Search Results for author: Marco Gaido

Found 22 papers, 11 papers with code

On the Dynamics of Gender Learning in Speech Translation

no code implementations NAACL (GeBNLP) 2022 Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, Marco Turchi

In this work, we contribute to such a line of inquiry by exploring the emergence of gender bias in Speech Translation (ST).

Translation

Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation

1 code implementation NAACL (AutoSimTrans) 2022 Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi

Simultaneous speech translation (SimulST) systems aim at generating their output with the lowest possible latency, which is normally computed in terms of Average Lagging (AL).

Translation

Who Are We Talking About? Handling Person Names in Speech Translation

1 code implementation IWSLT (ACL) 2022 Marco Gaido, Matteo Negri, Marco Turchi

Recent work has shown that systems for speech translation (ST) -- similarly to automatic speech recognition (ASR) -- poorly handle person names.

Automatic Speech Recognition speech-recognition +1

Efficient yet Competitive Speech Translation: FBK@IWSLT2022

1 code implementation IWSLT (ACL) 2022 Marco Gaido, Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri, Marco Turchi

The primary goal of this FBK's systems submission to the IWSLT 2022 offline and simultaneous speech translation tasks is to reduce model training costs without sacrificing translation quality.

Translation

Does Simultaneous Speech Translation need Simultaneous Models?

no code implementations8 Apr 2022 Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi

In simultaneous speech translation (SimulST), finding the best trade-off between high translation quality and low latency is a challenging task.

Translation

Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation

1 code implementation ACL 2022 Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, Marco Turchi

Gender bias is largely recognized as a problematic phenomenon affecting language technologies, with recent studies underscoring that it might surface differently across languages.

POS Translation

Speechformer: Reducing Information Loss in Direct Speech Translation

1 code implementation EMNLP 2021 Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi

Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation.

Speech-to-Text Translation Translation

Between Flexibility and Consistency: Joint Generation of Captions and Subtitles

1 code implementation ACL (IWSLT) 2021 Alina Karakanta, Marco Gaido, Matteo Negri, Marco Turchi

Speech translation (ST) has lately received growing interest for the generation of subtitles without the need for an intermediate source language transcription and timing (i. e. captions).

Translation

Dealing with training and test segmentation mismatch: FBK@IWSLT2021

no code implementations ACL (IWSLT) 2021 Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi

Both knowledge distillation and the first fine-tuning step are carried out on manually segmented real and synthetic data, the latter being generated with an MT system trained on the available corpora.

Action Detection Activity Detection +2

Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?

no code implementations ACL 2021 Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta, Alberto Martinelli, Matteo Negri, Marco Turchi

Five years after the first published proofs of concept, direct approaches to speech translation (ST) are now competing with traditional cascade solutions.

Translation

How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation

1 code implementation Findings (ACL) 2021 Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi

In light of this finding, we propose a combined approach that preserves BPE overall translation quality, while leveraging the higher ability of character-based segmentation to properly translate gender.

Translation

Gender Bias in Machine Translation

no code implementations13 Apr 2021 Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, Marco Turchi

Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, elaborating and communicating information.

Machine Translation Translation

CTC-based Compression for Direct Speech Translation

1 code implementation EACL 2021 Marco Gaido, Mauro Cettolo, Matteo Negri, Marco Turchi

Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST).

Translation

Breeding Gender-aware Direct Speech Translation Systems

no code implementations COLING 2020 Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi

In particular, by translating speech audio data without intermediate transcription, direct ST models are able to leverage and preserve essential information present in the input (e. g. speaker's vocal characteristics) that is otherwise lost in the cascade framework.

Machine Translation Natural Language Processing +1

On Knowledge Distillation for Direct Speech Translation

1 code implementation9 Dec 2020 Marco Gaido, Mattia A. Di Gangi, Matteo Negri, Marco Turchi

Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT).

Automatic Speech Recognition Knowledge Distillation +4

On Target Segmentation for Direct Speech Translation

no code implementations AMTA 2020 Mattia Antonino Di Gangi, Marco Gaido, Matteo Negri, Marco Turchi

Then, subword-level segmentation became the state of the art in neural machine translation as it produces shorter sequences that reduce the training time, while being superior to word-level models.

Data Augmentation Machine Translation +1

Contextualized Translation of Automatically Segmented Speech

1 code implementation5 Aug 2020 Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Mauro Cettolo, Marco Turchi

We show that our context-aware solution is more robust to VAD-segmented input, outperforming a strong base model and the fine-tuning on different VAD segmentations of an English-German test set by up to 4. 25 BLEU points.

Speech-to-Text Translation Translation

End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020

no code implementations WS 2020 Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Marco Turchi

The test talks are provided in two versions: one contains the data already segmented with automatic tools and the other is the raw data without any segmentation.

Data Augmentation Knowledge Distillation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.