{ "componentChunkName": "component---src-templates-post-tsx", "path": "/Textledd NLP: Generating expressive speech from raw audio/", "result": {"data":{"logo":null,"markdownRemark":{"html":"

Textless NLP: Generating expressive speech from raw audio

\n\n

Intro

\n\n

Background

\n\n

Textless NLP’s benefits

\n\n

Data

\n\n

Model

\n \n\n\n\n

Result

\n\n","htmlAst":{"type":"root","children":[{"type":"element","tagName":"h1","properties":{},"children":[{"type":"text","value":"Textless NLP: Generating expressive speech from raw audio"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"a","properties":{"href":"https://arxiv.org/abs/2102.01192"},"children":[{"type":"text","value":"paper"}]},{"type":"text","value":" / "},{"type":"element","tagName":"a","properties":{"href":"https://github.com/pytorch/fairseq/tree/master/examples/textless_nlp/gslm"},"children":[{"type":"text","value":"code / pre-train model"}]},{"type":"text","value":" / "},{"type":"element","tagName":"a","properties":{"href":"https://ai.facebook.com/blog/textless-nlp-generating-expressive-speech-from-raw-audio"},"children":[{"type":"text","value":"blog"}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Name: Generative Spoken Language Model (GSLM)"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Intro"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"BERT, RoBERTa, GPT-3 등 최근 몇 년간 "},{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"텍스트"}]},{"type":"text","value":"에 집중된 NLP 모델들이 발전되어 왔음."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"이건 분명한 한계다. 텍스트에 대한 디펜던시를 깨야한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"언어 == 문자가 아니다. speech가 있다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"그래서 우리 GSLM이 텍스트에 대한 디펜던시를 깰 수 있는 가능성을 보였다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"음성 프롬프트 시대의 시작을 알린다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"음성을 프롬프트로 주면 뒤이어서 인공지능이 말을 계속 이어서 말하는 모델의 등장!"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Background"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"음성을 입력으로 하는 NLP 어플리케이션들은 ASR => NLP를 거쳐야 했음."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"ASR의 정확도가 100%가 아니기 때문에 분명한 정보의 오류가 존재함."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"우리는 여기서 ASR + NLP 구조가 아닌 Speech to Speech로 간다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Text나 label 없이 only 음성만으로 학습한다."}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Textless NLP’s benefits"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"언어 상관없이 학습이 가능해질 가능성이 높아짐"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"텍스트로 표현이 안되는 말의 뉘앙스, 감정 등의 정보를 반영할 수 있음"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"텍스트 레이블링 혹은 ASR 학습 없이 모델을 학습할 수 있음"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"유아들이 어떻게 언어를 배우고 말을 시작하는지를 알 수 있다(? 과연?)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"처음으로 텍스트 없이 audio to audio 번역 시스템이 가능해졌다!"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Data"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"6,000시간의 Libri-Light와 LibriSpeech 데이터셋 (인코더 학습)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"LibriSpeech and LJSpeech (디코더(TTS System) 학습)"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Model"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"img","properties":{"src":"https://user-images.githubusercontent.com/42150335/134018698-f46507a0-c375-4f6f-a67f-63e6ca2a9240.png","width":600},"children":[]},{"type":"text","value":" \n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Encoder (S2u)\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Speech를 인풋으로 받아서 discrete unit(pseudo-text라고 부름)으로 인코딩"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"unit은 k-means clustering으로 나눔."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"인코더로는 CPC, wav2vec 2.0, HuBERT를 사용 (좋은 acoustic encoder들이라고 보시면 됨)"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"uLM\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"unit sequence를 생성"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Decoder (u2S)\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"TTS System (Tacotron2 사용)"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"여기서 unit(pseudo-text)은 letter or phoneme과 매핑되지는 않음."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"100 이상의 유닛일 때 좋은 성능을 보였으며 unit은 보통 음소보다 짧은 단위를 인코딩했음."}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"img","properties":{"src":"https://scontent-gmp1-1.xx.fbcdn.net/v/t39.2365-6/241223788_398469455180920_2630499539056655858_n.jpg?