Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 25.01.2022 at 12:00 PM CET
Settings

Settings

Goto Application

1. WO2015068947 - SYSTEM FOR ANALYZING SPEECH CONTENT ON BASIS OF EXTRACTION OF KEYWORDS FROM RECORDED VOICE DATA, INDEXING METHOD USING SYSTEM AND METHOD FOR ANALYZING SPEECH CONTENT

Publication Number WO/2015/068947
Publication Date 14.05.2015
International Application No. PCT/KR2014/008706
International Filing Date 18.09.2014
IPC
G10L 15/28 2013.1
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
28Constructional details of speech recognition systems
G10L 15/08 2006.1
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
CPC
G06F 16/328
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
30of unstructured textual data
31Indexing; Data structures therefor; Storage structures
316Indexing structures
328Management therefor
G06F 16/61
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
60of audio data
61Indexing; Data structures therefor; Storage structures
G06F 16/638
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
60of audio data
63Querying
638Presentation of query results
G06F 16/683
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
60of audio data
68Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
683using metadata automatically derived from the content
G10L 15/01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
01Assessment or evaluation of speech recognition systems
G10L 15/08
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
Applicants
  • 주식회사 시스트란인터내셔널 SYSTRAN INTERNATIONAL CO., LTD. [KR]/[KR]
Inventors
  • 지창진 JI, Chang Jin
Agents
  • 유미특허법인 YOU ME PATENT AND LAW FIRM
Priority Data
10-2013-013424606.11.2013KR
Publication Language Korean (ko)
Filing Language Korean (KO)
Designated States
Title
(EN) SYSTEM FOR ANALYZING SPEECH CONTENT ON BASIS OF EXTRACTION OF KEYWORDS FROM RECORDED VOICE DATA, INDEXING METHOD USING SYSTEM AND METHOD FOR ANALYZING SPEECH CONTENT
(FR) SYSTÈME D'ANALYSE DE CONTENU VOCAL REPOSANT SUR L'EXTRACTION DE MOTS-CLÉS À PARTIR DE DONNÉES VOCALES ENREGISTRÉES, PROCÉDÉ D'INDEXATION À L'AIDE DU SYSTÈME ET PROCÉDÉ D'ANALYSE DE CONTENU VOCAL
(KO) 녹취된 음성 데이터에 대한 핵심어 추출 기반 발화 내용 파악 시스템과, 이 시스템을 이용한 인덱싱 방법 및 발화 내용 파악 방법
Abstract
(EN) Disclosed are a system for analyzing speech content on the basis of the extraction of keywords from recorded voice data, an indexing method using the system and a method for analyzing speech content. An indexing unit of the system receives the voice data and forms a phoneme lattice by performing a phoneme-based voice recognition by frame unit, generates indexing information partitioned for a time limit frame comprising the plurality of frames and then stores the indexing information in an indexing database, wherein the partitioned indexing information includes the phoneme lattices formed for each time limit frame. A searching unit searches a phoneme string matching a search word through a phoneme-based comparison on the partitioned indexing information stored in the indexing database by using, as the search word, the keyword inputted from a user, and finds out a voice portion corresponding to the search word through a precise acoustical analysis on the matching phoneme string. An analyzing unit analyzes a subject word through the search result searched by the searching unit and then outputs the subject word to the user so as to enable the user to understand the speech content of the voice data.
(FR) La présente invention concerne un système d'analyse de contenu vocal reposant sur l'extraction de mots-clés à partir de données vocales enregistrées, un procédé d'indexation à l'aide du système et un procédé d'analyse de contenu vocal. Une unité d'indexation du système reçoit les données vocales et forme une grille de phonèmes par la mise en œuvre d'une reconnaissance vocale basée sur les phonèmes par unité de trame, génère des informations d'indexation partitionnées pour une trame de limite de temps comprenant la pluralité de trames et mémorise ensuite les informations d'indexation dans une base de données d'indexation, les informations d'indexation partitionnées comprenant les grilles de phonèmes formées pour chaque trame de limite de temps. Une unité de recherche recherche une chaîne de phonèmes correspondant à un critère de recherche par le biais d'une comparaison basée sur les phonèmes avec les informations d'indexation partitionnées mémorisées dans la base de données d'indexation à l'aide, comme critère de recherche, du mot-clé entré par un utilisateur, et trouve une partie vocale correspondant au critère de recherche par le biais d'une analyse acoustique précise sur la chaîne de phonèmes correspondante. Une unité d'analyse analyse un mot-matière par le biais du résultat de recherche recherché par l'unité de recherche et délivre ensuite le mot-matière à l'utilisateur pour permettre à l'utilisateur de comprendre le contenu vocal des données vocales.
(KO) 녹취된 음성 데이터에 대한 핵심어 추출 기반 발화 내용 파악 시스템과, 이 시스템을 이용한 인덱싱 방법 및 발화 내용 파악 방법이 개시된다. 이 시스템의 인덱싱부는 음성 데이터를 입력받아서 프레임 단위로 음소 기준의 음성 인식을 수행하여 음소 격자를 형성하고, 복수의 프레임으로 구성되는 제한 시간의 프레임에 대해 분할된 인덱싱 정보-여기서 분할된 인덱싱 정보는 제한 시간의 프레임별로 형성되는 음소 격자를 포함함-를 생성하여 인덱싱 데이터베이스에 저장한다. 검색부는 사용자로부터 입력되는 핵심어를 검색어로 하여 인덱싱 데이터베이스에 저장된 분할된 인덱싱 정보에 대해 음소 기준의 비교를 통해 상기 검색어와 일치하는 음소열을 검색하고 일치하는 음소열에 대해 정밀한 음향학적 분석을 통해 검색어에 해당하는 음성부분을 찾아내고, 파악부는 상기 검색부에 의해 검색되는 검색 결과를 통해 주제어를 파악하여 상기 음성 데이터의 발화 내용을 파악할 수 있도록 사용자에게 출력한다.
Latest bibliographic data on file with the International Bureau