Contact us

Archive: 2021 December

News
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Tutorials

HuBERT: ์ˆจ๊ฒจ์ง„ ๋‹จ์œ„์˜ ๋งˆ์Šคํ‚น ์˜ˆ์ธก์„ ํ†ตํ•œ ์ž์ฒด ์ง€๋„ ์Œ์„ฑ ํ‘œํ˜„ ํ•™์Šต

wav2vec 2.0์ด ๋Œ€์กฐ์  ์ž์ฒด ์ง€๋„๋กœ ๊ฒŒ์ž„์„ ๋ฐ”๊ฟจ์ง€๋งŒ, HuBERT๋Š” ๋” ๋‚ ์นด๋กœ์šด ์งˆ๋ฌธ์„ ์ œ์‹œํ–ˆ์Šต๋‹ˆ๋‹ค: ๋Œ€์กฐ์  ํŠธ๋ฆญ์„ ์™„์ „ํžˆ ๊ฑด๋„ˆ๋›ฐ๊ณ  ์Œ์„ฑ์—์„œ BERT ์Šคํƒ€์ผ์˜ ๋งˆ์Šคํ‚น ์˜ˆ์ธก์„ ์ˆ˜ํ–‰ํ•˜๋ฉด ์–ด๋–จ๊นŒ์š”?

12์›” 14, 2021ยท 1 min read
W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self Supervise
Tutorials

W2v-BERT: ๋Œ€์กฐ ํ•™์Šต๊ณผ ๋งˆ์Šคํ‚น๋œ ์–ธ์–ด ๋ชจ๋ธ๋ง์„ ๊ฒฐํ•ฉํ•œ ์ž์ฒด ์ง€๋„

์Œ์„ฑ ์‚ฌ์ „ ํ•™์Šต์„ ์œ„ํ•ด ๋Œ€์กฐ ํ•™์Šต๊ณผ ๋งˆ์Šคํ‚น๋œ ์–ธ์–ด ๋ชจ๋ธ๋ง ์ค‘์— ์„ ํƒํ•ด์•ผ ํ•  ๋•Œ ๋‘˜์„ ๊ฐ™์€ ๋„คํŠธ์›Œํฌ์— ์—ฐ๊ฒฐํ•  ์ˆ˜ ์žˆ๋‹ค๋ฉด ์™œ ์„ ํƒํ•ด์•ผ ํ• ๊นŒ์š”?

12์›” 12, 2021ยท 1 min read
Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition
Tutorials

์Œ์„ฑ ๊ฐ์ • ์ธ์‹ ๊ฐœ์„ ์„ ์œ„ํ•œ Wav2vec 2.0 ๋ฏธ์„ธ ์กฐ์ • ํƒ์ƒ‰

์Œ์„ฑ ๊ฐ์ • ์ธ์‹์€ ์˜ค๋žซ๋™์•ˆ ์ž‘์€ ๋ ˆ์ด๋ธ”๋œ ๋ฐ์ดํ„ฐ์…‹๊ณผ ์†์œผ๋กœ ๋งŒ๋“  ์Œํ–ฅ ํŠน์„ฑ์— ๊ฐ‡ํ˜€ ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.

12์›” 4, 2021ยท 1 min read
Joint Unsupervised and Supervised Training for Multilingual ASR
Tutorials

๋‹ค๊ตญ์–ด ASR์„ ์œ„ํ•œ ๊ณต๋™ ๋น„์ง€๋„ํ•™์Šต ๋ฐ ์ง€๋„ํ•™์Šต ํ›ˆ๋ จ

์‚ฌ์ „ ํ›ˆ๋ จ ํ›„ ๋ฏธ์„ธ ์กฐ์ •์ด ๋‹ค๊ตญ์–ด ASR์˜ ๊ธฐ๋ณธ ๋ ˆ์‹œํ”ผ๊ฐ€ ๋˜์—ˆ์ง€๋งŒ, ๋งŽ์€ ์ž ์žฌ๋ ฅ์„ ๋‚จ๊ธฐ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค: ๋‘ ๋‹จ๊ณ„๊ฐ€ ์†์‹ค์„ ๊ณต์œ ํ•˜์ง€ ์•Š์œผ๋ฉฐ, ์ง€๋„ ๋‹จ๊ณ„๊ฐ€ ์œ ์šฉํ•œ ์ž์ฒด ์ง€๋„ ๊ตฌ์กฐ๋ฅผ ์กฐ์šฉํžˆ ์ œ๊ฑฐํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค

12์›” 4, 2021ยท 1 min read