Sara Papi


2024

pdf bib
FINDINGS OF THE IWSLT 2024 EVALUATION CAMPAIGN
Ibrahim Said Ahmad | Antonios Anastasopoulos | Ondřej Bojar | Claudia Borg | Marine Carpuat | Roldano Cattoni | Mauro Cettolo | William Chen | Qianqian Dong | Marcello Federico | Barry Haddow | Dávid Javorský | Mateusz Krubiński | Tsz Kim Lam | Xutai Ma | Prashant Mathur | Evgeny Matusov | Chandresh Maurya | John McCrae | Kenton Murray | Satoshi Nakamura | Matteo Negri | Jan Niehues | Xing Niu | Atul Kr. Ojha | John Ortega | Sara Papi | Peter Polák | Adam Pospíšil | Pavel Pecina | Elizabeth Salesky | Nivedita Sethiya | Balaram Sarkar | Jiatong Shi | Claytone Sikasote | Matthias Sperber | Sebastian Stüker | Katsuhito Sudoh | Brian Thompson | Alex Waibel | Shinji Watanabe | Patrick Wilken | Petr Zemánek | Rodolfo Zevallos
Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)

This paper reports on the shared tasks organized by the 21st IWSLT Conference. The shared tasks address 7 scientific challenges in spoken language translation: simultaneous and offline translation, automatic subtitling and dubbing, speech-to-speech translation, dialect and low-resource speech translation, and Indic languages. The shared tasks attracted 17 teams whose submissions are documented in 27 system papers. The growing interest towards spoken language translation is also witnessed by the constantly increasing number of shared task organizers and contributors to the overview paper, almost evenly distributed across industry and academia.

pdf bib
SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
Sara Papi | Marco Gaido | Matteo Negri | Luisa Bentivogli
Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)

This paper describes the FBK’s participation in the Simultaneous Translation Evaluation Campaign at IWSLT 2024. For this year’s submission in the speech-to-text translation (ST) sub-track, we propose SimulSeamless, which is realized by combining AlignAtt and SeamlessM4T in its medium configuration. The SeamlessM4T model is used ‘off-the-shelf’ and its simultaneous inference is enabled through the adoption of AlignAtt, a SimulST policy based on cross-attention that can be applied without any retraining or adaptation of the underlying model for the simultaneous task. We participated in all the Shared Task languages (English->German, Japanese, Chinese, and Czech->English), achieving acceptable or even better results compared to last year’s submissions. SimulSeamless, covering more than 143 source languages and 200 target languages, is released at: https://github.com/hlt-mt/FBK-fairseq/.

pdf bib
Automatic Subtitling and Subtitle Compression: FBK at the IWSLT 2024 Subtitling track
Marco Gaido | Sara Papi | Mauro Cettolo | Roldano Cattoni | Andrea Piergentili | Matteo Negri | Luisa Bentivogli
Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)

The paper describes the FBK submissions to the Subtitling track of the 2024 IWSLT Evaluation Campaign, which covers both the Automatic Subtitling and the Subtitle Compression task for two language pairs: English to German (en-de) and English to Spanish (en-es). For the Automatic Subtitling task, we submitted two systems: i) a direct model, trained in constrained conditions, that produces the SRT files from the audio without intermediate outputs (e.g., transcripts), and ii) a cascade solution that integrates only free-to-use components, either taken off-the-shelf or developed in-house. Results show that, on both language pairs, our direct model outperforms both cascade and direct systems trained in constrained conditions in last year’s edition of the campaign, while our cascade solution is competitive with the best 2023 runs. For the Subtitle Compression task, our primary submission involved prompting a Large Language Model (LLM) in zero-shot mode to shorten subtitles that exceed the reading speed limit of 21 characters per second. Our results highlight the challenges inherent in shrinking out-of-context sentence fragments that are automatically generated and potentially error-prone, underscoring the need for future studies to develop targeted solutions.

pdf bib
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
Neele Falk | Sara Papi | Mike Zhang
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop

pdf bib
How Do Hyenas Deal with Human Speech? Speech Recognition and Translation with ConfHyena
Marco Gaido | Sara Papi | Matteo Negri | Luisa Bentivogli
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

The attention mechanism, a cornerstone of state-of-the-art neural models, faces computational hurdles in processing long sequences due to its quadratic complexity. Consequently, research efforts in the last few years focused on finding more efficient alternatives. Among them, Hyena (Poli et al., 2023) stands out for achieving competitive results in both language modeling and image classification, while offering sub-quadratic memory and computational complexity. Building on these promising results, we propose ConfHyena, a Conformer whose encoder self-attentions are replaced with an adaptation of Hyena for speech processing, where the long input sequences cause high computational costs. Through experiments in automatic speech recognition (for English) and translation (from English into 8 target languages), we show that our best ConfHyena model significantly reduces the training time by 27%, at the cost of minimal quality degradation (∼1%), which, in most cases, is not statistically significant.

