Vishala Pannala
Speech Researcher,
Hyderabad, India.
About me
I hold a PhD degree, in the department of Electronics and Communication Engineering (ECE), with specialization in speech processing, under the guidance of Prof. B.Yegnanarayana, from International Institute of Information Technology (IIIT), Hyderabad. During PhD, I worked on speech and speaker-specific tasks using signal processing methods and artificial neural network based approaches.
Before upgrading to PhD, I worked as a Research Assistant and was an MS Research Scholar at the same place. During this time, I worked on developing end-to-end spoken dialogue systems for Indian languages, specifically Telugu.
I hold a Bachelor of Technology (B.Tech) degree in the department of Electrical and Electronics Engineering (EEE) from Jawaharlal Nehru Technological University (JNTU), Hyderabad.
My research interests
My research interests include:
Speech based human-computer interactive (HCI) systems
Artificial neural networks
Speech recognition
Speech signal processing, Representation of speech information, Speech features extraction
Voice activity detection (VAD), Speech separation
Spoofed speech detection, Distant speech detection, Mimicry speech detection
Speaker diarization, Speaker separation, Speaker turn detection
Speaker recognition
Speaker verification
Privacy preservation
Keyword spotting
Similarities in speech patterns
Practical degradations and real world scenarios
Publications
PhD Thesis
Thesis title: "Application of single frequency filtering for speech and speaker-specific tasks". Click here for pdf
Journal papers
Radhika Bayya, Vishala Pannala, Sudhanshu Singh, Sriram Sundar, Krishna Prapoorna Biligiri, "Time-Frequency Analysis of Acoustic Signals from Tyre-Pavement Interaction", The Journal of the Acoustical Society of America, vol. 151, no. 1, pp. 370-386, 2022. DOI: 10.1121/10.0009269.
Vishala Pannala and B.Yegnanarayana, "A neural network approach for speech activity detection for Apollo corpus", Computer, Speech & Language, vol. 65, pp. 101137, 2021. DOI: 10.1016/j.csl.2020.101137.
Vishala Pannala, "Processing of speech signals for robust recognition in practical environments", CSI Transactions on ICT, Springer, vol. 5, no. 2, pp. 167-178, 2017. DOI: 10.1007/s40012-016-0153-5
Conference papers
B. Yegnanarayana, BHVS Narayana Murthy, JV Satyanarayana, Vishala Pannala, and Nivedita Chennupati, "Robustness and Accuracy of Time Delay Estimation in a Live Room", in Proceedings of National Conference on Communications (NCC), IEEE, pp. 1-6, July, 2021. DOI: 10.1109/ncc52529.2021.9530120.
B.Yegnanarayana, Anand Joseph and Vishala Pannala, "Enhancing formant information in spectrographic display of speech", in Proceedings of INTERSPEECH, pp. 165-169, 2020. DOI: 10.21437/Interspeech.2020-2653.
Vishala Pannala, G. Aneeja, Sudarsana Reddy Kadiri, and B.Yegnanarayana, "Robust Estimation of Fundamental Frequency using Single Frequency Filtering Approach", in Proceedings of INTERSPEECH, pp. 2155-2159, 2016. DOI: 10.21437/Interspeech.2016-1401
Sivanand Achanta, Nivedita Chennupati, Vishala Pannala, Mansi Rankawat, and Kishore Prahallad, "Voice Activity Detection using Temporal Characteristics of Autocorrelation Lag and Maximum Spectral Amplitude in Sub-bands", in Proceedings of the ICON, pp. 48-55, 2014. URI: https://aclanthology.org/W14-5107
Awards and achievements
During PhD, for the years 2015-2019, I was awarded with Visveswaraya PhD Fellowship for Electronics & IT, Ministry of Electronics and Information Technology (MEITy), Government of India (GoI).
Secured 3rd place in the ‘Fearless Steps Challenge Phase-01’ for the task of ‘Speech Activity Detection’, held during INTERSPEECH, 2019.
Presentations
Enhancing formant information in spectrographic display of speech, (Virtual) Interspeech, ISCA, Shanghai, China, October 2020.
Robust Estimation of Fundamental Frequency using Single Frequency Filtering Approach, Interspeech, ISCA, SanFrancisco, USA, September 2016.
Processing of speech signals for robust recognition in practical environments, Visvesvaraya PhD Scheme Paper Presentations, IIT Bombay, October 2016.
Processing of Speech Signals for Recognition in Practical Environments, Google Speech PhD Summit, Google Office, London, UK, June 2016.
Contact
My profiles:
LinkedIn profile: www.linkedin.com/in/vishala-pannala-5b609317
Institute profile: http://speech.iiit.ac.in/~vishala
ORCID profile: https://orcid.org/0000-0001-7997-9255
Scopus profile: https://www.scopus.com/authid/detail.uri?authorId=57191862102
Google Scholar: https://scholar.google.co.in/citations?user=x33u0HsAAAAJ&hl=en
DBLP profile: https://dblp.org/pid/194/1252.html
Email ids:
E-mail address: pannalavishala@gmail.com
Alternate mail: p.vishala@alumni.iiit.ac.in