Chandan K. A. Reddy — accepted AI-conference papers

2025

Impairments are Clustered in Latents of Deep Neural Network-based Speech Quality Models

Fredrik Cumlin, Xinyu Liang, Victor Ungureanu, Chandan K. A. Reddy, Christian Schüldt, Saikat Chatterjee

ICASSP 2025accepted

In this article, we provide an experimental observation: Deep neural network (DNN) based speech quality assessment (SQA) models have inherent latent representations where many types of impairments are clustered. While DNN-based SQA models are not trained for impairment classification, our experiment…

Cited by 0 Source ↗Scholar ↗

2025

Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on Hearables

Artem Dementyev, Chandan K. A. Reddy, Scott Wisdom, Navin Chatlani, John R. Hershey, Richard F. Lyon

ICASSP 2025accepted

Low latency models are critical for real-time speech enhancement applications, such as hearing aids and hearables. However, the sub-millisecond latency space for resource-constrained hearables remains underexplored. We demonstrate speech enhancement using a computationally efficient minimum-phase FI…

Cited by 0 Source ↗Scholar ↗

2023

AURA: Privacy-Preserving Augmentation to Improve Test Set Diversity in Speech Enhancement

Xavier Gitiaux, Aditya Khant, Ebrahim Beyrami, Chandan K. A. Reddy, Jayant Gupchup, Ross Cutler

ICASSP 2023accepted

Speech enhancement models running in production environments are commonly trained on publicly available data. This approach leads to regressions due to the lack of training/testing on representative customer data. Moreover, due to privacy reasons, developers cannot listen to customer content. This ‘…

Cited by 0 Source ↗Scholar ↗

2022

Dnsmos P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors

Chandan K. A. Reddy, Vishak Gopal, Ross Cutler

ICASSP 2022accepted

Human subjective evaluation is the "gold standard" to evaluate speech quality optimized for human perception. Perceptual objective metrics serve as a proxy for subjective scores. We have recently developed a non-intrusive speech quality metric called Deep Noise Suppression Mean Opinion Score (DNSMOS…

Cited by 0 Source ↗Scholar ↗

2021

Dnsmos: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors

Chandan K. A. Reddy, Vishak Gopal, Ross Cutler

ICASSP 2021accepted

Human subjective evaluation is the "gold standard" to evaluate speech quality optimized for human perception. Perceptual objective metrics serve as a proxy for subjective scores. The conventional and widely used metrics require a reference clean speech signal, which is unavailable in real recordings…

Cited by 0 Source ↗Scholar ↗

2021

ICASSP 2021 Deep Noise Suppression Challenge

Chandan K. A. Reddy, Harishchandra Dubey, Vishak Gopal, Ross Cutler, Sebastian Braun, Hannes Gamper +2

ICASSP 2021accepted

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. We recently organized a DNS challenge special session at INTERSPEECH 2020 where we open-sourced training and test datasets for researchers to tr…

Cited by 0 Source ↗Scholar ↗

2021

Towards Efficient Models for Real-Time Deep Noise Suppression

Sebastian Braun, Hannes Gamper, Chandan K. A. Reddy, Ivan Tashev

ICASSP 2021accepted

With recent research advancements, deep learning models are be-coming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality and background noise reduction, the main challenge is to ob…

Cited by 0 Source ↗Scholar ↗

2020

Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement

Yangyang Xia, Sebastian Braun, Chandan K. A. Reddy, Harishchandra Dubey, Ross Cutler, Ivan Tashev

ICASSP 2020accepted

This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that enhances short-time speech spectra on a single-frame-in, sing…

Cited by 0 Source ↗Scholar ↗

2019

Non-intrusive Speech Quality Assessment Using Neural Networks

Anderson R. Avila, Hannes Gamper, Chandan K. A. Reddy, Ross Cutler, Ivan Tashev, Johannes Gehrke

ICASSP 2019accepted

Estimating the perceived quality of an audio signal is critical for many multimedia and audio processing systems. Providers strive to offer optimal and reliable services in order to increase the user quality of experience (QoE). In this work, we present an investigation of the applicability of neura…

Cited by 0 Source ↗Scholar ↗

2017

ICA based single microphone Blind Speech Separation technique using non-linear estimation of speech

Chandan K. A. Reddy, Anshuman Ganguly, Issa M. S. Panahi

ICASSP 2017accepted

In this paper, a Blind Speech Separation (BSS) technique is introduced based on Independent Component Analysis (ICA) for underdetermined single microphone case. In general, ICA uses noisy speech from at least two microphones to separate speech and noise. But ICA fails to separate when only one strea…

Cited by 0 Source ↗Scholar ↗

2015

Improved Parallel Feedback Active noise control using linear prediction for adaptive noise decomposition

Anshuman Ganguly, Chandan K. A. Reddy, Issa M. S. Panahi

ICASSP 2015accepted

This paper presents an improved Parallel Feedback Active noise control (PFANC) method with adaptive noise signal decomposition using NLMS based linear prediction. The proposed method is tested for several stationary periodic signals, quasi-periodic signals and non-stationary signals buried in Additi…

Cited by 0 Source ↗Scholar ↗