_nc_cat=107&ccb=1-5&_nc_sid=ad8a9d&_nc_ohc=rfiDlgtmTcYAX-EraG5&_nc_ht=scontent-gmp1-1.xx&oh=1c96a38f6af0ada3774380e4fd6110e6&oe=61489C23","width":600},"children":[]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"생성한 음성은 pre-trained ASR 모델로 인식해서 성능 측정"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Pre-trained LM으로 텍스트 성능 측정"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Result"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"img","properties":{"src":"https://scontent-gmp1-1.xx.fbcdn.net/v/t39.2365-6/241364732_225715579507676_6485051182702467200_n.jpg?_nc_cat=108&ccb=1-5&_nc_sid=ad8a9d&_nc_ohc=h45PImsz8SkAX-kM1rz&_nc_ht=scontent-gmp1-1.xx&oh=88949e5b3a057a6e42b8266d03171ac7&oe=61492788","width":600},"children":[]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Unit의 수가 모델 성능에 큰 영향을 미침."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Unit 수가 커질수록 Acoustic의 성능은 좋아졌음. (PER이 낮아졌다)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"LM 점수도 비슷한 경향이었으나, 너무 많은 unit을 사용하면 오히려 안 좋았음. (NLP에서 vocab의 적당한 사이즈가 좋은 이유와 비슷한 것 같음)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"어떤 인코더 모델이냐에 따라 다른 결과가 나옴. HuBERT 성능이 가장 좋았음."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"이렇게 자동으로 측정한 성능이 사람이 평가했을 때와 correlation이 높았음. (좋은 성능 지표)"}]},{"type":"text","value":"\n"}]}],"data":{"quirksMode":false}},"excerpt":"Textless NLP: Generating expressive speech from raw audio paper / code / pre-train model / blog Name: Generative Spoken Language Model (GSLM…","fields":{"readingTime":{"text":"4 min read"}},"frontmatter":{"title":"Sooftware NLP - Textless NLP","userDate":"19 September 2021","date":"2021-09-19T10:00:00.000Z","tags":["speech","nlp","paper"],"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","backgroundColor":"#f8f8f8","images":{"fallback":{"src":"/static/b91fe939e42bcc0b6f0c076dca98fcc8/afa5c/gslm.png","srcSet":"/static/b91fe939e42bcc0b6f0c076dca98fcc8/0dee1/gslm.png 750w,\n/static/b91fe939e42bcc0b6f0c076dca98fcc8/8beaa/gslm.png 1080w,\n/static/b91fe939e42bcc0b6f0c076dca98fcc8/d079a/gslm.png 1366w,\n/static/b91fe939e42bcc0b6f0c076dca98fcc8/afa5c/gslm.png 1920w","sizes":"100vw"},"sources":[{"srcSet":"/static/b91fe939e42bcc0b6f0c076dca98fcc8/a66aa/gslm.webp 750w,\n/static/b91fe939e42bcc0b6f0c076dca98fcc8/65dd5/gslm.webp 1080w,\n/static/b91fe939e42bcc0b6f0c076dca98fcc8/4fad6/gslm.webp 1366w,\n/static/b91fe939e42bcc0b6f0c076dca98fcc8/c512e/gslm.webp 1920w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.5625}}},"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":"/Textledd NLP: Generating expressive speech from raw audio/","prev":{"excerpt":"이번에 저희 튜닙에서 공들여 만든 TUNiB Electra 모델을 공개했습니다 !! 🎉 🎉 이번 공개에서는 한-영 bilingual 모델과 한국어 모델을 각각 Small/Base 사이즈로 공개했으며, HuggingFace transformers…","frontmatter":{"title":"TUNiB Electra 공개","tags":["huggingface","nlp","record"],"date":"2021-09-18T15:11:55.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/7ccdb9951c9d362c8a3548e8c2a87231/59ccb/electra.png","srcSet":"/static/7ccdb9951c9d362c8a3548e8c2a87231/c68af/electra.png 750w,\n/static/7ccdb9951c9d362c8a3548e8c2a87231/87f65/electra.png 1080w,\n/static/7ccdb9951c9d362c8a3548e8c2a87231/d464a/electra.png 1366w,\n/static/7ccdb9951c9d362c8a3548e8c2a87231/59ccb/electra.png 1920w","sizes":"100vw"},"sources":[{"srcSet":"/static/7ccdb9951c9d362c8a3548e8c2a87231/9fb02/electra.webp 750w,\n/static/7ccdb9951c9d362c8a3548e8c2a87231/cd76f/electra.webp 1080w,\n/static/7ccdb9951c9d362c8a3548e8c2a87231/b7397/electra.webp 1366w,\n/static/7ccdb9951c9d362c8a3548e8c2a87231/507b8/electra.webp 1920w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.4479166666666667}}},"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":"2 min read"},"layout":"post","slug":"/tunib_electra/"}},"next":{"excerpt":"React 기반 개인 웹페이지 배포하기 이번 글에서는 react…","frontmatter":{"title":"React 기반 개인 웹페이지 배포하기 (gatsby)","tags":["toolkit","web"],"date":"2021-09-22T10:00:00.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/ddaa4cb6857e989e32ffc466cf76e8a5/7c984/gatsby.png","srcSet":"/static/ddaa4cb6857e989e32ffc466cf76e8a5/5b584/gatsby.png 750w,\n/static/ddaa4cb6857e989e32ffc466cf76e8a5/c1f05/gatsby.png 1080w,\n/static/ddaa4cb6857e989e32ffc466cf76e8a5/7c984/gatsby.png 1123w","sizes":"100vw"},"sources":[{"srcSet":"/static/ddaa4cb6857e989e32ffc466cf76e8a5/73e0d/gatsby.webp 750w,\n/static/ddaa4cb6857e989e32ffc466cf76e8a5/9fede/gatsby.webp 1080w,\n/static/ddaa4cb6857e989e32ffc466cf76e8a5/d4610/gatsby.webp 1123w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.5253784505788067}}},"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":"15 min read"},"layout":"","slug":"/react_homepage/"}},"primaryTag":"speech"}}, "staticQueryHashes": ["3170763342","3229353822"]}