Hemant Kumar Kathania

52 papers A 3Misc 3Journal 28Unranked 18
YearRankTypeTitle / Venue / Authors
2026 J jnl
A study on the layer-wise transferability of self-supervised learning features for children's speech processing tasks.
Speech Commun.
Abhijit Sinha, Hemant Kumar Kathania, Mikko Kurimo
2026 — conf
Autoencoder Based Optimized SSL Representations: Complexity Minimization and Improved Dysarthric ASR.
NCC
Paban Sapkota, Hemant Kumar Kathania, Mikko Kurimo, Shrikanth Narayanan, Sudarsana Reddy Kadiri
2026 J jnl
Fusion of Data Augmentation for Improved Dysarthria Severity Classification.
J. Signal Process. Syst.
Paban Sapkota, Bhanuja Karumuru, Hemant Kumar Kathania, Sudarsana Reddy Kadiri
2026 J jnl
Role of SSL models: Finetuning and feature optimization for dysarthric speech recognition and keyword spotting.
Comput. Electr. Eng.
Paban Sapkota, Hemant Kumar Kathania, Subham Kutum
2025 A conf
Beyond Traditional Speech Modifications : Utilizing Self Supervised Features for Enhanced Zero-Shot Children ASR.
INTERSPEECH
Abhijit Sinha, Hemant Kumar Kathania, Mikko Kurimo
2025 — conf
Bridging the Gap in Children's Speech Recognition: Zero-Speech Approaches with Speech Modifications and ASR Architectures.
EUSIPCO
Abhijit Sinha, Mittul Singh, Sudarsana Reddy Kadiri, Hemant Kumar Kathania, Mikko Kurimo
2025 J jnl
Can Layer-Wise SSL Features Improve Zero-Shot ASR Performance for Children's Speech?
IEEE Signal Process. Lett.
Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Shrikanth Narayanan
2025 J jnl
Can Layer-wise SSL Features Improve Zero-Shot ASR Performance for Children's Speech?
CoRR
Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Shrikanth Narayanan
2025 J jnl
Do all features matter? Layer-wise feature probing of self-supervised speech models for dysarthria severity classification.
Speech Commun.
Paban Sapkota, Harsh Srivastava, Hemant Kumar Kathania, Shrikanth Narayanan, Sudarsana Reddy Kadiri
2025 J jnl
Empowering dysarthric communication: a self-supervised approach to keyword spotting.
Signal Image Video Process.
Subham Kutum, Paban Sapkota, Abhijit Sinha, Hemant Kumar Kathania, Mahesh Chandra Govil
2025 J jnl
Enhancing Speaker-Independent Dysarthric Speech Severity Classification with DSSCNet and Cross-Corpus Adaptation.
CoRR
Arnab Kumar Roy, Hemant Kumar Kathania, Paban Sapkota
2025 — conf
Enhancing Traditional Kaldi Dysarthric Speech Recognition Using SSL-Features.
NCC
Paban Sapkota, Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri
2025 J jnl
Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech.
CoRR
Abhijit Sinha, Harishankar Kumar, Mohit Joshi, Hemant Kumar Kathania, Shrikanth Narayanan, Sudarsana Reddy Kadiri
2025 J jnl
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition.
IEEE Signal Process. Lett.
Arnab Kumar Roy, Hemant Kumar Kathania, Adhitiya Sharma, Abhishek Dey, Md. Sarfaraj Alam Ansari
2025 J jnl
Zero-Shot KWS for Children's Speech using Layer-Wise Features from SSL Models.
CoRR
Subham Kutum, Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Mahesh Chandra Govil
2025 J jnl
Zero-shot KWS for children's speech using layer-wise features from SSL models.
Pattern Recognit. Lett.
Subham Kutum, Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Mahesh Chandra Govil
2024 — conf
Effect of Speech Modification on Wav2Vec2 Models for Children Speech Recognition.
