公开(公告)号：KR1020080010167A

公开(公告)日：2008-01-30

申请号：KR1020060070305

申请日：2006-07-26

Applicant: 한국정보통신대학교 산학협력단

Inventor： 서영주 ,  김회린 ,  김성탁

IPC: G10L15/04 ,  G10L15/28 ,  G10L25/03

Abstract: A system and a method for recognizing a voice by using class-based histogram equalization are provided to bring plural classes to a voice characteristic parameter and perform the histogram equalization by class, thereby preventing the performance of the voice recognition system from being deteriorated by effectively reducing sound discordance existing in a sound characteristic parameter. A system for recognizing a voice comprises a characteristic extractor(101), a characteristic corrector(102), and a voice recognizer(103). The characteristic extractor divides a digital voice signal into a frame unit with regular time intervals and extracts a sound characteristic parameter. The characteristic corrector generates characteristic correction components by class by multiplying each class weight after applying histogram equalization to the characteristic parameter, and obtains a characteristic parameter where sound discordance is corrected by adding the entire characteristic correction components by class to the characteristic correction components by class. The voice recognizer performs voice recognition from the corrected characteristic parameter.

Abstract translation: 提供一种通过使用基于类的直方图均衡来识别语音的系统和方法，以使多个等级成为语音特征参数，并且按类进行直方图均衡，从而通过有效地减少语音识别系统的性能而不会恶化 声音特征参数中存在声音不一致。 用于识别语音的系统包括特征提取器（101），特征校正器（102）和语音识别器（103）。 特征提取器将数字语音信号以规则的时间间隔划分成帧单元并提取声音特性参数。 特征校正器通过将直方图均衡后的每个等级权重与特征参数相乘来生成特征校正分量，并且通过将类别的整个特征校正分量通过类别添加到特征校正分量中来获得校正声音不一致的特性参数。 语音识别器从校正的特征参数执行语音识别。

公开(公告)号：KR100808775B1

公开(公告)日：2008-03-07

申请号：KR1020060070305

申请日：2006-07-26

Applicant: 한국정보통신대학교 산학협력단

Inventor： 서영주 ,  김회린 ,  김성탁

IPC: G10L15/04 ,  G10L15/28 ,  G10L25/03

Abstract: 본 발명은 클래스 기반 히스토그램 등화 기법을 이용한 음성인식 시스템 및 방법에 관한 것으로, 음성인식 시스템은 디지털 음성신호를 일정한 시간 간격의 프레임 단위로 분할하고, 프레임마다 음향 특징 파라메터를 추출하는 특징추출기, 특징 파라메터에 대해 클래스별로 히스토그램 등화 기법을 적용한 후 각 클래스 가중치를 곱하여 각 클래스별 특징 보상 성분을 생성하고, 전체 클래스별 특징 보상 성분을 가산하여 음향 불일치가 보상된 특징 파라메터를 구하는 특징보상기 및, 보상된 특징 파라메터로부터 음성인식을 수행하는 음성인식기를 구비한다.
음성인식, 음향 특징 파라메터 보상, 히스토그램 등화, 클래스

公开(公告)号：KR100774800B1

公开(公告)日：2007-11-07

申请号：KR1020060085461

申请日：2006-09-06

Applicant: 한국정보통신대학교 산학협력단

Inventor： 서영주 ,  김회린 ,  지미경

IPC: G10L25/93

Abstract: A segment-unit voice/non-voice classification method using a Poisson polling method and an apparatus therefor are provided to classify whether an input signal in a segment interval is a voice or a non-voice accurately and need only a memory of a low calculation quantity and low capacity. A signal input device(100) receives a voice or non-voice signal, and converts the received voice or non-voice signal into a digital signal. A feature extractor(101) classifies the digital signal inputted from the signal input device(100) by a frame unit, and extracts a feature parameter per frame. A score converter(102) receives the feature parameter of the frame unit extracted in the feature extractor(101), compares the received feature parameter with a voice and non-voice pattern, and converts voice or non-voice degree into a score. A score quantizer(103) quantizes the scores obtained in the score converter(102). A voice/non-voice classifier(104) judges whether an input signal is a voice/non-voice per segment on the basis of a Poisson polling method from the score of the frame unit and the quantized scores inputted from the score converter(102) and the score quantizer(103). An output device(105) outputs voice/non-voice information judged in the voice/non-voice classifier(104).

Abstract translation: 提供一种使用泊松轮询方法的分段单元语音/非语音分类方法及其装置，用于分类段间隔中的输入信号是语音还是非语音，并且仅需要低计算的存储器 数量少，容量低。 信号输入装置（100）接收语音或非话音信号，并将接收到的语音或非话音信号转换为数字信号。 特征提取器（101）将从信号输入装置（100）输入的数字信号分类为帧单位，并且提取每帧的特征参数。 分数转换器（102）接收在特征提取器（101）中提取的帧单元的特征参数，将接收的特征参数与语音和非语音模式进行比较，并将语音或非语音程度转换为分数。 得分量化器（103）对得分转换器（102）中获得的得分进行量化。 语音/非语音分类器（104）基于来自帧单位的分数的泊松轮询方法和从分数转换器（102）输入的量化分数来判断输入信号是每个分段的语音/非语音 ）和分数量化器（103）。 输出设备（105）输出在语音/非语音分类器（104）中判断的语音/非语音信息。