paper-with-me

홈 › Papers

On the Cost and Benefits of Training Context with Utterance or Full Conversation Training: A Comparative Stud

2025-05-12 · Hyouin Liu, Zhikuan Zhang

Modern TTS systems designed for conversations achieve high-quality utterances but often remain inaccessible publicly. Are existing open-source architectures inadequate, or are current training techniques insufficient? This paper investigates prominent models and their underlying behaviors regarding conversational context. Using 20 GPU-hours on an NVIDIA H100, we empirically examine two approaches: context-based utterance-level training versus full conversation training. Results demonstrate that context-based utterance training achieves superior MOS scores (4.3/5.0 vs 3.7/5.0) and reduces training time by 37%, while full conversation approaches suffer from speaker similarity hallucination issues. These findings provide practical guidelines for conversational TTS development, favoring utterance-level training with contextual conditioning for both resource efficiency and output quality.

📄 PDF Abstract BibTeX arXiv:2505.07202

Code (0)

등록된 구현이 없습니다.

Tasks

GPUHallucination

Similar Papers 제목 키워드 기반

Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue

2021-11-16 · ACL ARR September 2021 9 · Anonymous

Context modeling plays a significant role in building multi-turn dialogue systems. In order to make full use of context information, systems can use Incomplete Utterance Rewriting(IUR) methods to simplify the multi-turn …

Contrastive LearningMulti-Task LearningSentence

Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue

2022-03-22 · Zhihao Wang, Tangjian Duan, ZiHao Wang, Minghui Yang 외

Context modeling plays a significant role in building multi-turn dialogue systems. In order to make full use of context information, systems can use Incomplete Utterance Rewriting(IUR) methods to simplify the multi-turn …

Contrastive LearningMulti-Task LearningSentence

Few-Shot Adaptation for Parsing Contextual Utterances with LLMs

2023-09-18 · Kevin Lin, Patrick Xia, Hao Fang

We evaluate the ability of semantic parsers based on large language models (LLMs) to handle contextual utterances. In real-world settings, there typically exists only a limited number of annotated contextual utterances d…

In-Context LearningSemantic Parsing

Learning to Map Context-Dependent Sentences to Executable Formal Queries

2018-04-18 · NAACL 2018 6 · Alane Suhr, Srinivasan Iyer, Yoav Artzi

We propose a context-dependent model to map utterances within an interaction to executable formal queries. To incorporate interaction history, the model maintains an interaction-level encoder that updates after each turn…

Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

2018-05-22 · WS 2018 7 · Shereen Oraby, Lena Reed, Shubhangi Tandon, T. S. Sharath 외

Natural language generators for task-oriented dialogue must effectively realize system dialogue actions and their associated semantics. In many applications, it is also desirable for generators to control the style of an…