Search Results for author:
Found 24 papers, 5 papers with code
Exploratory Evaluation of Speech Content Masking
Most recent speech privacy efforts have focused on anonymizing acoustic speaker attributes but there has not been as much research into protecting information from speech content.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Protecting Publicly Available Data With Machine Learning Shortcuts
Machine-learning (ML) shortcuts or spurious correlations are artifacts in datasets that lead to very good training and test performance but severely limit the model's generalization capability.
Localized Shortcut Removal
This is often due to the existence of machine learning shortcuts - features in the data that are predictive but unrelated to the problem at hand.
Attacker Attribution of Audio Deepfakes
This is despite the fact that attribution (who created which fake?)
Analysis of Voice Conversion and Code-Switching Synthesis Using VQ-VAE
We found that speech synthesis quality degrades after increasing the number of language switches within an utterance and decreasing the number of words.
Same Cause; Different Effects in the Brain
It is then natural to ask: "Is the activity in these different brain zones caused by the stimulus properties in the same way?"
Behavior measures are predicted by how information is encoded in an individual's brain
We hypothesize that individual differences in how information is encoded in the brain are task-specific and predict different behavior measures.
Revisiting Speech Content Privacy
In this paper, we discuss an important aspect of speech privacy: protecting spoken content.
Human Perception of Audio Deepfakes
The recent emergence of deepfakes has brought manipulated and generated content to the forefront of machine learning research.
Exploring Disentanglement with Multilingual and Monolingual VQ-VAE
This work examines the content and usefulness of disentangled phone and speaker representations from two separately trained VQ-VAE systems: one trained on multilingual data and another trained on monolingual data.
Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm
Additionally, phones can be recognized from sub-phone VQ codebook indices in our semi-supervised VQ-VAE better than self-supervised with global conditions.
Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
Our NN predicts MOS with a high correlation to human judgments.
Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
Our system used convolutional neural networks (CNNs) and a representation of the speech audio that combined x-vector attack embeddings with signal processing features.
Recognizing Emotions in Video Using Multimodal DNN Feature Fusion
We present our system description of input-level multimodal fusion of audio, video, and text for recognition of emotions and their intensities for the 2018 First Grand Challenge on Computational Modeling of Human Multimodal Language.
DNN Multimodal Fusion Techniques for Predicting Video Sentiment
Our work also improves feature selection for unimodal sentiment analysis, while proposing a novel and effective multimodal fusion architecture for this task.
Twitter Language Identification Of Similar Languages And Dialects Without Ground Truth
We present a new method to bootstrap filter Twitter language ID labels in our dataset for automatic language identification (LID).
A New Twitter Verb Lexicon for Natural Language Processing
We describe in-progress work on the creation of a new lexical resource that contains a list of 486 verbs annotated with quantified temporal durations for the events that they describe.
