Alert button
Picture for Ramon Sanabria

Ramon Sanabria

Alert button

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

Feb 04, 2024
Alexandra Saliba, Yuanchao Li, Ramon Sanabria, Catherine Lai

Viaarxiv icon

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

Jun 03, 2023
Ramon Sanabria, Ondrej Klejch, Hao Tang, Sharon Goldwater

Figure 1 for Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling
Figure 2 for Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling
Figure 3 for Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling
Figure 4 for Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling
Viaarxiv icon

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

Mar 31, 2023
Ramon Sanabria, Nikolay Bogoychev, Nina Markl, Andrea Carmantini, Ondrej Klejch, Peter Bell

Figure 1 for The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR
Figure 2 for The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR
Figure 3 for The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR
Viaarxiv icon

Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models

Oct 28, 2022
Ramon Sanabria, Hao Tang, Sharon Goldwater

Figure 1 for Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models
Figure 2 for Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models
Figure 3 for Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models
Figure 4 for Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models
Viaarxiv icon

Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training

Mar 02, 2022
Ramon Sanabria, Wei-Ning Hsu, Alexei Baevski, Michael Auli

Figure 1 for Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training
Figure 2 for Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training
Figure 3 for Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training
Figure 4 for Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training
Viaarxiv icon

On the Difficulty of Segmenting Words with Attention

Sep 21, 2021
Ramon Sanabria, Hao Tang, Sharon Goldwater

Figure 1 for On the Difficulty of Segmenting Words with Attention
Figure 2 for On the Difficulty of Segmenting Words with Attention
Figure 3 for On the Difficulty of Segmenting Words with Attention
Figure 4 for On the Difficulty of Segmenting Words with Attention
Viaarxiv icon

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

Apr 08, 2021
Ramon Sanabria, Austin Waters, Jason Baldridge

Figure 1 for Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
Figure 2 for Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
Figure 3 for Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
Figure 4 for Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
Viaarxiv icon

Multimodal Speech Recognition with Unstructured Audio Masking

Oct 16, 2020
Tejas Srinivasan, Ramon Sanabria, Florian Metze, Desmond Elliott

Figure 1 for Multimodal Speech Recognition with Unstructured Audio Masking
Figure 2 for Multimodal Speech Recognition with Unstructured Audio Masking
Figure 3 for Multimodal Speech Recognition with Unstructured Audio Masking
Figure 4 for Multimodal Speech Recognition with Unstructured Audio Masking
Viaarxiv icon

Fine-Grained Grounding for Multimodal Speech Recognition

Oct 05, 2020
Tejas Srinivasan, Ramon Sanabria, Florian Metze, Desmond Elliott

Figure 1 for Fine-Grained Grounding for Multimodal Speech Recognition
Figure 2 for Fine-Grained Grounding for Multimodal Speech Recognition
Figure 3 for Fine-Grained Grounding for Multimodal Speech Recognition
Figure 4 for Fine-Grained Grounding for Multimodal Speech Recognition
Viaarxiv icon