default search action
Devang Naik
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [j3]Minsik Cho
, Keivan Alizadeh-Vahid
eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models. IEEE Comput. Archit. Lett. 23(1): 37-40 (2024) - [c21]Kumari Nishu, Minsik Cho, Paul Dixon, Devang Naik:
Flexible Keyword Spotting Based on Homogeneous Audio-Text Embedding. ICASSP 2024: 5050-5054 - [c20]Alexandre Bittar, Paul Dixon, Mohammad Samragh, Kumari Nishu, Devang Naik:
Improving Vision-Inspired Keyword Spotting Using Dynamic Module Skipping in Streaming Conformer Encoder. ICASSP 2024: 10386-10390 - [c19]Minsik Cho, Mohammad Rastegari, Devang Naik:
KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation. ICML 2024 - [i21]Minsik Cho, Mohammad Rastegari, Devang Naik:
KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation. CoRR abs/2405.05329 (2024) - [i20]Arnav Kundu, Prateeth Nayak, Hywel Richards, Priyanka Padmanabhan, Devang Naik:
RepCNN: Micro-sized, Mighty Models for Wakeword Detection. CoRR abs/2406.02652 (2024) - [i19]Arnav Kundu, Yanzi Jin, Mohammad Hossein Sekhavat, Maxwell Horton, Danny Tormoen, Devang Naik:
An Efficient and Streaming Audio Visual Active Speaker Detection System. CoRR abs/2409.09018 (2024) - [i18]Kumari Nishu, Minsik Cho, Devang Naik:
SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spotting. CoRR abs/2409.09067 (2024) - [i17]Mohammad Samragh, Seyed-Iman Mirzadeh, Keivan Alizadeh-Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar:
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization. CoRR abs/2409.12903 (2024) - 2023
- [c18]Arnav Kundu, Mohammad Samragh, Minsik Cho, Priyanka Padmanabhan, Devang Naik:
HEiMDaL: Highly Efficient Method for Detection and Localization of Wake-Words. ICASSP 2023: 1-5 - [c17]Mohammad Samragh, Arnav Kundu, Ting-Yao Hu, Aman Chadha, Ashish Srivastava, Minsik Cho, Oncel Tuzel, Devang Naik:
I See What You Hear: A Vision-Inspired Method to Localize Words. ICASSP 2023: 1-5 - [c16]Kumari Nishu, Minsik Cho, Devang Naik:
Matching Latent Encoding for Audio-Text based Keyword Spotting. INTERSPEECH 2023: 1613-1617 - [c15]Minsik Cho, Saurabh Adya, Devang Naik:
PDP: Parameter-free Differentiable Pruning is All You Need. NeurIPS 2023 - [i16]Minsik Cho, Saurabh Adya, Devang Naik:
PDP: Parameter-free Differentiable Pruning is All You Need. CoRR abs/2305.11203 (2023) - [i15]Kumari Nishu, Minsik Cho, Devang Naik:
Matching Latent Encoding for Audio-Text based Keyword Spotting. CoRR abs/2306.05245 (2023) - [i14]Kumari Nishu, Minsik Cho, Paul Dixon, Devang Naik:
Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding. CoRR abs/2308.06472 (2023) - [i13]Alexandre Bittar, Paul Dixon, Mohammad Samragh, Kumari Nishu, Devang Naik:
Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder. CoRR abs/2309.00140 (2023) - [i12]Minsik Cho, Keivan Alizadeh-Vahid, Qichen Fu, Saurabh Adya, Carlo C. del Mundo, Mohammad Rastegari, Devang Naik, Peter Zatloukal:
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models. CoRR abs/2309.00964 (2023) - [i11]Mohammad Samragh, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Fartash Faghri, Devang Naik, Oncel Tuzel, Mohammad Rastegari:
Weight subcloning: direct initialization of transformers using larger pretrained ones. CoRR abs/2312.09299 (2023) - 2022
- [i10]Mohammad Samragh, Arnav Kundu, Ting-Yao Hu, Minsik Cho, Aman Chadha, Ashish Shrivastava, Oncel Tuzel, Devang Naik:
I see what you hear: a vision-inspired method to localize words. CoRR abs/2210.13567 (2022) - [i9]Arnav Kundu, Mohammad Samragh Razlighi, Minsik Cho, Priyanka Padmanabhan, Devang Naik:
HEiMDaL: Highly Efficient Method for Detection and Localization of wake-words. CoRR abs/2210.15425 (2022) - 2021
- [c14]Ashish Shrivastava, Arnav Kundu, Chandra Dhir, Devang Naik, Oncel Tuzel:
Optimize What Matters: Training DNN-Hmm Keyword Spotting Model Using End Metric. ICASSP 2021: 4000-4004 - [c13]Pranay Dighe, Erik Marchi, Srikanth Vishnubhotla, Sachin Kajarekar, Devang Naik:
Knowledge Transfer for Efficient on-Device False Trigger Mitigation. ICASSP 2021: 6838-6842 - [c12]Zakaria Aldeneh, Anushree Prasanna Kumar, Barry-John Theobald, Erik Marchi, Sachin Kajarekar, Devang Naik, Ahmed Hussen Abdelaziz:
On The Role of Visual Cues in Audiovisual Speech Enhancement. ICASSP 2021: 8423-8427 - 2020
- [j2]Jason Wung
