102 citations · 207 across the 15 of their papers we have counts for
16 papers
CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment
Anurag Kumar, Raghuveer Peri, Jon Burnsky +4
Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a highe…
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
Raghuveer Peri, Sai Muralidhar Jayanthi, Srikanth Ronanki +11
Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and r…
VoxWatch: An open-set speaker recognition benchmark on VoxCeleb
Raghuveer Peri, Seyed Omid Sadjadi, Daniel Garcia-Romero
Despite its broad practical applications such as in fraud prevention, open-set speaker identification (OSI) has received less attention in the speaker recognition community compare…
User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition in Federated Learning
Tiantian Feng, Raghuveer Peri, Shrikanth Narayanan
Many existing privacy-enhanced speech emotion recognition (SER) frameworks focus on perturbing the original speech data through adversarial training within a centralized machine le…
Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems
Nicholas Mehlman, Anirudh Sreeram, Raghuveer Peri +1
A variety of recent works have looked into defenses for deep neural networks against adversarial attacks particularly within the image processing domain. Speech processing applicat…
To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition
Raghuveer Peri, Krishna Somandepalli, Shrikanth Narayanan
Speaker recognition is increasingly used in several everyday applications including smart speakers, customer care centers and other speech-driven analytics. It is crucial to accura…
Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems
Anirudh Sreeram, Nicholas Mehlman, Raghuveer Peri +2
In this paper we investigate speech denoising as a defense against adversarial attacks on automatic speech recognition (ASR) systems. Adversarial attacks attempt to force misclassi…
Automated Evaluation Of Psychotherapy Skills Using Speech And Language Technologies
Nikolaos Flemotomos, Victor R. Martinez, Zhuohao Chen +13
With the growing prevalence of psychological interventions, it is vital to have measures which rate the effectiveness of psychological care to assist in training, supervision, and…
Disentanglement for audio-visual emotion recognition using multitask setup
Raghuveer Peri, Srinivas Parthasarathy, Charles Bradshaw +1
Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with mu…
Adversarial defense for deep speaker recognition using hybrid adversarial training
Monisankha Pal, Arindam Jati, Raghuveer Peri +3
Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversar…
Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems
Arindam Jati, Chin-Cheng Hsu, Monisankha Pal +3
Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart s…
Meta-learning with Latent Space Clustering in Generative Adversarial Network for Speaker Diarization
Monisankha Pal, Manoj Kumar, Raghuveer Peri +5
The performance of most speaker diarization systems with x-vector embeddings is both vulnerable to noisy environments and lacks domain robustness. Earlier work on speaker diarizati…
An empirical analysis of information encoded in disentangled neural speaker representations
Raghuveer Peri, Haoqi Li, Krishna Somandepalli +2
The primary characteristic of robust speaker representations is that they are invariant to factors of variability not related to speaker identity. Disentanglement of speaker repres…
Robust speaker recognition using unsupervised adversarial invariance
Raghuveer Peri, Monisankha Pal, Arindam Jati +2
In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations…
A study of semi-supervised speaker diarization system using gan mixture model
Monisankha Pal, Manoj Kumar, Raghuveer Peri +1
We propose a new speaker diarization system based on a recently introduced unsupervised clustering technique namely, generative adversarial network mixture model (GANMM). The propo…
Speaker diarization using latent space clustering in generative adversarial network
Monisankha Pal, Manoj Kumar, Raghuveer Peri +5
In this work, we propose deep latent space clustering for speaker diarization using generative adversarial network (GAN) backprojection with the help of an encoder network. The pro…