-
公开(公告)号：KR100911429B1
公开(公告)日：2009-08-11
申请号：KR1020070084301
申请日：2007-08-22
Applicant: 한국전자통신연구원
IPC: G10L21/0208 , G10L15/20 , G10L15/06
CPC classification number: G10L15/20
Abstract: 본 발명은 잡음 적응형 변별 학습 방법을 포함하는 잡음 적응형 음향 모델 생성 방법 및 장치에 관한 것으로서, 다양한 환경 잡음을 포함하는 대규모 음성 학습 데이터로부터 기본 음향 모델 파라미터를 생성하는 단계 및 상기 생성된 기본 음향 모델 파라미터를 입력받아 변별 학습 기법을 적용하여 실제 정용 환경에 적합한 적응형 음향 모델 파라미터를 생성하는 단계를 포함하는 잡음 적응형 음향 모델 생성 방법을 제공할 수 있다.
음향 모델, 환경 잡음-
公开(公告)号：KR1020090065746A
公开(公告)日：2009-06-23
申请号：KR1020070133217
申请日：2007-12-18
Applicant: 한국전자통신연구원
CPC classification number: G10L15/01
Abstract: A device and a method for evaluating performance of a speech recognition engine are provided to require no interference of a person in any noise environment by adjusting an SNR(Signal-to-Noise Ratio) based on free volume control of a speech sound in a speaker. An evaluation speech database(201) stores evaluation speeches. An automatic voice recognition evaluator(203) plays the stored evaluation speech. The automatic voice recognition evaluator transmits an answer list and an audio signal file of evaluation data when voice recognition control for the evaluation data is completed. A speech recognizer(207) recognizes voice, and stores a voice recognition result list and a voice signal file used in voice recognition. A performance evaluation block(209) evaluates performance of a voice recognizer by comparing the answer list and the audio file with the voice recognition result list and the voice signal file.
Abstract translation: 提供了一种用于评估语音识别引擎的性能的装置和方法，用于通过基于扬声器中的语音的自由音量控制来调整SNR（信噪比）来不要求任何噪声环境中的人的干扰 。 评价语音数据库（201）存储评价语句。 自动语音识别评估器（203）播放存储的评估语音。 当评估数据的语音识别控制完成时，自动语音识别评估器发送评估数据的答案列表和音频信号文件。 语音识别器（207）识别语音，并存储语音识别结果列表和用于语音识别的语音信号文件。 性能评估块（209）通过将应答列表和音频文件与语音识别结果列表和语音信号文件进行比较来评估语音识别器的性能。
-
公开(公告)号：KR1020090061566A
公开(公告)日：2009-06-16
申请号：KR1020080088318
申请日：2008-09-08
Applicant: 한국전자통신연구원
IPC: G10L15/20
Abstract: A microphone array-based voice recognition system and a target voice extracting method in the system are provided to automatically find out one target voice uttered for voice recognition by using an HMM(Hidden Markov Model) and a GMM(Gaussian Mixture Model), thereby obtaining a higher recognition rate even in case of noise existence. A signal separator(110) separates mixed signals individually inputted through plural microphones into sound source signals through independent component analysis. A target voice extractor(120) extracts one target voice uttered for voice recognition among the separated sound source signals. A voice recognizer(130) recognizes a desired voice through the extracted target voice. An additional information unit transmits additional information used for the extraction of the target voice to the target voice extractor.
