Unsupervised Testing Strategies for ASR

By Brian Strope, Doug Beeferman, Alexander Gruenstein, X. Lei. 2011

15 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mark John Francis Gales
2. Andy Zeng
3. Michael S. Ryoo
4. Vikas Sindhwani
5. Anton Ragni
6. Krzysztof Marcin Choromanski
7. Peter R. Florence
8. Qiujia Li

In Speech & Audio

1. Anton Ragni
2. Mark John Francis Gales
3. Qiujia Li
4. Vikas Sindhwani
5. Vincent Vanhoucke
6. Yu Wang
7. Andrew W. Senior
8. Yu Zhang

In Signal Processing

1. Anton Ragni
2. Mark John Francis Gales
3. Qiujia Li
4. Michael S. Ryoo
5. Krzysztof Marcin Choromanski
6. Vikas Sindhwani
7. Johnny Lee
8. Vincent Vanhoucke

Citations in the corpus

• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022, methodology): “As an example of using this approach, we extend the method in (Strope et al. 2011) to Socratic Models on egocentric perception, where we show it is possible to quantify the mutual dependence between foundation models without ground truth data.”
• Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks (2018, background): “ consideration. Deletions, however, are a very challenging type of error to recover from in both downstream and upstream tasks. Moreover, drifts in deployment domains either planned [16] or unplanned [17] typically lead to large increases in deletion errors. Though schemes such as frame weighting [1”