SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.12087 · 2019

A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
mozilla/LPCNet canonical 5 of 14
FunctionStatusWhere it lives
dump_layer_ignore Ran mozilla/LPCNet/training_tf2/dump_lpcnet.py
code served (permissive licence) · get_code("52188c0085750c07")
interp_mulaw Ran mozilla/LPCNet/training_tf2/lossfuncs.py
code served (permissive licence) · get_code("a6e64cda1739e303")
printVector Ran mozilla/LPCNet/training_tf2/keraslayerdump.py
code served (permissive licence) · get_code("a228df437cb01d43")
quant_regularizer Ran mozilla/LPCNet/training_tf2/lpcnet_plc.py
code served (permissive licence) · get_code("a1a9d70573973a74")
tree_to_pdf Ran mozilla/LPCNet/training_tf2/lpcnet.py
code served (permissive licence) · get_code("9e51f3aeba5a1306")
dump_sparse_gru Not yet run mozilla/LPCNet/training_tf2/dump_lpcnet.py
code served (permissive licence) · get_code("6e0af699c31a78db")
dump_sparse_gru Not yet run mozilla/LPCNet/training_tf2/keraslayerdump.py
code served (permissive licence) · get_code("3874048af50f43b6")
interleave Not yet run mozilla/LPCNet/training_tf2/lpcnet.py
code served (permissive licence) · get_code("462214bb0c5c4921")
lpc2rc Not yet run mozilla/LPCNet/training_tf2/dataloader.py
code served (permissive licence) · get_code("72b68e6945caf8ec")
metric_icel Not yet run mozilla/LPCNet/training_tf2/lossfuncs.py
code served (permissive licence) · get_code("3d3bf2278d25692a")
metric_oginterploss Not yet run mozilla/LPCNet/training_tf2/lossfuncs.py
code served (permissive licence) · get_code("d9840947585808dc")
printSparseVector Not yet run mozilla/LPCNet/training_tf2/dump_lpcnet.py
code served (permissive licence) · get_code("7437251d9a634f0b")
printSparseVector Not yet run mozilla/LPCNet/training_tf2/keraslayerdump.py
code served (permissive licence) · get_code("3a4032c58aaadc9d")
tree_to_pdf_train Not yet run mozilla/LPCNet/training_tf2/lpcnet.py
code served (permissive licence) · get_code("1f1e48ec8adf543a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Neural speech synthesis algorithms are a promising new approach for coding speech at very low bitrate. They have so far demonstrated quality that far exceeds traditional vocoders, at the cost of very high complexity. In this work, we present a low-bitrate neural vocoder based on the LPCNet model. The use of linear prediction and sparse recurrent networks makes it possible to achieve real-time operation on general-purpose hardware. We demonstrate that LPCNet operating at 1.6 kb/s achieves significantly higher quality than MELP and that uncompressed LPCNet can exceed the quality of a waveform codec operating at low bitrate. This opens the way for new codec designs based on neural synthesis models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1903.12087")
get_code_for_paper("1903.12087")
have("1903.12087")

Connect an agent — have() is free.