Hari Krishna Vydana

According to our database, Hari Krishna Vydana authored at least 25 papers between 2015 and 2022.

Collaborative distances:

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

2022

Spelling-Aware Word-Based End-to-End ASR.

Ekaterina Egorova, Hari Krishna Vydana, Lukás Burget, Jan Honza Cernocký

IEEE Signal Process. Lett., 2022

2021

Detection of Fricative Landmarks Using Spectral Weighting: A Temporal Approach.

Hari Krishna Vydana, Anil Kumar Vuppala

Circuits Syst. Signal Process., 2021

The IWSLT 2021 BUT Speech Translation Systems.

Hari Krishna Vydana, Martin Karafiát, Lukás Burget, Jan Cernocký

Proceedings of the 18th International Conference on Spoken Language Translation, 2021

Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System.

Ekaterina Egorova, Hari Krishna Vydana, Lukás Burget, Jan Cernocký

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

Jointly Trained Transformers Models for Spoken Language Translation.

Hari Krishna Vydana, Martin Karafiát, Katerina Zmolíková, Lukás Burget, Honza Cernocký

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

A Technical Report: BUT Speech Translation Systems.

Hari Krishna Vydana, Lukás Burget, Jan Cernocký

CoRR, 2020

BUT Opensat 2019 Speech Recognition System.

Martin Karafiát, Murali Karthick Baskar, Igor Szöke, Hari Krishna Vydana, Karel Veselý, Jan Honza Cernocký

CoRR, 2020

2019

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery.

Lucas Ondel, Hari Krishna Vydana, Lukás Burget, Jan Cernocký

Proceedings of the Interspeech 2019, 2019

Multi-Head Self-Attention Networks for Language Identification.

Ravi Kumar Vuddagiri, Tirusha Mandava, Hari Krishna Vydana, Anil Kumar Vuppala

Proceedings of the 2019 Twelfth International Conference on Contemporary Computing, 2019

An Investigation of LSTM-CTC based Joint Acoustic Model for Indian Language Identification.

Tirusha Mandava, Ravi Kumar Vuddagiri, Hari Krishna Vydana, Anil Kumar Vuppala

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

2018

Curriculum learning based approach for noise robust language identification using DNN with attention.

Ravi Kumar Vuddagiri, Hari Krishna Vydana, Anil Kumar Vuppala

Expert Syst. Appl., 2018

Improved Language Identification Using Stacked SDC Features and Residual Neural Network.

Ravi Kumar Vuddagiri, Hari Krishna Vydana, Anil Kumar Vuppala

Proceedings of the 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages, 2018

IIITH-ILSC Speech Database for Indain Language Identification.

Ravi Kumar Vuddagiri, Krishna Gurugubelli, Priyam Jain, Hari Krishna Vydana, Anil Kumar Vuppala

Proceedings of the 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages, 2018

Incorporating Speaker Normalizing Capabilities to an End-to-End Speech Recognition System.

Hari Krishna Vydana, Sivanand Achanta, Anil Kumar Vuppala

Proceedings of the 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages, 2018

An Exploration towards Joint Acoustic Modeling for Indian Languages: IIIT-H Submission for Low Resource Speech Recognition Challenge for Indian Languages, INTERSPEECH 2018.

Hari Krishna Vydana, Krishna Gurugubelli, Vishnu Vidyadhara Raju Vegesna, Anil Kumar Vuppala

Proceedings of the Interspeech 2018, 2018

2017

Investigative study of various activation functions for speech recognition.

Hari Krishna Vydana, Anil Kumar Vuppala

Proceedings of the Twenty-third National Conference on Communications, 2017

DNN-HMM Acoustic Modeling for Large Vocabulary Telugu Speech Recognition.

Vishnu Vidyadhara Raju Vegesna, Krishna Gurugubelli, Hari Krishna Vydana, Bhargav Pulugandla, Manish Shrivastava, Anil Kumar Vuppala

Proceedings of the Mining Intelligence and Knowledge Exploration, 2017

Significance of neural phonotactic models for large-scale spoken language identification.

Brij Mohan Lal Srivastava, Hari Krishna Vydana, Anil Kumar Vuppala, Manish Shrivastava

Proceedings of the 2017 International Joint Conference on Neural Networks, 2017

Residual neural networks for speech recognition.

Hari Krishna Vydana, Anil Kumar Vuppala

Proceedings of the 25th European Signal Processing Conference, 2017

Importance of non-uniform prosody modification for speech recognition in emotion conditions.

Vishnu Vidyadhara Raju Vegesna, Hari Krishna Vydana, Suryakanth V. Gangashetty, Anil Kumar Vuppala

Proceedings of the 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017

2016

Vowel-Based Non-uniform Prosody Modification for Emotion Conversion.

Hari Krishna Vydana, Sudarsana Reddy Kadiri, Anil Kumar Vuppala

Circuits Syst. Signal Process., 2016

A Study on Vowel Region Detection from a Continuous Speech.

Ramakrishna Thirumuru, Hari Krishna Vydana, Suryakanth V. Gangashetty, Anil Kumar Vuppala

Proceedings of the Mining Intelligence and Knowledge Exploration, 2016

2015

A language model based approach towards large scale and lightweight language identification systems.

Brij Mohan Lal Srivastava, Hari Krishna Vydana, Anil Kumar Vuppala, Manish Shrivastava

CoRR, 2015

Significance of Emotionally Significant Regions of Speech for Emotive to Neutral Conversion.

Hari Krishna Vydana, Vishnu Vidyadhara Raju Vegesna, Suryakanth V. Gangashetty, Anil Kumar Vuppala

Proceedings of the Mining Intelligence and Knowledge Exploration, 2015

Improved Language Identification in Presence of Speech Coding.

Ravi Kumar Vuddagiri, Hari Krishna Vydana, Jiteesh Varma Bhupathiraju, Suryakanth V. Gangashetty, Anil Kumar Vuppala

Proceedings of the Mining Intelligence and Knowledge Exploration, 2015