French

The 'French' dataset/benchmark contains audio and text data used to evaluate the performance of Simultaneous Speech Translation (SimulST) systems, particularly in terms of translation quality and latency.

Papers using French (11)

REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation2025 · 1 citesLanguage Barriers: Evaluating Cross-Lingual Performance of CNN and Transformer Architectures for Speech Quality Estimation2025 · 1 citesUnsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Only2026Speech-to-Speech Translation Pipelines for Conversations in Low-Resource Languages2025Analysis of Voice Conversion and Code-Switching Synthesis Using VQ-VAE2022 · 1 citesAnalyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models2022 · 1 citesGuided contrastive self-supervised pre-training for automatic speech recognition2022Learning Multilingual Expressive Speech Representation for Prosody Prediction without Parallel Data2023Semantic enrichment towards efficient speech representations2023Zero Resource Cross-Lingual Part Of Speech Tagging2024Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion2024