DeepAI
Log In Sign Up

DeviceTTS: A Small-Footprint, Fast, Stable Network for On-Device Text-to-Speech

10/29/2020
by   Zhiying Huang, et al.
0

With the number of smart devices increasing, the demand for on-device text-to-speech (TTS) increases rapidly. In recent years, many prominent End-to-End TTS methods have been proposed, and have greatly improved the quality of synthesized speech. However, to ensure the qualified speech, most TTS systems depend on large and complex neural network models, and it's hard to deploy these TTS systems on-device. In this paper, a small-footprint, fast, stable network for on-device TTS is proposed, named as DeviceTTS. DeviceTTS makes use of a duration predictor as a bridge between encoder and decoder so as to avoid the problem of words skipping and repeating in Tacotron. As we all know, model size is a key factor for on-device TTS. For DeviceTTS, Deep Feedforward Sequential Memory Network (DFSMN) is used as the basic component. Moreover, to speed up inference, mix-resolution decoder is proposed for balance the inference speed and speech quality. Experiences are done with WORLD and LPCNet vocoder. Finally, with only 1.4 million model parameters and 0.099 GFLOPS, DeviceTTS achieves comparable performance with Tacotron and FastSpeech. As far as we know, the DeviceTTS can meet the needs of most of the devices in practical application.

READ FULL TEXT
05/22/2019

FastSpeech: Fast, Robust and Controllable Text to Speech

Neural network based end-to-end text to speech (TTS) has significantly i...
04/06/2021

Extremely Low Footprint End-to-End ASR System for Smart Device

Recently, end-to-end (E2E) speech recognition has become popular, since ...
12/22/2021

VoiceMoji: A Novel On-Device Pipeline for Seamless Emoji Insertion in Dictation

Most of the speech recognition systems recover only words in the speech ...
11/10/2019

Transformation of low-quality device-recorded speech to high-quality speech using improved SEGAN model

Nowadays vast amounts of speech data are recorded from low-quality recor...
01/19/2022

MHTTS: Fast multi-head text-to-speech for spontaneous speech with imperfect transcription

Neural network based end-to-end Text-to-Speech (TTS) has greatly improve...
10/25/2022

Streaming Parrotron for on-device speech-to-speech conversion

We present a fully on-device and streaming Speech-To-Speech (STS) conver...
09/16/2019

Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition

Deep-learning recently show great success across disciplines yet convent...