analiza aiqbench
This research investigates the transferability of prosodic features—such as pitch, energy, and timing—across different language pairs to improve expressive speech-to-speech translation systems. By analyzing multilingual dubbing data, the study identifies inherent correlations in prosodic structure that can guide future model architectures for conveying emotion and intent beyond mere lexical content.
Is Prosody Lost in Translation? Fine-Grained Cross-Lingual Prosody Similarity Across Languages
arXiv:2608.27848v1 Announce Type: cross Abstract: Prosody plays an important role in speech translation, conveying information such as emphasis, emotion, and intent beyond lexical content. However, despite recent progress in expressive speech-to-speech translation (S2ST), little is known about how prosodic patterns are similar/different across languages. Understanding these cross-lingual similarities and differences is crucial for effectively incorporating prosody into expressive S2ST systems. In this work, we present the first fine-grained cross-lingual analysis of prosody using multilingual dubbing data across English-German, English-Spanish, and English-French language pairs. We analyze the similarity of pitch, energy, and temporal feature patterns between source and target speech and investigate the linguistic and alignment-related factors affecting this similarity. Our analysis reveals inherent cross-lingual correlations in prosodic structure between certain languages. The findings provide important insights into the transferability of prosody across languages and offer empirical guidance for future expressive speech-to-speech translation systems.
Title:Is Prosody Lost in Translation? Fine-Grained Cross-Lingual Prosody Similarity Across Languages
Abstract:Prosody plays an important role in speech translation, conveying information such as emphasis, emotion, and intent beyond lexical content. However, despite recent progress in expressive speech-to-speech translation (S2ST), little is known about how prosodic patterns are similar/different across languages. Understanding these cross-lingual similarities and differences is crucial for effectively incorporating prosody into expressive S2ST systems. In this work, we present the first fine-grained cross-lingual analysis of prosody using multilingual dubbing data across English-German, English-Spanish, and English-French language pairs. We analyze the similarity of pitch, energy, and temporal feature patterns between source and target speech and investigate the linguistic and alignment-related factors affecting this similarity. Our analysis reveals inherent cross-lingual correlations in prosodic structure between certain languages. The findings provide important insights into the transferability of prosody across languages and offer empirical guidance for future expressive speech-to-speech translation systems.
Sound (cs.SD); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
arXiv:2608.27848 [cs.SD]
(or arXiv:2608.27848v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2608.27848 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 251 cuvinte
Subiecte conexe
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
arXiv · 12 oct. 2026
Generative Models Enhanced by Sequence Labelling and Aspect-Code Switching Improve Cross-lingual Aspect-Based Sentiment Analysis
arXiv · 1 sept. 2026
PolERo: Studying Political Evasion in Romanian
arXiv · 3 sept. 2026
ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs
arXiv · 2 sept. 2026