On the Cost and Benefits of Training Context with Utterance or Full Conversation Training: A Comparative Stud
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.
Code (0)
등록된 구현이 없습니다.
Tasks
GPUHallucinationSimilar Papers 제목 키워드 기반
Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue
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 LearningSentenceUtterance Rewriting with Contrastive Learning in Multi-turn Dialogue
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 LearningSentenceFew-Shot Adaptation for Parsing Contextual Utterances with LLMs
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 ParsingLearning to Map Context-Dependent Sentences to Executable Formal Queries
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
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…