HMM-based data augmentation for E2E systems for building conversational speech synthesis systems

TL;DR

This paper introduces a novel data augmentation method using HMM-based synthesized speech to enhance end-to-end TTS systems for technical domains, improving intelligibility and handling low-resource scenarios.

Contribution

It presents a new approach combining HMM synthesis with fine-tuning on real data to improve E2E TTS quality, especially in low-resource settings.

Findings

Speech quality surpasses baseline E2E in intelligibility

Effective in low-resource scenarios

Reduces synthesis errors like word skips and repetitions

Abstract

This paper proposes an approach to build a high-quality text-to-speech (TTS) system for technical domains using data augmentation. An end-to-end (E2E) system is trained on hidden Markov model (HMM) based synthesized speech and further fine-tuned with studio-recorded TTS data to improve the timbre of the synthesized voice. The motivation behind the work is that issues of word skips and repetitions are usually absent in HMM systems due to their ability to model the duration distribution of phonemes accurately. Context-dependent pentaphone modeling, along with tree-based clustering and state-tying, takes care of unseen context and out-of-vocabulary words. A language model is also employed to reduce synthesis errors further. Subjective evaluations indicate that speech produced using the proposed system is superior to the baseline E2E synthesis approach in terms of intelligibility when combining complementing attributes from HMM and E2E frameworks. The further analysis highlights the proposed approach's efficacy in low-resource scenarios.