HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 20 Dec 2017 09:04:22 GMT access-control-allow-origin: * etag: W/"5a3a2796-46934f" expires: Sun, 28 Dec 2025 11:02:33 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 66F2:2916CC:79025D:878D84:69510BF1 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 10:52:33 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210044-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766919153.325805,VS0,VE403 vary: Accept-Encoding x-fastly-request-id: 2f3e0298c84a429541c5816a97918fefdeb6d606 content-length: 3264562

Sound samples for "ON USING BACKPROPAGATION FOR SPEECH TEXTURE GENERATION AND VOICE CONVERSION"

Figure 1 - speech reconstructions

	p225	p226
C0
FC1

Figure 2 - speech texture synthesis

p225, C0	p226, C0-C5
p225, C0-C5	Polish speaker, C0-C5

Figure 5 - voice conversion

Original	p225	p226
Converted	p225->p226	p226->p225

Bonus Figure - voice conversion using short utterance in Polish

Content

Style

Converted