{ "componentChunkName": "component---src-templates-post-tsx", "path": "/audio_app2/", "result": {"data":{"logo":null,"markdownRemark":{"html":"

AI & Speech Processing: Application-2

\n

본 글은 광운대학교 전자공학과 박호종 교수님의 강의를 듣고 작성되었음을 밝힙니다.

\n

Speaker Verification and Identification

\n

Verification (인증)

\n

\"image\"

\n

음성신호에서 개인별 고유 정보를 추출하여 본인 검증

\n

Identification (인식)

\n

\"image\"

\n

여러 음성 신호에서 특정인 검색

\n\n

\"image\"

\n\n

기존 비밀번호보다 편리?

\n

기존 비밀번호보다 안전?

\n

\"image\"

\n

Voice를 이용한 보안의 문제점은 테러범의 핸드폰 같은 경우, 지문 혹은 얼굴 인식과 달리 본인이 마음 먹지 않으면 절대 풀 수가 없음.

\n

Sound Recognition / Detection

\n\n
Robot\n\n아기 울음소리 / 동물소리 인식\n\n자율주행 \n:: 자율주행에서도 소리로 특징을 포착하는 기술이 필요 (구글은 사이렌 소리를 인식)\n\n청각장애
\n\n
불법 벌목 감청 (구글이 도입)\n\n멸종위기 고래 탐지
\n

Music Information Analysis

\n

\"image\"

\n

음악 검색, Hit 가능성 여부 예측, 인공 작곡 + 감정

\n\n
노래 일부분의 음만을 가지고 찾고싶은 노래 검색  \n\n표절 확인\n\n자동 노래 선곡 시스템
\n

Speech and Audio Coding

\n

전송 또는 저장을 위한 디지털 데이터양을 감소시키는 기술

\n

=> 거의 완벽하게 산업화에 성공

\n

디지털 이동 통신, portable music의 핵심

\n

\"image\"

\n\n

모든 종류의 sound를 통합적으로 처리
\n(기존에는 speech codec, audio codec으로 구분)

\n\n

3D Audio / 입체 음향

\n

\"image\"

\n\n

\"image\"

\n

디지털 오디오 방송

\n

객체(Object) 기반 디지털 오디오 방송

\n

\"image\"

\n\n

사용자는 원하는 오디오를 선택하여 청취

\n

잡음 제거

\n

\"image\"

\n

잡음을 제거하는 간단한 방법으로 마이크를 여러개 설치한다.

\n

Active Noise Cancellation (ANC)
\n=> Airpod Pro에 탑재된 기술 (주변 소음 제거)

\n

\"image\"

