EfficientSpeech: An On-Device Text to Speech Model

05/23/2023
by   Rowel Atienza, et al.
0

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on speech quality with cloud inference in mind. Neural TTS models are generally not designed to perform standalone speech syntheses on resource-constrained and no Internet access edge devices. In this work, an efficient neural TTS called EfficientSpeech that synthesizes speech on an ARM CPU in real-time is proposed. EfficientSpeech uses a shallow non-autoregressive pyramid-structure transformer forming a U-Network. EfficientSpeech has 266k parameters and consumes 90 MFLOPS only or about 1 computation in modern compact models such as Mixer-TTS. EfficientSpeech achieves an average mel generation real-time factor of 104.3 on an RPi4. Human evaluation shows only a slight degradation in audio quality as compared to FastSpeech2.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/27/2021

FlowVocoder: A small Footprint Neural Vocoder based Normalizing flow for Speech Synthesis

Recently, non-autoregressive neural vocoders have provided remarkable pe...
research
02/23/2018

Efficient Neural Audio Synthesis

Sequential models achieve state-of-the-art results in audio, visual and ...
research
07/21/2020

Very Fast Keyword Spotting System with Real Time Factor below 0.01

In the paper we present an architecture of a keyword spotting (KWS) syst...
research
11/25/2020

FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge

Nowadays more and more applications can benefit from edge-based text-to-...
research
03/27/2022

Bunched LPCNet2: Efficient Neural Vocoders Covering Devices from Cloud to Edge

Text-to-Speech (TTS) services that run on edge devices have many advanta...
research
06/15/2023

Audio Tagging on an Embedded Hardware Platform

Convolutional neural networks (CNNs) have exhibited state-of-the-art per...
research
10/24/2022

Real-time Speech Interruption Analysis: From Cloud to Client Deployment

Meetings are an essential form of communication for all types of organiz...

Please sign up or login with your details

Forgot password? Click here to reset