BABelen Alastruey

Belen Alastruey

*This is an algorithmically generated author record based on publicly available information.

Belen Alastruey has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Towards Real-World Streaming Speech Translation for Code-Switched Speech

    by Belen Alastruey, Matthias Sperber, Christian Gollan, Dominic Telaar, Tim Ng, Aashish Agarwal

    Code-switching (CS), i.e. mixing different languages in a single sentence, is a common phenomenon in communication and can be challenging in many Natural Language Processing (NLP) settings. Previous studies on CS speech have shown promising results for end-to-end speech translation (ST), but have been limited to offline scenarios and to translation to one of the languages present in the source (\textit{monolingual transcription}). In this paper, we focus on two essential yet unexplored areas for real-world CS speech translation: streaming settings, and translation to a third language (i.e., a language not included in the source). To this end, we extend the Fisher and Miami test and validation datasets to include new targets in Spanish and German. Using this data, we train a model for both offline and streaming ST and we establish baseline results for the two settings mentioned earlier.

  • Open Access

    Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition

    by Belen Alastruey, Lukas Drude, Jahn Heymann, Simon Wiesler

    Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and height of an audio spectrogram denote different information, e.g., due to reverberation as well as the articulatory system, the time axis has a clear left-to-right dependency. On the contrary, vowels and consonants demonstrate very different patterns and occupy almost disjoint frequency ranges. Therefore, we hypothesize, global attention over frequencies is beneficial over local convolution. We obtain 2.4 % relative word error rate reduction (rWERR) on a production scale Conformer transducer replacing its convolutional neural network frontend by the proposed F-Attention module on Alexa traffic. To demonstrate generalizability, we validate this on public LibriSpeech data with a long short term memory-based listen attend and spell architecture obtaining 4.6 % rWERR and demonstrate robustness to (simulated) noisy conditions.

  • Open Access

    Towards Real-World Streaming Speech Translation for Code-Switched Speech

    by Belen Alastruey, Matthias Sperber, Christian Gollan, Dominic Telaar, Tim Ng, Aashish Agarwal

    Belen Alastruey, Matthias Sperber, Christian Gollan, Dominic Telaar, Tim Ng, Aashish Agarwal. Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching. 2023.


  • Open Access

    Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer

    by Javier Ferrando, Gerard I. Gállego, Belen Alastruey, Carlos Escolano, Marta R. Costa-Jussà

    In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly focused solely on source sentence tokens' attributions. Therefore, we lack a full understanding of the influences of every input token (source sentence and target prefix) in the model predictions. In this work, we propose an interpretability method that tracks input tokens' attributions for both contexts. Our method, which can be extended to any encoder-decoder Transformer-based model, allows us to better comprehend the inner workings of current NMT models. We apply the proposed method to both bilingual and multilingual Transformers and present insights into their behaviour.