pdf bib
When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP
Sara Papi | Marco Gaido | Andrea Pilzer | Matteo Negri
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Despite its crucial role in research experiments, code correctness is often presumed solely based on the perceived quality of results. This assumption, however, comes with the risk of erroneous outcomes and, in turn, potentially misleading findings. To mitigate this risk, we posit that the current focus on reproducibility should go hand in hand with the emphasis on software quality. We support our arguments with a case study in which we identify and fix three bugs in widely used implementations of the state-of-the-art Conformer architecture. Through experiments on speech recognition and translation in various languages, we demonstrate that the presence of bugs does not prevent the achievement of good and reproducible results, which however can lead to incorrect conclusions that potentially misguide future research. As countermeasures, we release pangoliNN, a library dedicated to testing neural models, and propose a Code-quality Checklist, with the goal of promoting coding best practices and improving software quality within the NLP community.

pdf bib
SBAAM! Eliminating Transcript Dependency in Automatic Subtitling
Marco Gaido | Sara Papi | Matteo Negri | Mauro Cettolo | Luisa Bentivogli
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Subtitling plays a crucial role in enhancing the accessibility of audiovisual content and encompasses three primary subtasks: translating spoken dialogue, segmenting translations into concise textual units, and estimating timestamps that govern their on-screen duration. Past attempts to automate this process rely, to varying degrees, on automatic transcripts, employed diversely for the three subtasks. In response to the acknowledged limitations associated with this reliance on transcripts, recent research has shifted towards transcription-free solutions for translation and segmentation, leaving the direct generation of timestamps as uncharted territory. To fill this gap, we introduce the first direct model capable of producing automatic subtitles, entirely eliminating any dependence on intermediate transcripts also for timestamp prediction. Experimental results, backed by manual evaluation, showcase our solution’s new state-of-the-art performance across multiple language pairs and diverse conditions.

pdf bib
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection
Sara Papi | Marco Gaido | Matteo Negri | Luisa Bentivogli
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Streaming speech-to-text translation (StreamST) is the task of automatically translating speech while incrementally receiving an audio stream. Unlike simultaneous ST (SimulST), which deals with pre-segmented speech, StreamST faces the challenges of handling continuous and unbounded audio streams. This requires additional decisions about what to retain of the previous history, which is impractical to keep entirely due to latency and computational constraints. Despite the real-world demand for real-time ST, research on streaming translation remains limited, with existing works solely focusing on SimulST. To fill this gap, we introduce StreamAtt, the first StreamST policy, and propose StreamLAAL, the first StreamST latency metric designed to be comparable with existing metrics for SimulST. Extensive experiments across all 8 languages of MuST-C v1.0 show the effectiveness of StreamAtt compared to a naive streaming baseline and the related state-of-the-art SimulST policy, providing a first step in StreamST research.

pdf bib
Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
Marco Gaido | Sara Papi | Matteo Negri | Luisa Bentivogli
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The field of natural language processing (NLP) has recently witnessed a transformative shift with the emergence of foundation models, particularly Large Language Models (LLMs) that have revolutionized text-based NLP. This paradigm has extended to other modalities, including speech, where researchers are actively exploring the combination of Speech Foundation Models (SFMs) and LLMs into single, unified models capable of addressing multimodal tasks. Among such tasks, this paper focuses on speech-to-text translation (ST). By examining the published papers on the topic, we propose a unified view of the architectural solutions and training strategies presented so far, highlighting similarities and differences among them. Based on this examination, we not only organize the lessons learned but also show how diverse settings and evaluation approaches hinder the identification of the best-performing solution for each architectural building block and training choice. Lastly, we outline recommendations for future works on the topic aimed at better understanding the strengths and weaknesses of the SFM+LLM solutions for ST.

2023

pdf bib
Direct Speech Translation for Automatic Subtitling
Sara Papi | Marco Gaido | Alina Karakanta | Mauro Cettolo | Matteo Negri | Marco Turchi
Transactions of the Association for Computational Linguistics, Volume 11

Automatic subtitling is the task of automatically translating the speech of audiovisual content into short pieces of timed text, i.e., subtitles and their corresponding timestamps. The generated subtitles need to conform to space and time requirements, while being synchronized with the speech and segmented in a way that facilitates comprehension. Given its considerable complexity, the task has so far been addressed through a pipeline of components that separately deal with transcribing, translating, and segmenting text into subtitles, as well as predicting timestamps. In this paper, we propose the first direct speech translation model for automatic subtitling that generates subtitles in the target language along with their timestamps with a single model. Our experiments on 7 language pairs show that our approach outperforms a cascade system in the same data condition, also being competitive with production tools on both in-domain and newly released out-domain benchmarks covering new scenarios.

