22 citations · 27 across the 5 of their papers we have counts for
6 papers
Training Autoregressive Speech Recognition Models with Limited in-domain Supervision
Chak-Fai Li, Francis Keith, William Hartmann +1
Advances in self-supervised learning have significantly reduced the amount of transcribed audio required for training. However, the majority of work in this area is focused on read…
Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscripts
Chak-Fai Li, Francis Keith, William Hartmann +2
Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, da…
Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition
Andrew Slottje, Shannon Wotherspoon, William Hartmann +2
Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-s…
Learning from Noisy Labels with Noise Modeling Network
Zhuolin Jiang, Jan Silovsky, Man-Hung Siu +3
Multi-label image classification has generated significant interest in recent years and the performance of such systems often suffers from the not so infrequent occurrence of incor…
Cross-lingual Information Retrieval with BERT
Zhuolin Jiang, Amro El-Jaroudi, William Hartmann +2
Multiple neural language models have been developed recently, e.g., BERT and XLNet, and achieved impressive results in various NLP tasks including sentence classification, question…
Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data
Herbert Gish, Jan Silovsky, Man-Ling Sung +3
We investigate the problem of machine learning with mislabeled training data. We try to make the effects of mislabeled training better understood through analysis of the basic mode…