Search Results for author:
Found 24 papers, 8 papers with code
Analyzing the effect of neural network architecture on training performance
Through novel theoretical and experimental results, we show how the neural net architecture affects gradient confusion, and thus the efficiency of training.
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck.
Large-scale Language Model Rescoring on Long-form Data
In this work, we study the impact of Large-scale Language Models (LLM) on Automated Speech Recognition (ASR) of YouTube videos, which we use as a source for long-form ASR.
Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
We address this limitation by distilling punctuation knowledge from a bidirectional teacher language model (LM) trained on written, punctuated text.
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model
We explore unifying a neural segmenter with two-pass cascaded encoder ASR into a single model.
Modular Hybrid Autoregressive Transducer
In this work, we propose a modular hybrid autoregressive transducer (MHAT) that has structurally separated label and blank decoders to predict label and blank distributions, respectively, along with a shared acoustic encoder.
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition.
Detecting Unintended Memorization in Language-Model-Fused ASR
End-to-end (E2E) models are often being accompanied by language models (LMs) via shallow fusion for boosting their overall quality as well as recognition of rare words.
Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition
We down-select a large corpus of web search queries by a factor of 53x and achieve better LM perplexities than without down-selection.
Capitalization Normalization for Language Modeling with an Accurate and Efficient Hierarchical RNN Model
Capitalization normalization (truecasing) is the task of restoring the correct case (uppercase or lowercase) of noisy text.
Scaling End-to-End Models for Large-Scale Multilingual ASR
Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data.
Lookup-Table Recurrent Language Models for Long Tail Speech Recognition
We introduce Lookup-Table Language Models (LookupLM), a method for scaling up the size of RNN language models with only a constant increase in the floating point operations, by increasing the expressivity of the embedding table.
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision.
Ranked #137 on
Image Classification
on CIFAR-10
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
We consider a particularly malicious poisoning attack that is both "from scratch" and "clean label", meaning we analyze an attack that successfully works against new, randomly initialized models, and is nearly imperceptible to humans, all while perturbing only a small fraction of the training data.
MetaPoison: Practical General-purpose Clean-label Data Poisoning
Existing attacks for data poisoning neural networks have relied on hand-crafted heuristics, because solving the poisoning problem directly via bilevel optimization is generally thought of as intractable for deep models.
DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images
In addition to high segmentation accuracy, we show that our cleansed images achieve a significant boost in recognition accuracy by popular OCR software such as Tesseract 4. 0.
Optical Character Recognition
Optical Character Recognition (OCR)
Deep k-NN Defense against Clean-label Data Poisoning Attacks
Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a particular test sample during inference.
The Effect of Neural Net Architecture on Gradient Confusion & Training Performance
Through novel theoretical and experimental results, we show how the neural net architecture affects gradient confusion, and thus the efficiency of training.
Understanding Generalization through Visualizations
The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive.
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data.
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
Our results show that, for popular initialization techniques, increasing the width of neural networks leads to lower gradient confusion, and thus faster model training.
Accurate, Data-Efficient Learning from Noisy, Choice-Based Labels for Inherent Risk Scoring
The data collection is synthetic; examples are crafted using optimal experimental design methods, obviating the need for real data which is often difficult to obtain due to regulatory concerns.
Are adversarial examples inevitable?
Using experiments, we explore the implications of theoretical guarantees for real-world problems and discuss how factors such as dimensionality and image complexity limit a classifier's robustness against adversarial examples.
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the labeling of training data.
