Picture for Martijn Bartelds

Martijn Bartelds

ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets

Add code
Jun 12, 2024
Viaarxiv icon

Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation

Add code
May 19, 2023
Figure 1 for Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation
Figure 2 for Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation
Figure 3 for Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation
Figure 4 for Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation
Viaarxiv icon

Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions

Add code
Feb 09, 2023
Figure 1 for Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions
Viaarxiv icon

Quantifying Language Variation Acoustically with Few Resources

Add code
May 05, 2022
Figure 1 for Quantifying Language Variation Acoustically with Few Resources
Figure 2 for Quantifying Language Variation Acoustically with Few Resources
Figure 3 for Quantifying Language Variation Acoustically with Few Resources
Figure 4 for Quantifying Language Variation Acoustically with Few Resources
Viaarxiv icon

Automated speech tools for helping communities process restricted-access corpora for language revival efforts

Add code
Apr 24, 2022
Figure 1 for Automated speech tools for helping communities process restricted-access corpora for language revival efforts
Figure 2 for Automated speech tools for helping communities process restricted-access corpora for language revival efforts
Figure 3 for Automated speech tools for helping communities process restricted-access corpora for language revival efforts
Figure 4 for Automated speech tools for helping communities process restricted-access corpora for language revival efforts
Viaarxiv icon

Adapting Monolingual Models: Data can be Scarce when Language Similarity is High

Add code
May 22, 2021
Figure 1 for Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
Figure 2 for Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
Figure 3 for Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
Figure 4 for Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
Viaarxiv icon

Leveraging neural representations for facilitating access to untranscribed speech from endangered languages

Add code
Mar 26, 2021
Figure 1 for Leveraging neural representations for facilitating access to untranscribed speech from endangered languages
Figure 2 for Leveraging neural representations for facilitating access to untranscribed speech from endangered languages
Figure 3 for Leveraging neural representations for facilitating access to untranscribed speech from endangered languages
Viaarxiv icon

Neural Representations for Modeling Variation in English Speech

Add code
Nov 25, 2020
Figure 1 for Neural Representations for Modeling Variation in English Speech
Figure 2 for Neural Representations for Modeling Variation in English Speech
Figure 3 for Neural Representations for Modeling Variation in English Speech
Figure 4 for Neural Representations for Modeling Variation in English Speech
Viaarxiv icon