paper-with-me

Papers

CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis

2023-12-16 · Yayue Deng, Jinlong Xue, Yukang Jia, Qifei Li, Yichen Han, Fengping Wang, Yingming Gao, Dengfeng Ke, Ya Li

Conversational speech synthesis (CSS) incorporates historical dialogue as supplementary information with the aim of generating speech that has dialogue-appropriate prosody. While previous methods have already delved into enhancing context comprehension, context representation still lacks effective representation capabilities and context-sensitive discriminability. In this paper, we introduce a contrastive learning-based CSS framework, CONCSS. Within this framework, we define an innovative pretext task specific to CSS that enables the model to perform self-supervised learning on unlabeled conversational datasets to boost the model's context understanding. Additionally, we introduce a sampling strategy for negative sample augmentation to enhance context vectors' discriminability. This is the first attempt to integrate contrastive learning into CSS. We conduct ablation studies on different contrastive learning strategies and comprehensive experiments in comparison with prior CSS systems. Results demonstrate that the synthesized speech from our proposed method exhibits more contextually appropriate and sensitive prosody.

📄 PDF Abstract BibTeX arXiv:2312.10358

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningSelf-Supervised LearningSpeech Synthesis

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses

2024-03-02 · Weihao Zeng, Keqing He, Yejie Wang, Dayuan Fu 외

Pre-trained language models have been successful in many scenarios. However, their usefulness in task-oriented dialogues is limited due to the intrinsic linguistic differences between general text and task-oriented dialo…

Diversity

Joint Learning of Context and Feedback Embeddings in Spoken Dialogue

2024-06-11 · Livia Qian, Gabriel Skantze

Short feedback responses, such as backchannels, play an important role in spoken dialogue. So far, most of the modeling of feedback responses has focused on their timing, often neglecting how their lexical and prosodic f…

Contrastive Learning

Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation

2026-09-04 · Jongkyung Shin, Inkyu Lee, Chiehyeon Lim arxiv

In persona-based dialogue generation (PDG), LLMs often overuse persona attributes by incorporating them regardless of dialogue context, resulting in unnatural responses. Despite its practical significance, the underlying…

Response GenerationDialogue Generation

ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings

2023-05-23 · Yuki Saito, Shinnosuke Takamichi, Eiji Iimori, Kentaro Tachibana 외

We propose ChatGPT-EDSS, an empathetic dialogue speech synthesis (EDSS) method using ChatGPT for extracting dialogue context. ChatGPT is a chatbot that can deeply understand the content and purpose of an input prompt and…

ChatbotReading ComprehensionSpeech SynthesisWord Embeddings

Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding

2024-09-09 · INLG 2024 9 · Bram Willemsen, Gabriel Skantze

We propose an approach to referring expression generation (REG) in visually grounded dialogue that is meant to produce referring expressions (REs) that are both discriminative and discourse-appropriate. Our method consti…

Image RetrievalReferring ExpressionReferring expression generationRetrieval