\n

들어오는 소리의 파형과 반대되는 파형을 더해줌으로써 0으로 만들어줌

\n

기타

\n

신호 복원 : 왜곡되고 변형된 신호를 원 신호로 복원

\n

Sound type 분리

\n

Multimedia DB에서 Audio 특성으로 원하는 장면 검색

\n

의료 신호처리

\n

음악 치료

\n

음향 장비

","htmlAst":{"type":"root","children":[{"type":"element","tagName":"h1","properties":{},"children":[{"type":"text","value":"AI & Speech Processing: Application-2"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"본 글은 광운대학교 전자공학과 박호종 교수님의 강의를 듣고 작성되었음을 밝힙니다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Speaker Verification and Identification"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"Verification (인증)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78555116-50184380-7847-11ea-8ff3-c6c393d6402c.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"음성신호에서 개인별 고유 정보를 추출하여 "},{"type":"element","tagName":"strong","properties":{},"children":[{"type":"text","value":"본인 검증"}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"Identification (인식)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78551433-afbf2080-7840-11ea-96f9-176458bae5dd.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"여러 음성 신호에서 "},{"type":"element","tagName":"strong","properties":{},"children":[{"type":"text","value":"특정인 검색"}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Ex) Smartphone 지문 인식 문제"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78553517-59ec7780-7844-11ea-8a81-300778187510.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Why Bio 인증?"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"기존 비밀번호보다 편리?"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"기존 비밀번호보다 안전?"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78553891-0890b800-7845-11ea-94f4-7acd4be09065.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"Voice를 이용한 보안의 문제점은 테러범의 핸드폰 같은 경우, 지문 혹은 얼굴 인식과 달리 본인이 마음 먹지 않으면 절대 풀 수가 없음."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Sound Recognition / Detection"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"인간과 동일한 sound 정보 인식"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"div","properties":{"className":["gatsby-highlight"],"dataLanguage":"text"},"children":[{"type":"element","tagName":"pre","properties":{"className":["language-text"]},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"Robot\n\n아기 울음소리 / 동물소리 인식\n\n자율주행 \n:: 자율주행에서도 소리로 특징을 포착하는 기술이 필요 (구글은 사이렌 소리를 인식)\n\n청각장애"}]}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"인간 능력 이상의 sound 정보 인식"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"div","properties":{"className":["gatsby-highlight"],"dataLanguage":"text"},"children":[{"type":"element","tagName":"pre","properties":{"className":["language-text"]},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"불법 벌목 감청 (구글이 도입)\n\n멸종위기 고래 탐지"}]}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Music Information Analysis"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78554986-1c3d1e00-7847-11ea-94c0-020f85549942.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"음악 검색, Hit 가능성 여부 예측, 인공 작곡 + 감정"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Content 기반으로 Music 검색 / Retrieval"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"div","properties":{"className":["gatsby-highlight"],"dataLanguage":"text"},"children":[{"type":"element","tagName":"pre","properties":{"className":["language-text"]},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"노래 일부분의 음만을 가지고 찾고싶은 노래 검색 \n\n표절 확인\n\n자동 노래 선곡 시스템"}]}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Speech and Audio Coding"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"전송 또는 저장을 위한 디지털 데이터양을 감소시키는 기술"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"=> 거의 완벽하게 산업화에 성공"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"디지털 이동 통신, portable music의 핵심"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78555377-d9c81100-7847-11ea-9987-cdcf3d884ad5.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"현재의 연구 동향"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"모든 종류의 sound를 통합적으로 처리"},{"type":"element","tagName":"br","properties":{},"children":[]},{"type":"text","value":"\n(기존에는 speech codec, audio codec으로 구분)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"국제 기관 (ITU, ISO 등)에서 표준 codec 선정"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"3D Audio / 입체 음향"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78555735-9d48e500-7848-11ea-852b-56129ba59960.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Audio for Virtual Reality"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78555846-d3866480-7848-11ea-9abf-fa4b18b994c6.