Search Results for author:
Found 23 papers, 7 papers with code
Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer
A good supervised embedding for a specific machine learning task is only sensitive to changes in the label of interest and is invariant to other confounding factors.
Requirements for Mass Adoption of Assistive Listening Technology by the General Public
Assistive listening systems (ALSs) dramatically increase speech intelligibility and reduce listening effort.
Smoothly Giving up: Robustness for Simple Models
There is a growing need for models that are interpretable and have reduced energy and computational cost (e. g., in health care analytics and federated learning).
Active Sequential Two-Sample Testing
The classification model is adaptively updated and then used to guide an active query scheme called bimodal query to label sample features in the regions with high dependency between the feature variables and the label variables.
Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection
In this paper, we propose a deep learning framework for generating acoustic feature embeddings sensitive to vocal quality and robust across different corpora.
TorchDIVA: An Extensible Computational Model of Speech Production built on an Open-Source Machine Learning Library
The DIVA model is a computational model of speech motor control that combines a simulation of the brain regions responsible for speech production with a model of the human vocal tract.
Does human speech follow Benford's Law?
Researchers have observed that the frequencies of leading digits in many man-made and naturally occurring datasets follow a logarithmic curve, with digits that start with the number 1 accounting for $\sim 30\%$ of all numbers in the dataset and digits that start with the number 9 accounting for $\sim 5\%$ of all numbers in the dataset.
Consonant-Vowel Transition Models Based on Deep Learning for Objective Evaluation of Articulation
Spectro-temporal dynamics of consonant-vowel (CV) transition regions are considered to provide robust cues related to articulation.
A label-efficient two-sample test
Two-sample tests evaluate whether two samples are realizations of the same distribution (the null hypothesis) or two different distributions (the alternative hypothesis).
Restoring degraded speech via a modified diffusion model
We replace the mel-spectrum upsampler in DiffWave with a deep CNN upsampler, which is trained to alter the degraded speech mel-spectrum to match that of the original speech.
Finding the Homology of Decision Boundaries with Active Learning
We theoretically analyze the proposed framework and show that the query complexity of our active learning algorithm depends naturally on the intrinsic complexity of the underlying manifold.
Comparing Fisher Information Regularization with Distillation for DNN Quantization
A large body of work addresses deep neural network (DNN) quantization and pruning to mitigate the high computational burden of deploying DNNs.
Regularization via Structural Label Smoothing
Regularization is an effective way to promote the generalization performance of machine learning models.
Robust Estimation of Hypernasality in Dysarthria with Acoustic Model Likelihood Features
To demonstrate that the features derived from these acoustic models are specific to hypernasal speech, we evaluate them across different dysarthria corpora.
A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders
Broadly speaking, the review is split into two categories: language features based on natural language processing and speech features based on speech signal processing.
Objective Assessment of Social Skills Using Automated Language Analysis for Identification of Schizophrenia and Bipolar Disorder
Furthermore, the same feature set can be used to build a strong binary classifier to distinguish between healthy controls and a clinical group (AUC = 0. 96) and also between patients within the clinical group with schizophrenia and bipolar I disorder (AUC = 0. 83).
Investigating the Effects of Word Substitution Errors on Sentence Embeddings
In this paper we investigate the effects of word substitution errors, such as those coming from automatic speech recognition errors (ASR), on several state-of-the-art sentence embedding methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Triplet Network with Attention for Speaker Diarization
In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers.
Minimizing Area and Energy of Deep Learning Hardware Design Using Collective Low Precision and Structured Compression
Deep learning algorithms have shown tremendous success in many recognition tasks; however, these algorithms typically include a deep neural network (DNN) structure and a large number of parameters, which makes it challenging to implement them on power/area-constrained embedded platforms.
Direct estimation of density functionals using a polynomial basis
Typically, estimating these quantities requires complete knowledge of the underlying distribution followed by multi-dimensional integration.
Reducing the Model Order of Deep Neural Networks Using Information Theory
In this paper, we propose a method to compress deep neural networks by using the Fisher Information metric, which we estimate through a stochastic optimization method that keeps track of second-order information in the network.
Empirically Estimable Classification Bounds Based on a New Divergence Measure
Information divergence functions play a critical role in statistics and information theory.
Empirical non-parametric estimation of the Fisher Information
Traditional approaches to estimating the FIM require estimating the probability distribution function (PDF), or its parameters, along with its gradient or Hessian.
