A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis

by   Rishabh Jain, et al.

Speech synthesis has come a long way as current text-to-speech (TTS) models can now generate natural human-sounding speech. However, most of the TTS research focuses on using adult speech data and there has been very limited work done on child speech synthesis. This study developed and validated a training pipeline for fine-tuning state-of-the-art (SOTA) neural TTS models using child speech datasets. This approach adopts a multi-speaker TTS retuning workflow to provide a transfer-learning pipeline. A publicly available child speech dataset was cleaned to provide a smaller subset of approximately 19 hours, which formed the basis of our fine-tuning experiments. Both subjective and objective evaluations were performed using a pretrained MOSNet for objective evaluation and a novel subjective framework for mean opinion score (MOS) evaluations. Subjective evaluations achieved the MOS of 3.95 for speech intelligibility, 3.89 for voice naturalness, and 3.96 for voice consistency. Objective evaluation using a pretrained MOSNet showed a strong correlation between real and synthetic child voices. Speaker similarity was also verified by calculating the cosine similarity between the embeddings of utterances. An automatic speech recognition (ASR) model is also used to provide a word error rate (WER) comparison between the real and synthetic child voices. The final trained TTS model was able to synthesize child-like speech from reference audio samples as short as 5 seconds.



page 6

page 7

page 10


Whispered and Lombard Neural Speech Synthesis

It is desirable for a text-to-speech system to take into account the env...

JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech

In neural text-to-speech (TTS), two-stage system or a cascade of separat...

Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody

Generating expressive and contextually appropriate prosody remains a cha...

GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis

Recent advances in neural multi-speaker text-to-speech (TTS) models have...

Manipulation of oral cancer speech using neural articulatory synthesis

We present an articulatory synthesis framework for the synthesis and man...

VRAIN-UPV MLLP's system for the Blizzard Challenge 2021

This paper presents the VRAIN-UPV MLLP's speech synthesis system for the...

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...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.