paper-with-me

Papers

AutoStyle-TTS: Retrieval-Augmented Generation based Automatic Style Matching Text-to-Speech Synthesis

2025-04-14 · Dan Luo, Chengyuan Ma, Weiqin Li, Jun Wang, Wei Chen, Zhiyong Wu

With the advancement of speech synthesis technology, users have higher expectations for the naturalness and expressiveness of synthesized speech. But previous research ignores the importance of prompt selection. This study proposes a text-to-speech (TTS) framework based on Retrieval-Augmented Generation (RAG) technology, which can dynamically adjust the speech style according to the text content to achieve more natural and vivid communication effects. We have constructed a speech style knowledge database containing high-quality speech samples in various contexts and developed a style matching scheme. This scheme uses embeddings, extracted by Llama, PER-LLM-Embedder,and Moka, to match with samples in the knowledge database, selecting the most appropriate speech style for synthesis. Furthermore, our empirical research validates the effectiveness of the proposed method. Our demo can be viewed at: https://thuhcsi.github.io/icme2025-AutoStyle-TTS

📄 PDF Abstract BibTeX arXiv:2504.10309

Code (0)

등록된 구현이 없습니다.

Tasks

RAGRetrieval-augmented GenerationSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Similar Papers 제목 키워드 기반

From Pixels to Posts: Retrieval-Augmented Fashion Captioning and Hashtag Generation

2025-11-24 · Moazzam Umer Gondal, Hamad Ul Qudous, Daniya Siddiqui, Asma Ahmad Farhan arxiv

This paper introduces the retrieval-augmented framework for automatic fashion caption and hashtag generation, combining multi-garment detection, attribute reasoning, and Large Language Model (LLM) prompting. The system a…

Domain Generalization

From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEM

2025-07-05 · Xinyi Wu, Yanhao Jia, Luwei Xiao, Shuai Zhao 외 arxiv

In AI-facilitated teaching, leveraging various query styles to interpret abstract educational content is crucial for delivering effective and accessible learning experiences. However, existing retrieval systems predomina…

Image Matching

Personalized Text Generation with Contrastive Activation Steering

2025-03-07 · Jinghao Zhang, YuTing Liu, Wenjie Wang, Qiang Liu 외

Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics. Existing solutions primarily adopt two…

parameter-efficient fine-tuningRAGRetrievalRetrieval-augmented Generation+1

Diversify Question Generation with Retrieval-Augmented Style Transfer

2023-10-23 · Qi Gou, Zehua Xia, Bowen Yu, Haiyang Yu 외

Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems. Existing solutions mainly focus on the in…

DiversityQuestion AnsweringQuestion GenerationQuestion-Generation+3

ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation

2025-01-21 · Peter Devine

Retrieval Augmented Generation (RAG) systems have been shown to improve the accuracy of Large Language Model (LLM) outputs. However, these models can often achieve low accuracy when applied to new data domains. We introd…

Language ModelingLanguage ModellingLarge Language ModelRAG+2