Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems

08/11/2020
by   Ravichander Vipperla, et al.
0

LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low. In this work, we present two techniques to further reduce it's complexity, aiming for a low-cost LPCNet vocoder-based neural Text-to-Speech (TTS) System. These techniques are: 1) Sample-bunching, which allows LPCNet to generate more than one audio sample per inference; and 2) Bit-bunching, which reduces the computations in the final layer of LPCNet. With the proposed bunching techniques, LPCNet, in conjunction with a Deep Convolutional TTS (DCTTS) acoustic model, shows a 2.19x improvement over the baseline run-time when running on a mobile device, with a less than 0.1 decrease in TTS mean opinion score (MOS).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/20/2020

Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction

We present a novel multi-modal unspoken punctuation prediction system fo...
research
07/13/2022

A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System

Neural-based text-to-speech (TTS) systems achieve very high-fidelity spe...
research
09/13/2019

DASNet: Dynamic Activation Sparsity for Neural Network Efficiency Improvement

To improve the execution speed and efficiency of neural networks in embe...
research
03/11/2019

Deep Text-to-Speech System with Seq2Seq Model

Recent trends in neural network based text-to-speech/speech synthesis pi...
research
07/23/2020

Efficient Residue Number System Based Winograd Convolution

Prior research has shown that Winograd algorithm can reduce the computat...
research
04/06/2022

SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis

In this work, we present the SOMOS dataset, the first large-scale mean o...
research
09/14/2023

Complexity Scaling for Speech Denoising

Computational complexity is critical when deploying deep learning-based ...

Please sign up or login with your details

Forgot password? Click here to reset