The evaluation campaign of the 19th International Conference on Spoken Language
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …

Direct speech-to-speech translation (S2ST), in which all components can be optimized
jointly, is advantageous over cascaded approaches to achieve fast inference with a …

Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR)
decoding can be a powerful alternative to beam search decoding, especially when …

Connectionist Temporal Classification (CTC) is a widely used approach for automatic
speech recognition (ASR) that performs conditionally independent monotonic alignment …

Minimum Bayes Risk (MBR) decoding is a method for choosing the outputs of a machine
learning system based not on the output with the highest probability, but the output with the …

ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the
broadening interests of the spoken language translation community. ESPnet-ST-v2 supports …

The black-box nature of end-to-end speech-to-text translation (E2E ST) makes it difficult to
understand how source language inputs are being mapped to the target language. To solve …

In the field of deep learning, researchers often focus on inventing novel neural network
models and improving benchmarks. In contrast, application developers are interested in …

This paper presents techniques and findings for improving the performance of low-resource
speech to text translation (ST). We conducted experiments on both simulated and real-low …

This paper presents ALADAN's approach to the IWSLT 2024 Dialectal and Low-resource
shared task, focusing on Levantine Arabic (apc) and Tunisian Arabic (aeb) to English …