Search Results - "Salesky, Elizabeth"

Towards Fluent Translations From Disfluent Speech by Salesky, Elizabeth, Burger, Susanne, Niehues, Jan, Waibel, Alex

“…When translating from speech, special consideration for conversational speech phenomena such as disfluencies is necessary. Most machine translation training…”
Get full text

Optimizing segmentation granularity for neural machine translation by Salesky, Elizabeth, Runge, Andrew, Coda, Alex, Niehues, Jan, Neubig, Graham

“…In neural machine translation (NMT), it has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent…”
Get full text

A Holistic Cascade System, Benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation by Huang, Wen-Chin, Peloquin, Benjamin, Kao, Justine, Wang, Changhan, Gong, Hongyu, Salesky, Elizabeth, Adi, Yossi, Lee, Ann, Chen, Peng-Jen

“…Expressive speech-to-speech translation (S2ST) aims to transfer prosodic attributes of source speech to target speech while maintaining translation accuracy…”
Get full text

Assessing Evaluation Metrics for Speech-to-Speech Translation by Salesky, Elizabeth, Mader, Julian, Klinger, Severin

“…Speech-to-speech translation combines machine translation with speech synthesis, introducing evaluation challenges not present in either task alone. How to…”
Get full text

Text Rendering Strategies for Pixel Language Models by Lotz, Jonas F, Salesky, Elizabeth, Rust, Phillip, Elliott, Desmond

“…Pixel-based language models process text rendered as images, which allows them to handle any script, making them a promising approach to open vocabulary…”
Get full text

Phone Features Improve Speech Translation by Salesky, Elizabeth, Black, Alan W

“…End-to-end models for speech translation (ST) more tightly couple speech recognition (ASR) and machine translation (MT) than a traditional cascade of separate…”
Get full text

Assessing Evaluation Metrics for Speech-to-Speech Translation by Salesky, Elizabeth, Mäder, Julian, Klinger, Severin

“…Speech-to-speech translation combines machine translation with speech synthesis, introducing evaluation challenges not present in either task alone. How to…”
Get full text

Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer by Salesky, Elizabeth, Verma, Neha, Koehn, Philipp, Post, Matt

“…We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations. We experiment with two different data…”
Get full text

Robust Open-Vocabulary Translation from Visual Text Representations by Salesky, Elizabeth, Etter, David, Post, Matt

“…Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on…”
Get full text

Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing by Meister, Clara, Salesky, Elizabeth, Cotterell, Ryan

“…Prior work has explored directly regularizing the output distributions of probabilistic models to alleviate peaky (i.e. over-confident) predictions, a common…”
Get full text

Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation by Salesky, Elizabeth, Sperber, Matthias, Black, Alan W

“…Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences…”
Get full text

Fluent Translations from Disfluent Speech in End-to-End Speech Translation by Salesky, Elizabeth, Sperber, Matthias, Waibel, Alex

“…Spoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies. With the rise of…”
Get full text

Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation by Sperber, Matthias, Bojar, Ondřej, Haddow, Barry, Javorský, Dávid, Ma, Xutai, Negri, Matteo, Niehues, Jan, Polák, Peter, Salesky, Elizabeth, Sudoh, Katsuhito, Turchi, Marco

“…Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) Human evaluation is a…”
Get full text

Language Modelling with Pixels by Rust, Phillip, Lotz, Jonas F, Bugliarello, Emanuele, Salesky, Elizabeth, de Lhoneux, Miryam, Elliott, Desmond

“…Language models are defined over a finite set of inputs, which creates a vocabulary bottleneck when we attempt to scale the number of supported languages…”
Get full text

A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation by Huang, Wen-Chin, Peloquin, Benjamin, Kao, Justine, Wang, Changhan, Gong, Hongyu, Salesky, Elizabeth, Adi, Yossi, Lee, Ann, Chen, Peng-Jen

“…Expressive speech-to-speech translation (S2ST) aims to transfer prosodic attributes of source speech to target speech while maintaining translation accuracy…”
Get full text

A surprisal--duration trade-off across and within the world's languages by Pimentel, Tiago, Meister, Clara, Salesky, Elizabeth, Teufel, Simone, Blasi, Damián, Cotterell, Ryan

“…While there exist scores of natural languages, each with its unique features and idiosyncrasies, they all share a unifying theme: enabling human communication…”
Get full text

Towards Fluent Translations from Disfluent Speech by Salesky, Elizabeth, Burger, Susanne, Niehues, Jan, Waibel, Alex

“…When translating from speech, special consideration for conversational speech phenomena such as disfluencies is necessary. Most machine translation training…”
Get full text

SIGTYP 2021 Shared Task: Robust Spoken Language Identification by Salesky, Elizabeth, Abdullah, Badr M, Mielke, Sabrina J, Klyachko, Elena, Serikov, Oleg, Ponti, Edoardo, Kumar, Ritesh, Cotterell, Ryan, Vylomova, Ekaterina

“…While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For…”
Get full text

Optimizing Segmentation Granularity for Neural Machine Translation by Salesky, Elizabeth, Runge, Andrew, Coda, Alex, Niehues, Jan, Neubig, Graham

“…In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on…”
Get full text

A Corpus for Large-Scale Phonetic Typology by Salesky, Elizabeth, Chodroff, Eleanor, Pimentel, Tiago, Wiesner, Matthew, Cotterell, Ryan, Black, Alan W, Eisner, Jason

“…A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions. We present VoxClamantis v1.0,…”
Get full text