This work presents the first fine-grained cross-lingual analysis of prosody using multilingual dubbing data across English-German, English-Spanish, and English-French language pairs and reveals inherent cross-lingual correlations in prosodic structure between certain 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.
This work quantifies the interaction between prosodic features and syntactic representations as their mutual information, and provides a general-purpose framework for estimating this quantity over large speech-text corpora using multimodal language models.
Junghyun Min, Alex Warstadt, Tamar I. Regev et al.· 0 citations
Irony and sarcasm are complex forms of non-literal language that hinge on a misalignment between surface meaning and speaker intent, requiring listeners to integrate contextual, semantic, and prosodic cues. While prior neuroimaging studies have implicated a broad network—including the temporal cortex, the inferior fron...
CVSS-X is introduced, a large-scale synthetic speech-to-speech translation corpus that extends CVSS by reversing the translation direction and enables research on bidirectional and multilingual speech-to-speech translation.
L. Gris, A. I. Ferreira, F. S. de Oliveira et al.· 0 citations
Languages differ in how they construct motion events. These crosslinguistic differences, referred to as framing typology, affect how speakers of different languages conceptualize motion events. Differences in event conceptualization may also transfer to the L2 (conceptual transfer), as shown from learners' grammatical...
Carissa A. Diantoro, Hak-Yung Sung, M. Baese-Berk· Language and Speech· 0 citations
A neural network is used to model a bilingual mapping within an English-Mandarin semantic space and indicates interesting possibilities for using quantitative word-level modeling as a tool to analyze the overlapping impacts of bilingualism, emotionality, and abstraction on each other.
Josephine Kaminaga, Jingyi Wu, Daniel Yeung et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 15, 2026
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026