Robust Multichannel Linear Prediction for Online Speech Dereverberation Using Weighted Householder Least Squares Lattice Adaptive Filter. IEEE Trans. Signal Process. 68: 3559-3574 (2020) - [j1]Sarmad Malik
Double-Talk Robust Multichannel Acoustic Echo Cancellation Using Least-Squares MIMO Adaptive Filtering: Transversal, Array, and Lattice Forms. IEEE Trans. Signal Process. 68: 4887-4902 (2020) - [c11]Siddharth Sigtia, Erik Marchi, Sachin Kajarekar, Devang Naik, John Bridle:
Multi-Task Learning for Speaker Verification and Voice Trigger Detection. ICASSP 2020: 6844-6848 - [c10]Vasudha Kowtha, Vikramjit Mitra, Chris Bartels, Erik Marchi, Sue Booker, William Caruso, Sachin Kajarekar, Devang Naik:
Detecting Emotion Primitives from Speech and Their Use in Discerning Categorical Emotions. ICASSP 2020: 7164-7168 - [c9]Pranay Dighe, Saurabh Adya, Nuoyu Li, Srikanth Vishnubhotla, Devang Naik, Adithya Sagar, Ying Ma, Stephen Pulman, Jason D. Williams
Lattice-Based Improvements for Voice Triggering Using Graph Neural Networks. ICASSP 2020: 7459-7463 - [c8]Rishika Agarwal, Xiaochuan Niu, Pranay Dighe, Srikanth Vishnubhotla, Sameer Badaskar, Devang Naik:
Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation. INTERSPEECH 2020: 4288-4292 - [i8]Siddharth Sigtia, Erik Marchi, Sachin Kajarekar, Devang Naik, John Bridle:
Multi-task Learning for Speaker Verification and Voice Trigger Detection. CoRR abs/2001.10816 (2020) - [i7]Pranay Dighe, Saurabh Adya, Nuoyu Li, Srikanth Vishnubhotla, Devang Naik, Adithya Sagar, Ying Ma, Stephen Pulman, Jason D. Williams:
Lattice-based Improvements for Voice Triggering Using Graph Neural Networks. CoRR abs/2001.10822 (2020) - [i6]Vasudha Kowtha, Vikramjit Mitra, Chris Bartels, Erik Marchi, Sue Booker, William Caruso, Sachin Kajarekar, Devang Naik:
Detecting Emotion Primitives from Speech and their use in discerning Categorical Emotions. CoRR abs/2002.01323 (2020) - [i5]Zakaria Aldeneh, Anushree Prasanna Kumar, Barry-John Theobald, Erik Marchi, Sachin Kajarekar, Devang Naik, Ahmed Hussen Abdelaziz:
Self-supervised Learning of Visual Speech Features with Audiovisual Speech Enhancement. CoRR abs/2004.12031 (2020) - [i4]Rishika Agarwal, Xiaochuan Niu, Pranay Dighe, Srikanth Vishnubhotla, Sameer Badaskar, Devang Naik:
Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation. CoRR abs/2008.08113 (2020) - [i3]Pranay Dighe, Erik Marchi, Srikanth Vishnubhotla, Sachin Kajarekar, Devang Naik:
Knowledge Transfer for Efficient On-device False Trigger Mitigation. CoRR abs/2010.10591 (2020) - [i2]Ashish Shrivastava, Arnav Kundu, Chandra Dhir, Devang Naik, Oncel Tuzel:
Optimize what matters: Training DNN-HMM Keyword Spotting Model Using End Metric. CoRR abs/2011.01151 (2020)
2010 – 2019
- 2019
- [c7]Vikramjit Mitra, Sue Booker, Erik Marchi, David Scott Farrar, Ute Dorothea Peitz, Bridget Cheng, Ermine Teves, Anuj Mehta, Devang Naik:
Leveraging Acoustic Cues and Paralinguistic Embeddings to Detect Expression from Voice. INTERSPEECH 2019: 1651-1655 - [c6]Qiong Hu, Erik Marchi, David Winarsky, Yannis Stylianou, Devang Naik, Sachin Kajarekar:
Neural Text-to-Speech Adaptation from Low Quality Public Recordings. SSW 2019: 24-28 - [i1]Vikramjit Mitra, Sue Booker, Erik Marchi, David Scott Farrar, Ute Dorothea Peitz, Bridget Cheng, Ermine Teves, Anuj Mehta, Devang Naik:
Leveraging Acoustic Cues and Paralinguistic Embeddings to Detect Expression from Voice. CoRR abs/1907.00112 (2019)
2000 – 2009
- 2001
- [c5]Jerome R. Bellegarda, Devang Naik, Matthias Neeracher, Kim E. A. Silverman:
Language-independent, short-enrollment voice verification over a far-field microphone. ICASSP 2001: 445-448
1990 – 1999
- 1999
- [c4]Kim E. A. Silverman, Victoria Anderson, Jerome R. Bellegarda, Kevin A. Lenzo, Devang Naik:
Design and ccollection of a corpus of polyphones and prosodic contexts for speech synthesis research and development. EUROSPEECH 1999: 2707-2708 - 1997
- [c3]Devang Naik:
Using talker location to detect spurious utterances in desktop command and control. ICASSP 1997: 3265-3268 - 1996
- [c2]Jerome R. Bellegarda, John W. Butzberger, Yen-Lu Chow, Noah B. Coccaro, Devang Naik:
A novel word clustering algorithm based on latent semantic analysis. ICASSP 1996: 172-175 - 1995
- [c1]Devang Naik:
Pole-filtered cepstral mean subtraction. ICASSP 1995: 157-160
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-22 21:15 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: