Revision as of 14:48, 14 August 2023 edit Artoria2e5 (talk \| contribs) Extended confirmed users, IP block exemptions 38,965 edits →Sub-fields ← Previous edit		Revision as of 14:04, 27 August 2023 edit undo Citation bot (talk \| contribs) Bots 5,867,152 edits Alter: title. \| Use this bot. Report bugs. \| #UCB_CommandLine Next edit →
Line 54: [[Lyra (codec)\|Lyra]] (Google): V1 uses neural network reconstruction of log-mel spectrogram; V2 is an end-to-end [[autoencoder]]. [[Satin (codec)\|Satin]] (Microsoft) ** LPCNet (Mozilla, Xiph): neural network reconstruction of LPC features<ref>{{cite web \|title=LPCNet: Efficient neural speech synthesis \|url=https://github.com/xiph/LPCNet \|publisher=Xiph.Org Foundation \|date=8 August 2023}}</ref> ; [[Narrowband]] audio coding

Speech coding: Difference between revisions