pdf bib
Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection
Dennis Fucci | Marco Gaido | Sara Papi | Mauro Cettolo | Matteo Negri | Luisa Bentivogli
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

When translating words referring to the speaker, speech translation (ST) systems should not resort to default masculine generics nor rely on potentially misleading vocal traits. Rather, they should assign gender according to the speakers’ preference. The existing solutions to do so, though effective, are hardly feasible in practice as they involve dedicated model re-training on gender-labeled ST data. To overcome these limitations, we propose the first inference-time solution to control speaker-related gender inflections in ST. Our approach partially replaces the (biased) internal language model (LM) implicitly learned by the ST decoder with gender-specific external LMs. Experiments on enes/fr/it show that our solution outperforms the base models and the best training-time mitigation strategy by up to 31.0 and 1.6 points in gender accuracy, respectively, for feminine forms. The gains are even larger (up to 32.0 and 3.4) in the challenging condition where speakers’ vocal traits conflict with their gender.

pdf bib
Attention as a Guide for Simultaneous Speech Translation
Sara Papi | Matteo Negri | Marco Turchi
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In simultaneous speech translation (SimulST), effective policies that determine when to write partial translations are crucial to reach high output quality with low latency. Towards this objective, we propose EDAtt (Encoder-Decoder Attention), an adaptive policy that exploits the attention patterns between audio source and target textual translation to guide an offline-trained ST model during simultaneous inference. EDAtt exploits the attention scores modeling the audio-translation relation to decide whether to emit a partial hypothesis or wait for more audio input. This is done under the assumption that, if attention is focused towards the most recently received speech segments, the information they provide can be insufficient to generate the hypothesis (indicating that the system has to wait for additional audio input). Results on en->de, es show that EDAtt yields better results compared to the SimulST state of the art, with gains respectively up to 7 and 4 BLEU points for the two languages, and with a reduction in computational-aware latency up to 1.4s and 0.7s compared to existing SimulST policies applied to offline-trained models.

pdf bib
Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023
Sara Papi | Marco Gaido | Matteo Negri
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)

This paper describes the FBK’s participation in the Simultaneous Translation and Automatic Subtitling tracks of the IWSLT 2023 Evaluation Campaign. Our submission focused on the use of direct architectures to perform both tasks: for the simultaneous one, we leveraged the knowledge already acquired by offline-trained models and directly applied a policy to obtain the real-time inference; for the subtitling one, we adapted the direct ST model to produce well-formed subtitles and exploited the same architecture to produce timestamps needed for the subtitle synchronization with audiovisual content. Our English-German SimulST system shows a reduced computational-aware latency compared to the one achieved by the top-ranked systems in the 2021 and 2022 rounds of the task, with gains of up to 3.5 BLEU. Our automatic subtitling system outperforms the only-existing solution based on a direct system by 3.7 and 1.7 SubER in English-German and English-Spanish respectively.

2022

pdf bib
Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST Corpora
Sara Papi | Alina Karakanta | Matteo Negri | Marco Turchi
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Speech translation for subtitling (SubST) is the task of automatically translating speech data into well-formed subtitles by inserting subtitle breaks compliant to specific displaying guidelines. Similar to speech translation (ST), model training requires parallel data comprising audio inputs paired with their textual translations. In SubST, however, the text has to be also annotated with subtitle breaks. So far, this requirement has represented a bottleneck for system development, as confirmed by the dearth of publicly available SubST corpora. To fill this gap, we propose a method to convert existing ST corpora into SubST resources without human intervention. We build a segmenter model that automatically segments texts into proper subtitles by exploiting audio and text in a multimodal fashion, achieving high segmentation quality in zero-shot conditions. Comparative experiments with SubST systems respectively trained on manual and automatic segmentations result in similar performance, showing the effectiveness of our approach.

pdf bib
Does Simultaneous Speech Translation need Simultaneous Models?
Sara Papi | Marco Gaido | Matteo Negri | Marco Turchi
Findings of the Association for Computational Linguistics: EMNLP 2022

In simultaneous speech translation (SimulST), finding the best trade-off between high output quality and low latency is a challenging task. To meet the latency constraints posed by different application scenarios, multiple dedicated SimulST models are usually trained and maintained, generating high computational costs. In this paper, also motivated by the increased sensitivity towards sustainable AI, we investigate whether a single model trained offline can serve both offline and simultaneous applications under different latency regimes without additional training or adaptation. Experiments on en->de, es show that, aside from facilitating the adoption of well-established offline architectures and training strategies without affecting latency, offline training achieves similar or better quality compared to the standard SimulST training protocol, also being competitive with the state-of-the-art system.

