Monisankha Pal

Present Designation:

R&D Staff Engineer, Infineon Technologies AG, Irvine, California | R&D Consultant, TCS Research - Mumbai, India | Post-doctoral Research Associate, University of Southern California (USC) Viterbi, ECE , Signal Analysis and Interpretation Laboratory (SAIL), USA.

B.Tech, M. E., Ph. D., Postdoc.

Phone: (+1)9495919225, (+91)7501774160

Email: monisankha.pal@gmail.com, monisankha86.pal@gmail.com

Research Interests: 

Speech Signal Processing, Machine Learning, Deep Learning, Speaker Diarization, Speaker Recognition, Speech Enhancement, Spoken Language Understanding, Voice Spoofing and Anti-spoofing, Adversarial Attack and Defense in Deep Speaker Recognition, Voice Conversion, Speech Fluency.

Education:

Ph. D. in speech signal processing from the Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur, India (2018)

• Thesis title: Voice Conversion, Its Impact on Voice Biometrics, and Development of Countermeasure.

M. E. in Communication Engineering from the Department of Electronics & Telecommunication Engineering, Jadavpur University, India (2011)

B. Tech in Electronics and Communication Engineering from Institute of Engineering & Management, West Bengal University of Technology, India (2008)

Publications:

Refereed Journal Publications:

1. Pal, M., Kumar, M., Peri, R., Park, T. J., Kim, S. H., Lord, C., Bishop, S., Narayanan, S.,  "Meta-learning with latent space clustering in generative adversarial network for speaker diarization." IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1204-1219, 2021. (Impact Factor: 3.398) [Cited by 9]

2. Jati, A., Hsu, C. C., Pal, M., Peri, R., AbdAlmageed, W., Narayanan, S., "Adversarial attack and defense strategies for deep speaker recognition systems." Computer Speech & Language, 68, 101199, 1-14, 2021. (Impact Factor: 2.116) [Cited by 15]

3. Kumar, K., Paul, D., Pal, M., Sahidullah, M., Saha, G., "Speech Frame Selection for Spoofing Detection with an Application to Partially Spoofed Audio-Data." International Journal of Speech Technology, Springer, 24, 193-203, 2021. (Impact Factor: 1.220) [Cited by 3]

4. Pal, M., Paul, D., Saha, G., "Synthetic speech detection using fundamental frequency variation and spectral features." Computer Speech & Language, 48, 31-50, 2018. (Impact Factor: 2.116) [Cited by 28]

5. Pal, M., and Saha, G., "Spectral Mapping Using Prior Re-estimation of i-vectors And System Fusion for Voice Conversion." IEEE/ACM Transactions on Audio, Speech, and Language Processing, 25(11), 2071-2084, 2017. (Impact Factor: 3.398) [Cited by 4]

6. Paul, D., Pal, M., Saha, G., "Spectral Features for Synthetic Speech Detection." IEEE Journal of Selected Topics in Signal Processing, 11:605-617, 2017. (Impact Factor: 4.981) [Cited by 47]

7.  Pal, M., and Saha, G., "On robustness of speech based biometric systems against voice conversion attack." Applied Soft Computing, 30:214-228, 2015. (Impact Factor: 5.472) [Cited by 31]

Refereed Conference Publications:

1. Pal, M., Raikar, A., Panda, A., Kopparapu, K. S., "Synthetic speech detection using meta-learning with prototypical loss." arXiv preprint arXiv:2201.09470 (2022).

2.  Pal, M., Jati, A., Peri, R., Hsu, C. C., AbdAlmageed, W., Narayanan, S., "Adversarial defense for deep speaker recognition using hybrid adversarial training."Proc. IEEE, ICASSP, Toronto, Canada, 6164-6168, 2021. [Cited by 6]

3. Pal, M., Kumar, M., Peri, R., Park, T. J., Kim, S. H., Lord, C., Bishop, S., Narayanan, S., "Speaker Diarization using Latent Space Clustering in Generative Adversarial Network." Proc. IEEE, ICASSP, Barcelona, Spain, 6504-6508, 2020. [Cited by 13]

4.  Peri, R., Pal, M., Jati, A., Somandepalli, K., Narayanan, S., "Robust Speaker Recognition using Unsupervised Adversarial Invariance" Proc. IEEE, ICASSP, Barcelona, Spain, 6614-6618, 2020. [Cited by 14]

5. Park, T. J., Kumar, M., Flemotomos, N., Pal, M., Peri, R., Lahiri, R., Georgiou, P., Narayanan, S., "The Second DIHARD challenge: System Description for USC-SAIL Team." Proc. Interspeech, Austria, 998-1002, 2019. [Cited by 8]

6. Jati, A., Peri, R., Pal, M., Park, T. J., Kumar, N., Travadi, R., Georgiou, P., Narayanan, S., "Multi-task Discriminative Training of Hybrid DNN-TVM Model for Speaker Verification with Noisy and Far-Field Speech." Proc. Interspeech, Austria, 2463-2467, 2019. [Cited by 9]

7.  Pal, M., Kumar, M., Peri, R., Narayanan, S., "A study of semi-supervised speaker diarization system using GAN mixture model." arXiv preprint arXiv:1910.11416, 2019. [Cited by 3]

8. Pal, M., Paul, D., Sahidullah, M., Saha, G., "Robustness of Voice Conversion Techniques Under Mismatched Conditions." arXiv preprint arXiv:1612.07523, 2016. [Cited by 2]

9. Paul, D., Pal, M., Saha, G., "Novel Speech Features for Improved Detection of Spoofing Attacks." Proceedings of IEEE India Conference (INDICON), at New Delhi, 2015. [Cited by 15]

10. Pal, M., and Chattopadhyay, S., "A novel orthogonal minimum cross-correlation spreading code in CDMA system." Proceedings of IEEE International Conference on Emerging Trends in Robotics and Communication Technologies (INTERACT), 80-84, 2010. [Cited by 23]

Conferences to be communicated:

1. Pal, M., Raikar, A., Panda, A., Kopparapu, K. S., "Synthetic speech detection using meta-learning with prototypical loss". To be communicated.

Patent filed:

1. Saha, G., Paul, D., Pal, M., "System and method for automatic synthetic speech detection for speech based biometric authentication." Status: Filed (Ref : 1241/KOL/2015 dated December 3, 2015).

Others (Unsubmitted draft):

1. Pal, M., Paul, D., Sahidullah, M., Saha, G., "Robustness of Voice Conversion Techniques Under Mismatched Conditions." arXiv preprint arXiv:1612.07523, 2016.

Professional Activities:

Reviewer for:

Computer Speech & Language (Elsevier), Interspeech, ICASSP.

Society Membership:

IEEE (Student Member: 2010-2011)

IEEE Signal Processing Society (2010-2011)

International Speech Communication Association (ISCA) (2020-2021).

Skills:

Tools: Kaldi, Scikit-learn, Librosa, PyTorch, Tensorflow, Keras, VOICEBOX, MSR Identity Toolbox, HSM, STRAIGHT, Audacity, Wavesurfer, Praat.

Programming: C, Python, Bash Scripting, MATLAB.

Languages: English, Bengali and Hindi