54 citations · 190 across the 11 of their papers we have counts for
11 papers
Enhancing Online Learning Efficiency Through Heterogeneous Resource Integration with a Multi-Agent RAG System
Devansh Srivastav, Hasan Md Tusfiqur Alam, Afsaneh Asaei +3
Efficient online learning requires seamless access to diverse resources such as videos, code repositories, documentation, and general web content. This poster paper introduces earl…
Information Theoretic Analysis of DNN-HMM Acoustic Modeling
Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
We propose an information theoretic framework for quantitative assessment of acoustic modeling for hidden Markov model (HMM) based automatic speech recognition (ASR). Acoustic mode…
Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models
Pranay Dighe, Afsaneh Asaei, Herve Bourlard
Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the target…
Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding
Milos Cernak, Alexandros Lazaridis, Afsaneh Asaei +1
Most current very low bit rate (VLBR) speech coding systems use hidden Markov model (HMM) based speech recognition/synthesis techniques. This allows transmission of information (su…
Exploiting Low-dimensional Structures to Enhance DNN Based Acoustic Modeling in Speech Recognition
Pranay Dighe, Gil Luyet, Afsaneh Asaei +1
We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low-dimensional subspaces. To that end, the training pos…
On Structured Sparsity of Phonological Posteriors for Linguistic Parsing
Milos Cernak, Afsaneh Asaei, Hervé Bourlard
The speech signal conveys information on different time scales from short time scale or segmental, associated to phonological and phonetic information to long time scale or supra s…
TDOA Matrices: Algebraic Properties and their Application to Robust Denoising with Missing Data
Jose Velasco, Daniel Pizarro, Javier Macias-Guarasa +1
Measuring the Time delay of Arrival (TDOA) between a set of sensors is the basic setup for many applications, such as localization or signal beamforming. This paper presents the se…
A New Identity for the Least-square Solution of Overdetermined Set of Linear Equations
Saeid Haghighatshoar, Mohammad J. Taghizadeh, Afsaneh Asaei
In this paper, we prove a new identity for the least-square solution of an over-determined set of linear equation , where is an full-rank matrix, is a col…
Ad Hoc Microphone Array Calibration: Euclidean Distance Matrix Completion Algorithm and Theoretical Guarantees
Mohammad J. Taghizadeh, Reza Parhizkar, Philip N. Garner +2
This paper addresses the problem of ad hoc microphone array calibration where only partial information about the distances between microphones is available. We construct a matrix c…
Convexity in source separation: Models, geometry, and algorithms
Michael B. McCoy, Volkan Cevher, Quoc Tran Dinh +2
Source separation or demixing is the process of extracting multiple components entangled within a signal. Contemporary signal processing presents a host of difficult source separat…
Structured Sparsity Models for Multiparty Speech Recovery from Reverberant Recordings
Afsaneh Asaei, Mohammad Golbabaee, Hervé Bourlard +1
We tackle the multi-party speech recovery problem through modeling the acoustic of the reverberant chambers. Our approach exploits structured sparsity models to perform room modeli…