Kartik Audhkhasi

According to our database, Kartik Audhkhasi authored at least 77 papers between 2007 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

STAB: Speech Tokenizer Assessment Benchmark.

Shikhar Vashishth, Harman Singh, Shikhar Bharadwaj, Sriram Ganapathy, Chulayuth Asawaroengchai, Kartik Audhkhasi, Andrew Rosenberg, Ankur Bapna, Bhuvana Ramabhadran

CoRR, 2024

Task Vector Algebra for ASR Models.

Gowtham Ramesh, Kartik Audhkhasi, Bhuvana Ramabhadran

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

O-1: Self-training with Oracle and 1-best Hypothesis.

Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Kartik Audhkhasi

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Robust Knowledge Distillation from RNN-T Models with Noisy Training Labels Using Full-Sum Loss.

Mohammad Zeineldeen, Kartik Audhkhasi, Murali Karthick Baskar, Bhuvana Ramabhadran

Proceedings of the IEEE International Conference on Acoustics, 2023

Large-Scale Language Model Rescoring on Long-Form Data.

Tongzhou Chen, Cyril Allauzen, Yinghui Huang, Daniel S. Park, David Rybach, W. Ronny Huang, Rodrigo Cabrera, Kartik Audhkhasi, Bhuvana Ramabhadran, Pedro J. Moreno, Michael Riley

Proceedings of the IEEE International Conference on Acoustics, 2023

Modular Conformer Training for Flexible End-to-End ASR.

Kartik Audhkhasi, Brian Farris, Bhuvana Ramabhadran, Pedro J. Moreno

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Modular Hybrid Autoregressive Transducer.

Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar, Yu Zhang, Gary Wang, Kartik Audhkhasi, Jesse Emond, Trevor Strohman, Bhuvana Ramabhadran, W. Ronny Huang, Ehsan Variani, Yinghui Huang, Pedro J. Moreno

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition.

Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran, Pedro J. Moreno

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Federated Learning for Affective Computing Tasks.

Krishna Somandepalli, Hang Qi, Brian Eoff, Alan Cowen, Kartik Audhkhasi, Josh Belanich, Brendan Jou

Proceedings of the 10th International Conference on Affective Computing and Intelligent Interaction, 2022

2021

Regularizing Word Segmentation by Creating Misspellings.

Hainan Xu, Kartik Audhkhasi, Yinghui Huang, Jesse Emond, Bhuvana Ramabhadran

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos.

Andrew Rouditchenko, Angie W. Boggust, David Harwath, Brian Chen, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Hilde Kuehne, Rameswar Panda, Rogério Schmidt Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James R. Glass

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Mixture Model Attention: Flexible Streaming and Non-Streaming Automatic Speech Recognition.

Kartik Audhkhasi, Tongzhou Chen, Bhuvana Ramabhadran, Pedro J. Moreno

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Convolutional Dropout and Wordpiece Augmentation for End-to-End Speech Recognition.

Hainan Xu, Yinghui Huang, Yun Zhu, Kartik Audhkhasi, Bhuvana Ramabhadran

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Noise can speed backpropagation learning and deep bidirectional pretraining.

Bart Kosko, Kartik Audhkhasi, Osonde Osoba

Neural Networks, 2020

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos.

Andrew Rouditchenko, Angie W. Boggust, David Harwath, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Rogério Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James R. Glass

CoRR, 2020

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300.

Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury

CoRR, 2020

Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art Results on Switchboard.

Zoltán Tüske, George Saon, Kartik Audhkhasi, Brian Kingsbury

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

End-to-End Spoken Language Understanding Without Full Transcripts.

Hong-Kwang Jeff Kuo, Zoltán Tüske, Samuel Thomas, Yinghui Huang, Kartik Audhkhasi, Brian Kingsbury, Gakuto Kurata, Zvi Kons, Ron Hoory, Luis A. Lastras

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Transliteration Based Data Augmentation for Training Multilingual ASR Acoustic Models in Low Resource Settings.

Samuel Thomas, Kartik Audhkhasi, Brian Kingsbury

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Alignment-Length Synchronous Decoding for RNN Transducer.

George Saon, Zoltán Tüske, Kartik Audhkhasi

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems.

Yinghui Huang, Hong-Kwang Kuo, Samuel Thomas, Zvi Kons, Kartik Audhkhasi, Brian Kingsbury, Ron Hoory, Michael Picheny

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Advancing Sequence-to-Sequence Based Speech Recognition.

Zoltán Tüske, Kartik Audhkhasi, George Saon

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Detection and Recovery of OOVs for Improved English Broadcast News Captioning.

Samuel Thomas, Kartik Audhkhasi, Zoltán Tüske, Yinghui Huang, Michael Picheny

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Challenging the Boundaries of Speech Recognition: The MALACH Corpus.

Michael Picheny, Zoltán Tüske, Brian Kingsbury, Kartik Audhkhasi, Xiaodong Cui, George Saon

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Multi-Task CTC Training with Auxiliary Feature Reconstruction for End-to-End Speech Recognition.

