9 citations · 22 across the 7 of their papers we have counts for
7 papers
The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources
Shayne Longpre, Stella Biderman, Alon Albalak +20
Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible development practices, we introduce the Foun…
Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens
Nay San, Georgios Paraskevopoulos, Aryaman Arora +4
While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relative…
Developing Speech Processing Pipelines for Police Accountability
Anjalie Field, Prateek Verma, Nay San +2
Police body-worn cameras have the potential to improve accountability and transparency in policing. Yet in practice, they result in millions of hours of footage that is never revie…
Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation
Martijn Bartelds, Nay San, Bradley McDonnell +2
The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech…
Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions
Nay San, Martijn Bartelds, Blaine Billings +7
Recent research using pre-trained transformer models suggests that just 10 minutes of transcribed speech may be enough to fine-tune such a model for automatic speech recognition (A…
Automated speech tools for helping communities process restricted-access corpora for language revival efforts
Nay San, Martijn Bartelds, Tolúlopé Ògúnrèmí +6
Many archival recordings of speech from endangered languages remain unannotated and inaccessible to community members and language learning programs. One bottleneck is the time-int…
Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages
Nay San, Martijn Bartelds, Mitchell Browne +9
Pre-trained speech representations like wav2vec 2.0 are a powerful tool for automatic speech recognition (ASR). Yet many endangered languages lack sufficient data for pre-training…