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"디지털 오디오 방송"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"객체(Object) 기반 디지털 오디오 방송"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78557966-beabd000-784c-11ea-9d56-ca474c336ae5.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"오디오 객체별로 신호 전송"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"사용자가 sound를 임의로 선택하여 청취"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Sports 중계 방송, 음악 방송, 드라마"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"언어 선택 (외국어로 방송 청취)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"입체 음향 청취"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"사용자는 원하는 오디오를 선택하여 청취"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"잡음 제거"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78558545-bb651400-784d-11ea-842a-9565d373a9ea.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"잡음을 제거하는 간단한 방법으로 마이크를 여러개 설치한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"Active Noise Cancellation (ANC)"},{"type":"element","tagName":"br","properties":{},"children":[]},{"type":"text","value":"\n=> Airpod Pro에 탑재된 기술 (주변 소음 제거)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/78558732-1860ca00-784e-11ea-9656-f8eab0578c1d.png","alt":"image"},"children":[]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"들어오는 소리의 파형과 반대되는 파형을 더해줌으로써 0으로 만들어줌"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"기타"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"신호 복원 : 왜곡되고 변형된 신호를 원 신호로 복원"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"Sound type 분리"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"Multimedia DB에서 Audio 특성으로 원하는 장면 검색"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"의료 신호처리"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"음악 치료"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"음향 장비"}]}],"data":{"quirksMode":false}},"excerpt":"AI & Speech Processing: Application-2 본 글은 광운대학교 전자공학과 박호종 교수님의 강의를 듣고 작성되었음을 밝힙니다. Speaker Verification and Identification Verification…","fields":{"readingTime":{"text":"4 min read"}},"frontmatter":{"title":"Sooftware Speech - AI & Speech Processing: Application-2","userDate":"17 April 2020","date":"2020-04-17T10:00:00.000Z","tags":["speech"],"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","backgroundColor":"#080808","images":{"fallback":{"src":"/static/b3321f8e0e847a673a28ec1ffe7b6c8c/c577e/audio_app2.png","srcSet":"/static/b3321f8e0e847a673a28ec1ffe7b6c8c/ca06a/audio_app2.png 750w,\n/static/b3321f8e0e847a673a28ec1ffe7b6c8c/c577e/audio_app2.png 753w","sizes":"100vw"},"sources":[{"srcSet":"/static/b3321f8e0e847a673a28ec1ffe7b6c8c/53639/audio_app2.webp 750w,\n/static/b3321f8e0e847a673a28ec1ffe7b6c8c/71889/audio_app2.webp 753w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6108897742363878}}},"author":[{"id":"Soohwan Kim","bio":"Co-founder/A.I. engineer at TUNiB.","avatar":{"children":[{"gatsbyImageData":{"layout":"fullWidth","backgroundColor":"#282838","images":{"fallback":{"src":"/static/a9e6b445142b247ee4cfa66155398bb2/0d6f4/soohwan.png","srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/248f9/soohwan.png 40w,\n/static/a9e6b445142b247ee4cfa66155398bb2/fd435/soohwan.png 80w,\n/static/a9e6b445142b247ee4cfa66155398bb2/0d6f4/soohwan.png 120w","sizes":"100vw"},"sources":[{"srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/e7f45/soohwan.webp 40w,\n/static/a9e6b445142b247ee4cfa66155398bb2/589ec/soohwan.webp 80w,\n/static/a9e6b445142b247ee4cfa66155398bb2/71a38/soohwan.webp 120w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6833333333333333}}]}}]}},"relatedPosts":{"totalCount":20,"edges":[{"node":{"id":"fa9e8cbb-841a-516f-9df6-4be0336b56b0","excerpt":"한국어 Tacotron2 이번 포스팅에서는 Tacotron2 아키텍처로 한국어 TTS 시스템을 만드는 방법에 대해 다루겠습니다. Tacotron2 Tacotron2는 17년 12월 구글이 NATURAL TTS SYNTHESIS BY…","frontmatter":{"title":"Sooftware Speech - 한국어 Tacotron2","date":"2021-10-10T10:00:00.000Z"},"fields":{"readingTime":{"text":"11 min read"},"slug":"/korean_tacotron2/"}}},{"node":{"id":"43c23529-71b1-5d60-8883-a45fbcd55ebd","excerpt":"Textless NLP: Generating expressive speech from raw audio paper / code / pre-train model / blog Name: Generative Spoken Language Model (GSLM…","frontmatter":{"title":"Sooftware NLP - Textless NLP","date":"2021-09-19T10:00:00.000Z"},"fields":{"readingTime":{"text":"4 min read"},"slug":"/Textledd NLP: Generating expressive speech from raw audio/"}}},{"node":{"id":"83c6b4fa-d71e-51d8-90bb-b58bfffc01d0","excerpt":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition Yu Zhang et al., 2020 Google Research, Brain Team Reference…","frontmatter":{"title":"Sooftware Speech - Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition Paper Review","date":"2021-03-17T10:00:00.000Z"},"fields":{"readingTime":{"text":"3 min read"},"slug":"/Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition/"}}},{"node":{"id":"894a24ca-fff9-5884-b6da-1c97f2ece7bc","excerpt":"PORORO Text-To-Speech (TTS) 얼마전에 저희 팀에서 공개한 PORORO: Platform Of neuRal mOdels for natuRal language prOcessing 라이브러리에 제가 공들여만든 TTS…","frontmatter":{"title":"PORORO Text-To-Speech (TTS)","date":"2021-02-16T10:00:00.000Z"},"fields":{"readingTime":{"text":"1 min read"},"slug":"/pororo-tts/"}}},{"node":{"id":"b039977c-cecb-50f4-a0dd-fd008731bc99","excerpt":"EMNLP Paper Review: Speech Adaptive Feature Selection for End-to-End Speech Translation (Biao Zhang et al) Incremental Text-to-Speech…","frontmatter":{"title":"Sooftware Speech - EMNLP Paper Review: Speech","date":"2020-12-08T10:00:00.000Z"},"fields":{"readingTime":{"text":"4 min read"},"slug":"/2020 EMNLP Speech Paper Review/"}}}]}},"pageContext":{"slug":"/audio_app2/","prev":{"excerpt":"AI & Speech Processing: Application-1 본 글은 광운대학교 전자공학과 박호종 교수님의 강의를 듣고 작성되었음을 밝힙니다. 음성/오디오/sound…","frontmatter":{"title":"Sooftware Speech - AI & Speech Processing: Application-1","tags":["speech"],"date":"2020-04-15T10:00:00.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/ea340e308aee7cbbeae7dcadb12a5f72/fee67/audio_app1.png","srcSet":"/static/ea340e308aee7cbbeae7dcadb12a5f72/ae605/audio_app1.png 750w,\n/static/ea340e308aee7cbbeae7dcadb12a5f72/fee67/audio_app1.png 841w","sizes":"100vw"},"sources":[{"srcSet":"/static/ea340e308aee7cbbeae7dcadb12a5f72/1211a/audio_app1.webp 750w,\n/static/ea340e308aee7cbbeae7dcadb12a5f72/d21da/audio_app1.webp 841w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.35434007134363854}}},"author":[{"id":"Soohwan Kim","bio":"Co-founder/A.I. engineer at TUNiB.","avatar":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png","srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/34f77/soohwan.png 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/a94f6/soohwan.png 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png 1148w","sizes":"100vw"},"sources":[{"srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/38420/soohwan.webp 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7470d/soohwan.webp 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/b5ef6/soohwan.webp 1148w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6829268292682927}}}}]},"fields":{"readingTime":{"text":"7 min read"},"layout":"","slug":"/audio_app/"}},"next":{"excerpt":"Conformer: Convolution-augmented Transformer for Speech Recognition Anmol Gulati et al. Google Inc. INTERSPEECH, 2020 Reference Conformer…","frontmatter":{"title":"Sooftware Speech - Conformer Paper Review","tags":["speech","paper"],"date":"2020-08-30T10:00:00.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/5ca9b355b1dc4393c360f527478a3ba2/503d5/conformer.png","srcSet":"/static/5ca9b355b1dc4393c360f527478a3ba2/bfaac/conformer.png 750w,\n/static/5ca9b355b1dc4393c360f527478a3ba2/abf2b/conformer.png 1080w,\n/static/5ca9b355b1dc4393c360f527478a3ba2/6c19a/conformer.png 1366w,\n/static/5ca9b355b1dc4393c360f527478a3ba2/503d5/conformer.png 1890w","sizes":"100vw"},"sources":[{"srcSet":"/static/5ca9b355b1dc4393c360f527478a3ba2/1e5e2/conformer.webp 750w,\n/static/5ca9b355b1dc4393c360f527478a3ba2/77f81/conformer.webp 1080w,\n/static/5ca9b355b1dc4393c360f527478a3ba2/b9a60/conformer.webp 1366w,\n/static/5ca9b355b1dc4393c360f527478a3ba2/2837d/conformer.webp 1890w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6888888888888889}}},"author":[{"id":"Soohwan Kim","bio":"Co-founder/A.I. engineer at TUNiB.","avatar":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png","srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/34f77/soohwan.png 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/a94f6/soohwan.png 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png 1148w","sizes":"100vw"},"sources":[{"srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/38420/soohwan.webp 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7470d/soohwan.webp 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/b5ef6/soohwan.webp 1148w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6829268292682927}}}}]},"fields":{"readingTime":{"text":"4 min read"},"layout":"","slug":"/conformer/"}},"primaryTag":"speech"}}, "staticQueryHashes": ["3170763342","3229353822"]}