SPCOM
Abhijit Sinha, Mittul Singh, Sudarsana Reddy Kadiri, Mikko Kurimo, Hemant Kumar Kathania
2024 J jnl
Improvement in Facial Emotion Recognition using Synthetic Data Generated by Diffusion Model.
CoRR
Arnab Kumar Roy, Hemant Kumar Kathania, Adhitiya Sharma
2024 — conf
Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation.
IEEECONF
Paban Sapkota, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Shrikanth Narayanan
2024 — conf
In-Domain Data Augmentation to Enhance Severity Level Classification of Dysarthria from Speech.
SPCOM
Bhanuja Karumuru, Paban Sapkota, Hemant Kumar Kathania
2024 J jnl
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition.
CoRR
Arnab Kumar Roy, Hemant Kumar Kathania, Adhitiya Sharma, Abhishek Dey, Md. Sarfaraj Alam Ansari
2024 — conf
Role of Acoustics and Prosodic Features for Children's Age Classification.
SPCOM
Vishakha Kumari, Abhijit Sinha, Hemant Kumar Kathania
2024 J jnl
Spectral warping based data augmentation for low resource children's speaker verification.
Multim. Tools Appl.
Hemant Kumar Kathania, Virender Kadyan, Sudarsana Reddy Kadiri, Mikko Kurimo
2024 — conf
Systematic Study of Dysarthric Speech Recognition: Spectral Features and Acoustic Models.
IEEECONF
Paban Sapkota, Hemant Kumar Kathania, Mikko Kurimo, Sudarsana Reddy Kadiri, Shrikanth Narayanan
2023 — conf
Effect of Linear Prediction Order to Modify Formant Locations for Children Speech Recognition.
SPECOM (1)
Udara Laxman Kumar, Mikko Kurimo, Hemant Kumar Kathania
2023 — conf
Gammatone-Filterbank Based Pitch-Normalized Cepstral Coefficients for Zero-Resource Children's ASR.
SPECOM (1)
Syed Shahnawazuddin, Ankita, Avinash Kumar, Hemant Kumar Kathania
2022 J jnl
A formant modification method for improved ASR of children's speech.
Speech Commun.
Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Paavo Alku, Mikko Kurimo
2022 J jnl
Data Augmentation Using Spectral Warping for Low Resource Children ASR.
J. Signal Process. Syst.
Hemant Kumar Kathania, Virender Kadyan, Sudarsana Reddy Kadiri, Mikko Kurimo
2022 J jnl
End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks.
CoRR
Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri, Hemant Kumar Kathania, Mikko Kurimo
2021 — conf
Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces.
NoDaLiDa
Tuomas Kaseva, Hemant Kumar Kathania, Aku Rouhe, Mikko Kurimo
2021 — conf
Spectral modification for recognition of children's speech undermismatched conditions.
NoDaLiDa
Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Paavo Alku, Mikko Kurimo
2021 — conf
Synthesis Speech Based Data Augmentation for Low Resource Children ASR.
SPECOM
Virender Kadyan, Hemant Kumar Kathania, Prajjval Govil, Mikko Kurimo
2021 Misc conf
Vowel Non-Vowel Based Spectral Warping and Time Scale Modification for Improvement in Children's ASR.
ICASSP
Hemant Kumar Kathania, Avinash Kumar, Mikko Kurimo
2020 J jnl
Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge.
CoRR
Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri, Hemant Kumar Kathania, Mikko Kurimo
2020 J jnl
Creating speaker independent ASR system through prosody modification based data augmentation.
Pattern Recognit. Lett.
S. Shahnawazuddin, Nagaraj Adiga, Hemant Kumar Kathania, B. Tarun Sai
2020 A conf
Data Augmentation Using Prosody and False Starts to Recognize Non-Native Children's Speech.
INTERSPEECH
Hemant Kumar Kathania, Mittul Singh, Tamás Grósz, Mikko Kurimo
2020 J jnl
Data augmentation using prosody and false starts to recognize non-native children's speech.
CoRR
Hemant Kumar Kathania, Mittul Singh, Tamás Grósz, Mikko Kurimo
2020 Misc conf
Study of Formant Modification for Children ASR.
ICASSP
Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Paavo Alku, Mikko Kurimo
2019 J jnl
Developing speaker independent ASR system using limited data through prosody modification based on fuzzy classification of spectral bins.
Digit. Signal Process.
S. Shahnawazuddin, Nagaraj Adiga, B. Tarun Sai, Waquar Ahmad, Hemant Kumar Kathania
2019 — conf
On the Role of Linear, Mel and Inverse-Mel Filterbank in the Context of Automatic Speech Recognition.
NCC
Hemant Kumar Kathania, Syed Shahnawazuddin, Waquar Ahmad, Nagaraj Adiga
2019 J jnl
Role of Linear, Mel and Inverse-Mel Filterbanks in Automatic Recognition of Speech from High-Pitched Speakers.
Circuits Syst. Signal Process.
Hemant Kumar Kathania, S. Shahnawazuddin, Waquar Ahmad, Nagaraj Adiga
2019 — conf
Speaking-Rate Adaptation of Automatic Speech Recognition System through Fuzzy Classification based Time-Scale Modification.
NCC
S. Shahnawazuddin, Waquar Ahmad, Hemant Kumar Kathania, Nagaraj Adiga, B. Tarun Sai
2018 J jnl
An Experimental Study on the Significance of Variable Frame-Length and Overlap in the Context of Children's Speech Recognition.
Circuits Syst. Signal Process.
S. Shahnawazuddin, Chaman Singh, Hemant Kumar Kathania, Waquar Ahmad, Gayadhar Pradhan
2018 J jnl
Explicit Pitch Mapping for Improved Children's Speech Recognition.
Circuits Syst. Signal Process.
Hemant Kumar Kathania, Waquar Ahmad, Syed Shahnawazuddin, Arun B. Samaddar
2018 — conf
Exploring the Role of Speaking-Rate Adaptation on Children's Speech Recognition.
SPCOM
S. Shahnawazuddin, Hemant Kumar Kathania, Chaman Singh, Waquar Ahmad, Gayadhar Pradhan
2018 — conf
Improving Children's Speech Recognition Through Time Scale Modification Based Speaking Rate Adaptation.
SPCOM
Hemant Kumar Kathania, S. Shahnawazuddin, Waquar Ahmad, Nagaraj Adiga, Sanjay Kumar Jana, Arun B. Samaddar
2018 J jnl
Improving children's mismatched ASR using structured low-rank feature projection.
Speech Commun.
Syed Shahnawazuddin, Hemant Kumar Kathania, Abhishek Dey, Rohit Sinha
2018 Misc conf
Role of Prosodic Features on Children's Speech Recognition.
ICASSP
Hemant Kumar Kathania, Syed Shahnawazuddin, Nagaraj Adiga, Waquar Ahmad
2018 J jnl
Studying the role of pitch-adaptive spectral estimation and speaking-rate normalization in automatic speech recognition.
Digit. Signal Process.
Syed Shahnawazuddin, Nagaraj Adiga, Hemant Kumar Kathania, Gayadhar Pradhan, Rohit Sinha
2017 J jnl
Effect of Prosody Modification on Children's ASR.
IEEE Signal Process. Lett.
Syed Shahnawazuddin, Nagaraj Adiga, Hemant Kumar Kathania
2017 A conf
Improving Children's Speech Recognition Through Explicit Pitch Scaling Based on Iterative Spectrogram Inversion.
INTERSPEECH
Waquar Ahmad, Syed Shahnawazuddin, Hemant Kumar Kathania, Gayadhar Pradhan, Arun B. Samaddar
2017 — conf
Improving children speech recognition in acoustically mismatched condition using eigenvoices and feature projections.
NCC
Hemant Kumar Kathania, Syed Shahnawazuddin, Rohit Sinha