Abstract translation: 提供了一种基于麦克风阵列的语音识别系统和系统中的目标语音提取方法，通过使用HMM（隐马尔可夫模型）和GMM（高斯混合模型）自动找出发出语音识别的一个目标语音，从而获得 甚至在噪声存在的情况下也具有更高的识别率。 信号分离器（110）通过独立分量分析将通过多个麦克风分别输入的混合信号分离成声源信号。 目标语音提取器（120）在分离的声源信号之间提取用于语音识别发出的一个目标语音。 语音识别器（130）通过所提取的目标语音来识别期望的语音。 附加信息单元将用于提取目标语音的附加信息发送到目标语音提取器。
-
公开(公告)号：KR1020080052279A
公开(公告)日：2008-06-11
申请号：KR1020070074287
申请日：2007-07-25
Applicant: 한국전자통신연구원
IPC: H04N21/43 , H04N21/2343
Abstract: An interactive TV agency service method for providing real-life information and an apparatus therefor are provided to acquire real-life information updated on a web in real time and expand the acquired information to various region when necessary by performing operation for which a user wishes through an interactive interface including a voice, a remote controller, and a text input and providing a corresponding suitable response. A dialogue sentence analyzing unit(20) analyzes an input sentence received from a user. A dialogue management unit(30) analyzes the request of the user by using the analyzed result of the dialogue sentence analyzing unit. When a real-time information update is requested from the dialogue management unit, a real-time automatic knowledge constructing unit(70) extracts daily life information updated on a web in real time and stores the extracted information in a daily information database. A response generating unit(40) generates a response for the request of the user analyzed in the dialogue management unit and provides the response to the user. When it is impossible to respond to the request of the user or an error is generated in the response for the request of the user, an exception processing unit(80) recovers a system to allow the user to cancel the request of the user.
Abstract translation: 提供用于提供现实生活信息的交互式电视机构服务方法及其装置，用于获取在网络上实时更新的现实生活信息，并且在必要时通过执行用户期望的操作将获取的信息扩展到各个区域 包括语音，遥控器和文本输入的交互式界面，并提供对应的合适响应。 对话句分析单元（20）分析从用户接收的输入语句。 对话管理单元（30）通过使用对话句分析单元的分析结果来分析用户的请求。 当从对话管理单元请求实时信息更新时，实时自动知识构建单元（70）实时地提取在web上更新的日常生活信息，并将提取的信息存储在日常信息数据库中。 响应生成单元（40）生成对话管理单元中分析的用户的请求的响应，并向用户提供响应。 当不可能响应于用户的请求或在针对用户的请求的响应中产生错误时，异常处理单元（80）恢复系统以允许用户取消用户的请求。
-
-
Patent Agency Ranking
-
-
-
公开(公告)号：KR101892736B1
公开(公告)日：2018-08-28
申请号：KR1020150035245
申请日：2015-03-13
Applicant: 한국전자통신연구원
IPC: G10L15/01 , G10L15/06 , G10L15/14 , G10L15/187
Abstract: 본발명에따른대용량음성인식시스템의실시간단어별지속시간모델링을이용한발화검증장치는수신된훈련신호의음소별지속시간의평균, 단어별지속시간의평균및 분산을계산하고, 상기단어별지속시간의평균및 분산의관계를회귀분석으로모델링하여회귀모델을생성하는훈련신호관리부, 수신된음성신호를문맥종속음소모델에적용하여음성인식결과를출력하는음성신호처리부및 기설정된단어빈도수의임계치에기초하여상기단어별지속시간의평균및 분산또는음소별지속시간의평균및 회귀모델에기초하여신뢰도측정값을생성하는발화검증부를포함한다.
-
公开(公告)号：KR101892095B1
公开(公告)日：2018-08-28
申请号：KR1020130119607
申请日：2013-10-08
Applicant: 한국전자통신연구원
Abstract: 다중음향공간 GMM을이용한음향모델생성방법이개시된다. 본발명에따른다중음향공간 GMM을이용한음향모델생성방법은소량의음성데이터베이스를수집하는단계; 상기음성데이터베이스를이용하여 n개의기존음향모델들에서통계정보를산출하는단계; 상기산출한통계정보및 상기 n개의기존음향모델들의통합규칙(tying rule)을기초로하여최적모델단위를결정하는단계; 상기 n개의기존음향모델들을 1 가우시안혼합모델(1 Gaussian mixture model)과각각혼합하여가우시안혼합수를증가시킨 n개의 n 가우시안혼합모델들을생성하는단계; 상기최적모델단위를상기 n개의 n 가우시안혼합모델들을결합한결과에적용하여최종가우시안혼합모델을생성하는단계; 및상기최종가우시안혼합모델을각 모델단위로구성하는최종음향모델의변별학습결과를기초로하여상기최종가우시안혼합모델간의최적가중치를계산하는단계를포함한다.
-
-
-
-
-
-
-
-
-
Search Results
210
records
(took 0.019 seconds)
