• 제목/요약/키워드: STT Error Correction

검색결과 3건 처리시간 0.02초

A Study on DNN-based STT Error Correction

  • Jong-Eon Lee
    • International journal of advanced smart convergence
    • /
    • 제12권4호
    • /
    • pp.171-176
    • /
    • 2023
  • This study is about a speech recognition error correction system designed to detect and correct speech recognition errors before natural language processing to increase the success rate of intent analysis in natural language processing with optimal efficiency in various service domains. An encoder is constructed to embedded the correct speech token and one or more error speech tokens corresponding to the correct speech token so that they are all located in a dense vector space for each correct token with similar vector values. One or more utterance tokens within a preset Manhattan distance based on the correct utterance token in the dense vector space for each embedded correct utterance token are detected through an error detector, and the correct answer closest to the detected error utterance token is based on the Manhattan distance. Errors are corrected by extracting the utterance token as the correct answer.

문법성 품질 예측에 기반한 음성 인식 오류 교정 (Grammatical Quality Estimation for Error Correction in Automatic Speech Recognition)

  • 서민택;나승훈;나민수;최맹식;이충희
    • 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
    • /
    • 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
    • /
    • pp.608-612
    • /
    • 2022
  • 딥러닝의 발전 이후, 다양한 분야에서는 딥러닝을 이용해 이전에 어려웠던 작업들을 해결하여 사용자에게 편의성을 제공하고 있다. 하지만 아직 딥러닝을 통해 이상적인 서비스를 제공하는 데는 어려움이 있다. 특히, 음성 인식 작업에서 음성 양식에서 이용 방안에 대하여 다양성을 제공해주는 음성을 텍스트로 전환하는 Speech-To-Text(STT)은 문장 결과가 이상치에 달하지 못해 오류가 나타나게 된다. 본 논문에서는 STT 결과 보정을 문법 교정으로 치환하여 종단에서 올바른 토큰들을 조합하여 성능 향상을 하기 위해 각 토큰 별 품질 평가를 진행하는 모델을 한국어에서 적용하고 성능의 향상을 확인한다.

  • PDF

지능형 온도 전송기의 시스템 안정성과 온도 보상 (Reliable Conversion and Compensation for Temperature of STT)

  • 이동규;박재현;김영수;조영학
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
    • /
    • pp.403-406
    • /
    • 1998
  • There are two cases of error occurrence of STT(Smart Temperature Transmitter). One is that because of unstable reference voltage, data from A/D converter is not reliable. The other is that because of change of room temperature, this change affects conversion of A/D converter. In this paper, we show algorithms be adapted to STT for reliable conversion of A/D converter through a experiment and compensation for temperature change. In a experiment, we collect data from reference voltage and ground then calculate nominal value of these at constant temperature during A/D converter initialization or at any conversion time. Algorithm for compensation for unstable reference voltage calculates a correction factor and adapts it to compensation for malfunction of A/D converter. Algorithm for compensation for variation of room temperature is come from linearization of thermistor but is adapted to zener diode, not thermistor, therefor we have less effort for compensation for temperature and have a idea that it can be adapted to A/D converter system.

  • PDF