pdf bib
Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation
Sara Papi | Marco Gaido | Matteo Negri | Marco Turchi
Proceedings of the Third Workshop on Automatic Simultaneous Translation

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). In this paper we highlight that, despite its widespread adoption, AL provides underestimated scores for systems that generate longer predictions compared to the corresponding references. We also show that this problem has practical relevance, as recent SimulST systems have indeed a tendency to over-generate. As a solution, we propose LAAL (Length-Adaptive Average Lagging), a modified version of the metric that takes into account the over-generation phenomenon and allows for unbiased evaluation of both under-/over-generating systems.

pdf bib
Efficient yet Competitive Speech Translation: FBK@IWSLT2022
Marco Gaido | Sara Papi | Dennis Fucci | Giuseppe Fiameni | Matteo Negri | Marco Turchi
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

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. As such, we first question the need of ASR pre-training, showing that it is not essential to achieve competitive results. Second, we focus on data filtering, showing that a simple method that looks at the ratio between source and target characters yields a quality improvement of 1 BLEU. Third, we compare different methods to reduce the detrimental effect of the audio segmentation mismatch between training data manually segmented at sentence level and inference data that is automatically segmented. Towards the same goal of training cost reduction, we participate in the simultaneous task with the same model trained for offline ST. The effectiveness of our lightweight training strategy is shown by the high score obtained on the MuST-C en-de corpus (26.7 BLEU) and is confirmed in high-resource data conditions by a 1.6 BLEU improvement on the IWSLT2020 test set over last year’s winning system.

2021

pdf bib
Simultaneous Speech Translation for Live Subtitling: from Delay to Display
Alina Karakanta | Sara Papi | Matteo Negri | Marco Turchi
Proceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW)

With the increased audiovisualisation of communication, the need for live subtitles in multilingual events is more relevant than ever. In an attempt to automatise the process, we aim at exploring the feasibility of simultaneous speech translation (SimulST) for live subtitling. However, the word-for-word rate of generation of SimulST systems is not optimal for displaying the subtitles in a comprehensible and readable way. In this work, we adapt SimulST systems to predict subtitle breaks along with the translation. We then propose a display mode that exploits the predicted break structure by presenting the subtitles in scrolling lines. We compare our proposed mode with a display 1) word-for-word and 2) in blocks, in terms of reading speed and delay. Experiments on three language pairs (en→it, de, fr) show that scrolling lines is the only mode achieving an acceptable reading speed while keeping delay close to a 4-second threshold. We argue that simultaneous translation for readable live subtitles still faces challenges, the main one being poor translation quality, and propose directions for steering future research.

pdf bib
Dealing with training and test segmentation mismatch: FBK@IWSLT2021
Sara Papi | Marco Gaido | Matteo Negri | Marco Turchi
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)

This paper describes FBK’s system submission to the IWSLT 2021 Offline Speech Translation task. We participated with a direct model, which is a Transformer-based architecture trained to translate English speech audio data into German texts. The training pipeline is characterized by knowledge distillation and a two-step fine-tuning procedure. 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. Differently, the second fine-tuning step is carried out on a random segmentation of the MuST-C v2 En-De dataset. Its main goal is to reduce the performance drops occurring when a speech translation model trained on manually segmented data (i.e. an ideal, sentence-like segmentation) is evaluated on automatically segmented audio (i.e. actual, more realistic testing conditions). For the same purpose, a custom hybrid segmentation procedure that accounts for both audio content (pauses) and for the length of the produced segments is applied to the test data before passing them to the system. At inference time, we compared this procedure with a baseline segmentation method based on Voice Activity Detection (VAD). Our results indicate the effectiveness of the proposed hybrid approach, shown by a reduction of the gap with manual segmentation from 8.3 to 1.4 BLEU points.

pdf bib
Speechformer: Reducing Information Loss in Direct Speech Translation
Sara Papi | Marco Gaido | Matteo Negri | Marco Turchi
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer’s quadratic complexity with respect to the input sequence length prevents its adoption as is with audio signals, which are typically represented by long sequences. Current solutions resort to an initial sub-optimal compression based on a fixed sampling of raw audio features. Therefore, potentially useful linguistic information is not accessible to higher-level layers in the architecture. To solve this issue, we propose Speechformer, an architecture that, thanks to reduced memory usage in the attention layers, avoids the initial lossy compression and aggregates information only at a higher level according to more informed linguistic criteria. Experiments on three language pairs (en→de/es/nl) show the efficacy of our solution, with gains of up to 0.8 BLEU on the standard MuST-C corpus and of up to 4.0 BLEU in a low resource scenario.