MUSTC

The MUSTC dataset is a benchmark used to evaluate speech translation tasks, containing multi-view speech representations for assessing model performance.

Papers using MUSTC (48)

SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation2026Optimal Multi-Task Learning at Regularization Horizon for Speech Translation Task2025InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model2025Optimizing Speech Multi-View Feature Fusion through Conditional Computation2025Speech Translation Refinement using Large Language Models2025M3ST: Mix at Three Levels for Speech Translation2022 · 14 citesPre-training for Speech Translation: CTC Meets Optimal Transport2023 · 7 citesEfficient Sequence Transduction by Jointly Predicting Tokens and Durations2023 · 6 citesSHAS: Approaching optimal Segmentation for End-to-End Speech Translation2022 · 3 citesSpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training2022 · 3 citesRegularizing End-to-End Speech Translation with Triangular Decomposition Agreement2021 · 2 citesSTEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation2022 · 2 citesGigaST: A 10,000-hour Pseudo Speech Translation Corpus2022 · 2 citesSimple and Effective Unsupervised Speech Translation2022 · 2 citesAdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation2022 · 2 citesWACO: Word-Aligned Contrastive Learning for Speech Translation2022 · 2 citesTuning Large language model for End-to-end Speech Translation2023 · 2 citesT-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation2022 · 1 citesEfficient Speech Translation with Dynamic Latent Perceivers2022 · 1 citesSegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations2022 · 1 citesHybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks2023 · 1 citesUnderstanding and Bridging the Modality Gap for Speech Translation2023 · 1 citesCMOT: Cross-modal Mixup via Optimal Transport for Speech Translation2023 · 1 citesSoft Alignment of Modality Space for End-to-end Speech Translation2023 · 1 citesFASST: Fast LLM-based Simultaneous Speech Translation2024 · 1 citesUnified Speech-Text Pre-training for Speech Translation and Recognition2022Cross-modal Contrastive Learning for Speech Translation2022Generating Synthetic Speech from SpokenVocab for Speech Translation2022RedApt: An Adaptor for wav2vec 2 Encoding \\ Faster and Smaller Speech Translation without Quality Compromise2022Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation2023Improving speech translation by fusing speech and text2023CTC-based Non-autoregressive Speech Translation2023Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT232023Modality Adaption or Regularization? A Case Study on End-to-End Speech Translation2023Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation2023Implicit Memory Transformer for Computationally Efficient Simultaneous Speech Translation2023Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts2023An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation2023Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition2023Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing2023Rethinking and Improving Multi-task Learning for End-to-end Speech Translation2023Pushing the Limits of Zero-shot End-to-End Speech Translation2024SimulTron: On-Device Simultaneous Speech to Speech Translation2024Task Arithmetic for Language Expansion in Speech Translation2024Representation Purification for End-to-End Speech Translation2024On the Impact of Noises in Crowd-Sourced Data for Speech Translation2022Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning2023Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff2023