Bridging the Gap: Converting Read Text to Conversational Dialogue

TL;DR

This paper presents PACC, a novel deep learning approach utilizing HiFi-GAN to convert read speech into natural conversational speech, improving naturalness and accuracy for real-time speech applications.

Contribution

Introduction of PACC, a new prosodic adjustment method using advanced neural networks and HiFi-GAN for high-quality speech conversion.

Findings

Significant improvements in naturalness and model accuracy.

Achieved new benchmarks in speech conversion and MOS evaluation.

Demonstrated successful extension to other speech conversion tasks.

Abstract

In recent advancements within speech processing, converting read speech to conversational speech has gained significant attention. The primary challenge in this domain is maintaining naturalness and intelligibility while minimizing computational overhead for real-time applications. Traditional read speech often lacks the nuanced prosodic variation essential for natural conversational interactions, posing challenges for applications in virtual assistants, customer service, and language learning tools. This paper introduces a novel approach, Prosodic Adjustment with Conversational Context (PACC), aimed at converting read speech into natural conversational speech used in various modern applications. PACC utilizes advanced deep neural networks to analyze and modify prosodic features such as intonation, stress, and rhythm. Unlike conventional methods, our approach uses High-Fidelity Generative Adversarial Networks (HiFi-GAN) for speech synthesis. Our experimental results demonstrate significant improvements in speech conversion, enhancing naturalness and achieving better model accuracy with additional training on speech datasets. This research establishes new benchmarks in speech conversion tasks and Mean Opinion Score (MOS) evaluation for testing model accuracy, and we show that our approach can be successfully extended to other speech conversion applications.