estimation

A method and apparatus estimate additive noise in a noisy signal using incremental Bayes learning, where a time-varying noise prior distribution is assumed and hyperparameters (mean and variance) are updated recursively using an approximation for posterior computed at the preceding time step. The additive noise in time domain is represented in the log-spectrum or cepstrum domain before applying incremental Bayes learning. The results of both the mean and variance estimates for the noise for each of separate frames are used to perform speech feature enhancement in the same log-spectrum or cepstrum domain.

Method of noise estimation using incremental bayesian learning

Method of proceeding noise estimation using increment bayes lerning

PURPOSE: A noise estimation method using incremental Bayes learning is provided to estimate noise in signals used for pattern recognition based on Gaussian approximation of data likelihood for the current frame and Gaussian approximation of noise in the sequence of previous frames. CONSTITUTION: A system for estimating noise of a pattern recognition signal estimates the noise using a recursive algorithm that estimates noise of each frame of a noise signal on the basis of a part of a noise estimate value based on at least one adjacent frame. The system carries out noise estimation for a single frame using incremental Bayes learning that takes time-varying noise prior distribution and recursively updates a noise estimate value using posteriori noise approximation calculated in a previous frame(302). Through the recursive process, the noise estimate value tracks nonstationary noise.

Deng Li

Papers

Method of noise estimation using incremental bayesian learning

Method of proceeding noise estimation using increment bayes lerning

Noise estimation method using incremental bayes learning for estimating noise in signal used for pattern recognition