activity
20172026
most citedMultitask Learning For Different Subword Segmentations In Neural Machine Translation

3 citations · 4 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

16 papers · 1 filter

cs.CL2024

Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems

Frank Palma Gomez, Ramon Sanabria, Yun-hsuan Sung +3

Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval sy…

cs.CL20241 cited

Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition

Alexandra Saliba, Yuanchao Li, Ramon Sanabria +1

The efficacy of self-supervised speech models has been validated, yet the optimal utilization of their representations remains challenging across diverse tasks. In this study, we d…

cs.CL2023

Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling

Ramon Sanabria, Ondrej Klejch, Hao Tang +1

Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KN…

cs.CL20231 cited

The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR

Ramon Sanabria, Nikolay Bogoychev, Nina Markl +3

English is the most widely spoken language in the world, used daily by millions of people as a first or second language in many different contexts. As a result, there are many vari…

cs.CL2021

On the Difficulty of Segmenting Words with Attention

Ramon Sanabria, Hao Tang, Sharon Goldwater

Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models traine…

cs.CL2021

Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval

Ramon Sanabria, Austin Waters, Jason Baldridge

Speech-based image retrieval has been studied as a proxy for joint representation learning, usually without emphasis on retrieval itself. As such, it is unclear how well speech-bas…