Gakuto Kurata, Kartik Audhkhasi

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation.

Gakuto Kurata, Kartik Audhkhasi

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic Speech Recognition.

Kartik Audhkhasi, George Saon, Zoltán Tüske, Brian Kingsbury, Michael Picheny

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Acoustically Grounded Word Embeddings for Improved Acoustics-to-word Speech Recognition.

Shane Settle, Kartik Audhkhasi, Karen Livescu, Michael Picheny

Proceedings of the IEEE International Conference on Acoustics, 2019

Sequence Noise Injected Training for End-to-end Speech Recognition.

George Saon, Zoltán Tüske, Kartik Audhkhasi, Brian Kingsbury

Proceedings of the IEEE International Conference on Acoustics, 2019

Grounding Spoken Words in Unlabeled Video.

Angie W. Boggust, Kartik Audhkhasi, Dhiraj Joshi, David Harwath, Samuel Thomas, Rogério Schmidt Feris, Danny Gutfreund, Yang Zhang, Antonio Torralba, Michael Picheny, James R. Glass

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019

Simplified LSTMS for Speech Recognition.

George Saon, Zoltán Tüske, Kartik Audhkhasi, Brian Kingsbury, Michael Picheny, Samuel Thomas

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Modeling Multiple Time Series Annotations as Noisy Distortions of the Ground Truth: An Expectation-Maximization Approach.

Rahul Gupta, Kartik Audhkhasi, Zach Jacokes, Agata Rozga, Shrikanth S. Narayanan

IEEE Trans. Affect. Comput., 2018

Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition.

Gakuto Kurata, Kartik Audhkhasi

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition.

Xuesong Yang, Kartik Audhkhasi, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Mark Hasegawa-Johnson

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Whole Sentence Neural Language Models.

Yinghui Huang, Abhinav Sethy, Kartik Audhkhasi, Bhuvana Ramabhadran

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition.

Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Michael Picheny

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

End-to-End ASR-Free Keyword Search From Speech.

Kartik Audhkhasi, Andrew Rosenberg, Abhinav Sethy, Bhuvana Ramabhadran, Brian Kingsbury

IEEE J. Sel. Top. Signal Process., 2017

Recent progress in deep end-to-end models for spoken language processing.

Kartik Audhkhasi, Andrew Rosenberg, George Saon, Abhinav Sethy, Bhuvana Ramabhadran, Stanley F. Chen, Michael Picheny

IBM J. Res. Dev., 2017

English Conversational Telephone Speech Recognition by Humans and Machines.

George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Direct Acoustics-to-Word Models for English Conversational Speech Recognition.

Kartik Audhkhasi, Bhuvana Ramabhadran, George Saon, Michael Picheny, David Nahamoo

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

End-to-end speech recognition and keyword search on low-resource languages.

Andrew Rosenberg, Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Michael Picheny

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Knowledge distillation across ensembles of multilingual models for low-resource languages.

Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Tom Sercu, Kartik Audhkhasi, Abhinav Sethy, Markus Nußbaum-Thom, Andrew Rosenberg

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Noise-enhanced convolutional neural networks.

Kartik Audhkhasi, Osonde Osoba, Bart Kosko

Neural Networks, 2016

Detecting paralinguistic events in audio stream using context in features and probabilistic decisions.

Rahul Gupta, Kartik Audhkhasi, Sungbok Lee, Shrikanth S. Narayanan

Comput. Speech Lang., 2016

Invariant Representations for Noisy Speech Recognition.

Dmitriy Serdyuk, Kartik Audhkhasi, Philemon Brakel, Bhuvana Ramabhadran, Samuel Thomas, Yoshua Bengio

CoRR, 2016

Multilingual Data Selection for Low Resource Speech Recognition.

Samuel Thomas, Kartik Audhkhasi, Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Efficient one-vs-one kernel ridge regression for speech recognition.

Jie Chen, Lingfei Wu, Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Semantic word embedding neural network language models for automatic speech recognition.

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Diverse Embedding Neural Network Language Models.

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran

Proceedings of the 3rd International Conference on Learning Representations, 2015

A mixture of experts approach towards intelligibility classification of pathological speech.

Rahul Gupta, Kartik Audhkhasi, Shrikanth S. Narayanan

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Multilingual representations for low resource speech recognition and keyword search.

Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, Abhinav Sethy, Kartik Audhkhasi, Xiaodong Cui, Ellen Kislal, Lidia Mangu, Markus Nußbaum-Thom, Michael Picheny, Zoltán Tüske, Pavel Golik, Ralf Schlüter, Hermann Ney, Mark J. F. Gales, Kate M. Knill, Anton Ragni, Haipeng Wang, Philip C. Woodland

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014

Theoretical Analysis of Diversity in an Ensemble of Automatic Speech Recognition Systems.

Kartik Audhkhasi, Andreas M. Zavou, Panayiotis G. Georgiou, Shrikanth S. Narayanan

IEEE ACM Trans. Audio Speech Lang. Process., 2014

Training ensemble of diverse classifiers on feature subsets.

Rahul Gupta, Kartik Audhkhasi, Shrikanth S. Narayanan

Proceedings of the IEEE International Conference on Acoustics, 2014

Semi-supervised term-weighted value rescoring for keyword search.

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan

Proceedings of the IEEE International Conference on Acoustics, 2014

Fusion of diverse denoising systems for robust automatic speech recognition.

Naveen Kumar, Maarten Van Segbroeck, Kartik Audhkhasi, Peter Drotár, Shrikanth S. Narayanan

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

A Globally-Variant Locally-Constant Model for Fusion of Labels from Multiple Diverse Experts without Using Reference Labels.

Kartik Audhkhasi, Shrikanth S. Narayanan

IEEE Trans. Pattern Anal. Mach. Intell., 2013

Generalized Ambiguity Decomposition for Understanding Ensemble Diversity.

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan

CoRR, 2013

Which ASR should I choose for my dialogue system?

Fabrizio Morbini, Kartik Audhkhasi, Kenji Sagae, Ron Artstein, Dogan Can, Panayiotis G. Georgiou, Shrikanth S. Narayanan, Anton Leuski, David R. Traum

Proceedings of the SIGDIAL 2013 Conference, 2013

Paralinguistic event detection from speech using probabilistic time-series smoothing and masking.

Rahul Gupta, Kartik Audhkhasi, Sungbok Lee, Shrikanth S. Narayanan

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Classifying language-related developmental disorders from speech cues: the promise and the potential confounds.

Daniel Bone, Theodora Chaspari, Kartik Audhkhasi, James Gibson, Andreas Tsiartas, Maarten Van Segbroeck, Ming Li, Sungbok Lee, Shrikanth S. Narayanan

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Empirical link between hypothesis diversity and fusion performance in an ensemble of automatic speech recognition systems.

Kartik Audhkhasi, Andreas M. Zavou, Panayiotis G. Georgiou, Shrikanth S. Narayanan

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Noisy hidden Markov models for speech recognition.

Kartik Audhkhasi, Osonde Osoba, Bart Kosko

Proceedings of the 2013 International Joint Conference on Neural Networks, 2013

Noise benefits in backpropagation and deep bidirectional pre-training.

Kartik Audhkhasi, Osonde Osoba, Bart Kosko

Proceedings of the 2013 International Joint Conference on Neural Networks, 2013

Joint training of interpolated exponential n-gram models.

Abhinav Sethy, Stanley F. Chen, Ebru Arisoy, Bhuvana Ramabhadran, Kartik Audhkhasi, Shrikanth S. Narayanan, Paul Vozila

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

2012

A reranking approach for recognition and classification of speech input in conversational dialogue systems.

Fabrizio Morbini, Kartik Audhkhasi, Ron Artstein, Maarten Van Segbroeck, Kenji Sagae, Panayiotis G. Georgiou, David R. Traum, Shrikanth S. Narayanan

Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

Speaker Personality Classification Using Systems Based on Acoustic-Lexical Cues and an Optimal Tree-Structured Bayesian Network.

Kartik Audhkhasi, Angeliki Metallinou, Ming Li, Shrikanth S. Narayanan

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Creating ensemble of diverse maximum entropy models.

Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Analyzing quality of crowd-sourced speech transcriptions of noisy audio for acoustic model adaptation.

Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Reliability-Weighted Acoustic Model Adaptation Using Crowd Sourced Transcriptions.

Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Emotion classification from speech using evaluator reliability-weighted combination of ranked lists.

Kartik Audhkhasi, Shrikanth S. Narayanan

Proceedings of the IEEE International Conference on Acoustics, 2011

Accurate transcription of broadcast news speech using multiple noisy transcribers and unsupervised reliability metrics.

Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

Automatic speech recognition system channel modeling.

Qun Feng Tan, Kartik Audhkhasi, Panayiotis G. Georgiou, Emil Ettelaie, Shrikanth S. Narayanan

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Data-dependent evaluator modeling and its application to emotional valence classification from speech.

Kartik Audhkhasi, Shrikanth S. Narayanan

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

2009

Automatic evaluation of spoken english fluency.

Om Deshmukh, Kundan Kandhway, Ashish Verma, Kartik Audhkhasi

Proceedings of the IEEE International Conference on Acoustics, 2009

Formant-based technique for automatic filled-pause detection in spontaneous spoken english.

Kartik Audhkhasi, Kundan Kandhway, Om Deshmukh, Ashish Verma

Proceedings of the IEEE International Conference on Acoustics, 2009

Lattice-based lexical cues for word fragment detection in conversational speech.

Kartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan

Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 2009

2007

Keyword Search using Modified Minimum Edit Distance Measure.

Kartik Audhkhasi, Ashish Verma

Proceedings of the IEEE International Conference on Acoustics, 2007