arXiv cs.AI· Parshav Singla, Agnik Banerjee, Aaditya Arora, Shruti Aggarwal, Anil Kumar Verma, Vikram C M, Raj Prakash Gohil, Gopal Kumar Agarwal·· 2 天前AI 评分20
PACC：将朗读语音转换为自然对话语音
Bridging the Gap: Converting Read Text to Conversational Dialogue
AI 导读
研究提出 PACC（Prosodic Adjustment with Conversational Context）方法，通过深度神经网络调整语调、重音和节奏等韵律特征，并采用 HiFi-GAN 进行语音合成，将朗读语音转换为自然对话语音。实验显示该方法在自然度和模型准确率上均有提升，并在语音转换任务和 MOS 评测中建立新基准，可扩展至其他语音转换应用。
正文 · 原文
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.
| Comments: | 11 pages, 4 figures. Published in ICICC 2025, Springer Lecture Notes in Networks and Systems |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2605.18001 [cs.CL] |
| (or arXiv:2605.18001v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.18001 arXiv-issued DOI via DataCite |
|
| Journal reference: | Innovative Computing and Communications (ICICC 2025), Lecture Notes in Networks and Systems, Springer Nature, 2025, pp. 543-556 |
| Related DOI: | https://doi.org/10.1007/978-981-96-6681-2_38
DOI(s) linking to related resources |
Submission history
From: Parshav Singla [view email]
[v1]
Mon, 18 May 2026 07:53:46 UTC (595 KB)
来源：arXiv cs.AI · arxiv.org