Search Results for author: Visar Berisha

Found 20 papers, 6 papers with code

Active Sequential Two-Sample Testing

no code implementations30 Jan 2023 Weizhi Li, Karthikeyan Natesan Ramamurthy, Prad Kadambi, Pouria Saidi, Gautam Dasarathy, Visar Berisha

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.

Two-sample testing

Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection

1 code implementation17 Nov 2022 Jianwei Zhang, Julie Liss, Suren Jayasuriya, Visar Berisha

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

1 code implementation17 Oct 2022 Sean Kinahan, Julie Liss, Visar Berisha

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?

no code implementations24 Mar 2022 Leo Hsu, Visar Berisha

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

no code implementations18 Mar 2022 Vikram C. Mathad, Julie M. Liss, Kathy Chapman, Nancy Scherer, Visar Berisha

Spectro-temporal dynamics of consonant-vowel (CV) transition regions are considered to provide robust cues related to articulation.

A label-efficient two-sample test

1 code implementation17 Nov 2021 Weizhi Li, Gautam Dasarathy, Karthikeyan Natesan Ramamurthy, Visar Berisha

Two-sample tests evaluate whether two samples are realizations of the same distribution (the null hypothesis) or two different distributions (the alternative hypothesis).

Two-sample testing

Restoring degraded speech via a modified diffusion model

no code implementations22 Apr 2021 Jianwei Zhang, Suren Jayasuriya, Visar Berisha

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

1 code implementation NeurIPS 2020 Weizhi Li, Gautam Dasarathy, Karthikeyan Natesan Ramamurthy, Visar Berisha

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.

Active Learning Meta-Learning +2

Regularization via Structural Label Smoothing

no code implementations7 Jan 2020 Weizhi Li, Gautam Dasarathy, Visar Berisha

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

no code implementations26 Nov 2019 Michael Saxon, Ayush Tripathi, Yishan Jiao, Julie Liss, Visar Berisha

To demonstrate that the features derived from these acoustic models are specific to hypernasal speech, we evaluate them across different dysarthria corpora.

BIG-bench Machine Learning

A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders

no code implementations4 Jun 2019 Rohit Voleti, Julie M. Liss, Visar Berisha

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

no code implementations24 Apr 2019 Rohit Voleti, Stephanie Woolridge, Julie M. Liss, Melissa Milanovic, Christopher R. Bowie, Visar Berisha

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

1 code implementation16 Nov 2018 Rohit Voleti, Julie M. Liss, Visar Berisha

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 Semantic Similarity +4

Triplet Network with Attention for Speaker Diarization

no code implementations4 Aug 2018 Huan Song, Megan Willi, Jayaraman J. Thiagarajan, Visar Berisha, Andreas Spanias

In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers.

Metric Learning speaker-diarization +1

Minimizing Area and Energy of Deep Learning Hardware Design Using Collective Low Precision and Structured Compression

no code implementations19 Apr 2018 Shihui Yin, Gaurav Srivastava, Shreyas K. Venkataramanaiah, Chaitali Chakrabarti, Visar Berisha, Jae-sun Seo

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

no code implementations21 Feb 2017 Alan Wisler, Visar Berisha, Andreas Spanias, Alfred O. Hero

Typically, estimating these quantities requires complete knowledge of the underlying distribution followed by multi-dimensional integration.

Density Estimation

Reducing the Model Order of Deep Neural Networks Using Information Theory

no code implementations16 May 2016 Ming Tu, Visar Berisha, Yu Cao, Jae-sun Seo

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.

General Classification Network Pruning +2

Empirical non-parametric estimation of the Fisher Information

1 code implementation6 Aug 2014 Visar Berisha, Alfred O. Hero

Traditional approaches to estimating the FIM require estimating the probability distribution function (PDF), or its parameters, along with its gradient or Hessian.

Density Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.