End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation

02/23/2022
by   Krishna Subramani, et al.
0

Neural vocoders have recently demonstrated high quality speech synthesis, but typically require a high computational complexity. LPCNet was proposed as a way to reduce the complexity of neural synthesis by using linear prediction (LP) to assist an autoregressive model. At inference time, LPCNet relies on the LP coefficients being explicitly computed from the input acoustic features. That makes the design of LPCNet-based systems more complicated, while adding the constraint that the input features must represent a clean speech spectrum. We propose an end-to-end version of LPCNet that lifts these limitations by learning to infer the LP coefficients in the frame rate network from the input features. Results show that the proposed end-to-end approach can reach the same level of quality as the original LPCNet model, but without explicit LP analysis. Our open-source end-to-end model still benefits from LPCNet's low complexity, while allowing for any type of conditioning features.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/10/2019

RawNet: Fast End-to-End Neural Vocoder

Neural networks based vocoders have recently demonstrated the powerful a...
research
02/22/2022

Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet

Neural speech synthesis models can synthesize high quality speech but ty...
research
11/29/2018

LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis

We propose a linear prediction (LP)-based waveform generation method via...
research
03/29/2022

Finding Structure and Causality in Linear Programs

Linear Programs (LP) are celebrated widely, particularly so in machine l...
research
12/12/2018

FPUAS : Fully Parallel UFANS-based End-to-End Acoustic System with 10x Speed Up

A lightweight end-to-end acoustic system is crucial in the deployment of...
research
11/04/2018

Investigating context features hidden in End-to-End TTS

Recent studies have introduced end-to-end TTS, which integrates the prod...
research
08/30/2019

Maximizing Mutual Information for Tacotron

End-to-end speech synthesis method such as Tacotron, Tacotron2 and Trans...

Please sign up or login with your details

Forgot password? Click here to reset