Investigating the Training Dynamics in End-to-end Speech Translation

The task of speech translation consists one translating speech input into text in a different language. In this project, we present an interpretability analysis of a Transformer model on this task. Our work builds upon previous research which explored the training phases of a Transformer for text tr...

Descripción completa

Detalles Bibliográficos
Autor: Alastruey Lasheras, Belén
Tipo de recurso: tesis de maestría
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/403813
Acceso en línea:https://hdl.handle.net/2117/403813
Access Level:acceso abierto
Palabra clave:Machine translating
Deep learning (Machine learning)
Speech processing systems
deep learning
machine translation
speech processing
transformer
Traducció automàtica
Aprenentatge profund
Processament de la parla
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic
Descripción
Sumario:The task of speech translation consists one translating speech input into text in a different language. In this project, we present an interpretability analysis of a Transformer model on this task. Our work builds upon previous research which explored the training phases of a Transformer for text translation. We extend their analysis to study the training of the Transformer for ST, focusing on the variations of contribution of the source to the predictions during the training process. We show that depending on the training strategy, some speech translation models show a similar source contribution than text translation ones, but others have a lower source contribution and a worse performance. Furthermore, we propose modification to the Transformer architecture, aiming to force the model to use more source in its predictions. Through this modifications, we achieve a significant performance boost of up to +1.3 BLEU.