A Real-Time Wideband Neural Vocoder at 1.6kb/s Using LPCNet
Autor: | Jean-Marc Valin, Jan Skoglund |
---|---|
Rok vydání: | 2019 |
Předmět: |
Computer science
Speech recognition 020206 networking & telecommunications Speech synthesis Linear prediction 02 engineering and technology computer.software_genre Uncompressed video High complexity 0202 electrical engineering electronic engineering information engineering Waveform Codec 020201 artificial intelligence & image processing Wideband computer Coding (social sciences) |
Zdroj: | INTERSPEECH |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |