Welcome

Dr. Bidisha Sharma received Ph.D. degree from Indian Institute of Technology (IIT) Guwahati in the year 2018 and Bachelor degree (Gold Medalist) in Electronics and Telecommunication Engineering from Gauhati University, Guwahati, India in the year 2012. Her Ph.D. work focused on improving the quality of synthesized speech obtained from a text-to-speech synthesis (TTS) system. Specifically, she uses acoustic-phonetic knowledge to perform post-filtering for synthesizing naturalistic speech from a TTS system. During her Ph.D., she also worked in speech enhancement, voice activity detection, and prosody modification. Dr. Bidisha was a lead team member in the project "Development of text-to-speech synthesis system in Assamese and Manipuri language" at IIT Guwahati. After completing Ph.D., initially, she worked as a Research Fellow in Sound and Music Computing (SMC) laboratory followed by Human Language Technology (HLT) laboratory at National University of Singapore till September 2021, where, she worked on projects related to Automatic Speech Recognition, and Spoken Language Understanding. During this period, Dr. Bidisha was involved in mentoring interns/masters/Ph.D. students. Dr. Bidisha is an active member of the organizing committee for IEEE ASRU 2019, SIGDIAL 2021, IWSDS 2021 and COCOSDA 2021 conferences. She was a co-chair of Young Female Researchers Mentoring (YFRM) at ASRU 2019 and Postdoctoral Mentor at Mentoring event, Interspeech 2019. Dr. Bidisha is a member of IEEE and ISCA. She is enthusiastic about active involvement in applied science and audio-related projects.

Highlights

  • November 2021: Local Chair, COCOSDA 2021, The 24th Conference of the Oriental COCOSDA, 18-20 November 2021, Singapore

  • November 2021: Co-chair, events, registration, IWSDS 2021, The 12th International Workshop on Spoken Dialog System Technology, 15-17 November 2021, Singapore

  • July 2021: Co-chair, events, registration, SIGDIAL 2021, The 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 29-31 July 2021, Singapore

  • December 2019: Co-chair, Young Female Researchers Mentoring (YFRM) at ASRU 2019, 15 December 2019, Singapore

  • December 2019: Registration Chair, IEEE Automatic Speech Recognition and Understanding Workshop, Singapore, 14-18 December 2019

  • September 2019: Postdoctotral Mentor, Mentoring event at Interspeech 2019, 17 September, 2019, Graz, Austria

News


Invited Talks


  • September 2020: TEQIP-III sponsored Short Term Training Program on “Emerging Trends in Speech & Biomedical Signal Processing”, Department of Electronics Engineering Sardar Vallabhbhai National Institute of Technology, Surat, Gujarat, India


  • July 2021: ATAL Online Faculty Development Programme (FDP), KLE Technological University,Vidya Nagar, Hubli, Karnataka 580031, India

Publications


Journals:


  1. Bidisha Sharma, Xiaoxue Gao, Karthika Vijayan, Xiaohai Tian, and Haizhou Li, “NHSS: A speech and singing parallel database”, Speech Communication, 133, July 2021, pp. 9-22. [pre-print post-print Database]


  1. Bidisha Sharma, and Ye Wang, “Automatic Evaluation of Song Intelligibility Using Singing Adapted STOI and Vocal-Specific Features.” IEEE/ACM Transactions on Audio, Speech, and Language Processing 28 (2019): 319-331 [pre-print post-print Code]


  1. Bidisha Sharma and S.R.M. Prasanna, “Sonority Measurement Using System, Source, and Suprasegmental Information,” in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 3, pp. 505-518, March 2017 [Pre-print Post-print Code]


  1. Bidisha Sharma and S.R.M. Prasanna, “Enhancement of Spectral Tilt in Synthesized Speech,” in IEEE Signal Processing Letters, vol. 24, no. 4, pp. 382-386, April 2017 [Post-print]


  1. Bidisha Sharma and S.R.M. Prasanna, “Significance of Sonority Information for Voiced/Unvoiced Decision in Speech Synthesis,” Speech Communication, vol. 99, pp.201-210, May, 2018 [Post-print]


  1. Bidisha Sharma and S.R.M. Prasanna, “Polyglot Speech Synthesis: A Review,” IETE Technical Review, vol. 34, no. 4, pp. 366-389, 2017 [Pre-print Post-print]


  1. Rohan Kumar Das, Bidisha Sharma and S.R.M. Prasanna, Significance of Duration Modification for Speaker Verification Under Mismatch Speech Tempo Condition, International Journal in Speech Technology, vol. 21, no. 3, pp.401-410, 2018 [Post-print Pre-print]


Conferences:


  1. Bidisha Sharma, Maulik Madhavi, Xuehao Zhou, and Haizhou Li, “Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification”, accepted in ASRU 2021.


  1. Xinyuan Qian, Bidisha Sharma, Amine El Abridi, Haizhou Li, “SLoClas : A Database for Joint Sound Localization and Classification”, accepted in Oriental COCOSDA 2021.


  1. Yidi Jiang, Bidisha Sharma, Maulik Madhavi, and Haizhou Li, “Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification”, accepted in Interspeech 2021 [Pre-print Code]


  1. Bidisha Sharma, Maulik Madhavi, and Haizhou Li, “Leveraging Acoustic and Linguistic Embeddings from Pre-trained Speech and Language Models for Intent Classification”, in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toronto, Ontario, Canada, June 2021 [Pre-print Post-print]


  1. Bidisha Sharma, R.K. Das, Haizhou Li, “On the Importance of Audio-Source Separation for Singer Identification in Polyphonic Music”, Proc. Interspeech 2019, 2020-2024, DOI:10.21437/Interspeech.2019-1925 [Post-print]


  1. Bidisha Sharma, Haizhou Li, “A Combination of Model-Based and Feature-Based Strategy for Speech-to-Singing Alignment”, Proc. Interspeech 2019, 624-628, DOI: 10.21437/Interspeech.2019-1942 [Post-print]


  1. Bidisha Sharma, R.K. Das, Haizhou Li, “Multi-Level Adaptive Speech Activity Detector for Speech in Naturalistic Environments”, Proc. Interspeech 2019, 2015-2019, DOI: 10.21437/Interspeech.2019-1928 [Post-print Code]


  1. Chitralekha Gupta, Karthika Vijayan, Bidisha Sharma, Haizhou Li, “NUS Speak-to-Sing: A Web Platform for Personalized Speech-to-Singing Conversion.” Proc. Interspeech 2019, pp 2376-2377 [Post-print Poster]


  1. Sheelvant, Rohan, Bidisha Sharma, Maulik Madhavi, Rohan Kumar Das, S. R. M. Prasanna, and Haizhou Li. “RSL2019: A Realistic Speech Localization Corpus”, Oriental COCOSDA 2019, Cebu, Philippines, pp. 1-6 [Pre-print Post-print Database]


  1. Bidisha Sharma , Chitralekha Gupta, Li Haizhou, Wang Ye, “Automatic Lyrics-to-Audio Alignment on Polyphonic Music Using Singing-Adapted Acoustic Models,” Accepted in ICASSP 2019, Brighton, UK, pp. 396-400 [Pre-print Post-print]


  1. Loitongbam Gyanendro Singh , Nagaraj Adiga, Bidisha Sharma, Sanasam Ranbir Singh, S.R.M. Prasanna, “Automatic Pause Marking for Speech Synthesis,” TENCON 2017, pp. 170-1794, Malaysia [Post-print]


  1. Bidisha Sharma “Scope of Sonority Information in Statistical Parametric Speech Synthesis,” 3rd Doctoral Consortium, INTERSPEECH 2017, Stockholm, Sweden [Post-print]


  1. Bidisha Sharma and S.R.M. Prasanna. “Vowel Onset Point Detection using Sonority Information,” in INTERSPEECH, 2017, pp. 444-448, Stockholm, Sweden [Post-print]


  1. Bidisha Sharma and S.R.M. Prasanna. “Pause Insertion in Assamese Synthesized Speech Using Speech Specific Features,” in Proc. NCC, 2017, pp. 1-6, IIT Madras, India [Post-print]


  1. Bidisha Sharma and S.R.M. Prasanna. “Speech Synthesis in Noisy Environment by Enhancing Strength of Excitation and Formant Prominence,” in Proc. INTERSPEECH 2016, pp.131-135, San Francisco, USA [Post-print]


  1. Deepshikha Mahanta , Bidisha Sharma, Priyankoo Sarmah and S.R.M. Prasanna, “Text to Speech Synthesis System in Indian English,” in Proc. TENCON, 2016, pp. 2614-2618, Singapore [Post-print]


  1. Bidisha Sharma, and S.R.M. Prasanna. “Improvement of Syllable based TTS System in Assamese using Prosody Modification,” in Proc. INDICON, 2015, pp. 1-6, Jamia Milia Islamia, New Delhi, India [Post-print]


  1. Bidisha Sharma, Nagaraj Adiga and S.R.M. Prasanna “Development of Assamese Text-to-Speech Synthesis System,” in Proc. TENCON, 2015, pp. 1-6, Macau, China [Post-print]


  1. Biswajit Dev Sarma , Bidisha Sharma , S. Ashwin Shanmugam , S.R.M. Prasanna and Hema A. Murthy, “Exploration of Vowel Onset and Offset Points for Hybrid Speech Segmentation,” in Proc. TENCON, 2015, pp. 1-6, Macau, China [Post-print]


  1. Bidisha Sharma and S.R.M. Prasanna, “Faster Prosody Modification using Time Scaling of Epochs,” in Proc. INDICON, 2014, pp. 1-5, Pune, India [Post-print]