Papers by Belen Alastruey
Unveiling the Role of Pretraining in Direct Speech Translation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to train direct speech-to-text translation systems are pretraining the encoder on automatic speech recognition, thus losing efficiency in the training process. |
| Approach: | They propose to change the decoder cross-attention to integrate source information from earlier steps in training. |
| Outcome: | The proposed model can achieve comparable performance to the pretrained model while reducing training time. |
SpeechAlign: A Framework for Speech Translation Alignment Evaluation (2024.lrec-main)
Copied to clipboard
| Challenge: | Speech-to-Speech and Speech- to-Text translation are currently dynamic areas of research. |
| Approach: | They propose a framework to evaluate source-target alignment in speech models . they introduce a speech gold alignment dataset and introduce two new metrics . |
| Outcome: | The proposed framework evaluates source-target alignment quality within speech models. |
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer (2022.emnlp-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) relies on source sentence and target prefix attributions for each input token. |
| Approach: | They propose an interpretability method that tracks input tokens’ attributions for both contexts and extends it to any encoder-decoder Transformer-based model. |
| Outcome: | The proposed method can be extended to any encoder-decoder Transformer-based model and provides insights into their behaviour. |
On the Locality of Attention in Direct Speech Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | Recent advances in NLP have created problems with the complexity of the self-attention layer. |
| Approach: | They propose to substitute standard self-attention with a local efficient one to avoid the computation of attention weights. |
| Outcome: | The proposed model matches the baseline performance and improves efficiency by skipping the computation of weights that standard attention discards. |
Mixture of Languages: Improved Multilingual Encoders Through Language Grouping (2025.emnlp-main)
Copied to clipboard
João Maria Janeiro, Belen Alastruey, Francisco Massa, Maha Elbayad, Benjamin Piwowarski, Patrick Gallinari, Loic Barrault
| Challenge: | Recent work in this field relies on training transformer encoders on a large amount of multilingual data, with all parameters shared across all languages. |
| Approach: | They propose a mixture of languages strategy to pretrain largely multilingual encoders using masked language modeling. |
| Outcome: | The proposed architecture outperforms a dense counterpart, MoE models and public multilingual encoders on downstream tasks while minimizing interference. |
Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to address speech tasks with a self-attention mechanism are expensive and lead to information loss. |
| Approach: | They propose a Transformer-based model which uses different attention mechanisms on each head to bias the self-attention towards the extraction of more diverse token interactions. |
| Outcome: | The proposed model outperforms baseline models by 0.7 BLEU in the speech task. |
2M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Dataset Download PDF (2025.findings-acl)
Copied to clipboard
Marta R. Costa-jussà, Bokai Yu, Pierre Andrews, Belen Alastruey, Necati Cihan Camgoz, Joe Chuang, Jean Maillard, Christophe Ropers, Arina Turkatenko, Carleigh Wood
| Challenge: | We extend the BELEBELE dataset to speech and sign, and extend the Automatic Speech Recognition Benchmark, FLEURS, by 20%. |
| Approach: | They extend the BELEBELE and FLEURS speech comprehension datasets to speech and sign . they evaluate the datasets for 5-shot and zero-shot settings and find that the accuracy is 10% lower than reading comprehension. |
| Outcome: | The proposed dataset covers 91 spoken languages and one sign language (ASL) it also extends the Automatic Speech Recognition Benchmark, FLEURS, by 20% across languages. |