Arindam Ghosh

Arindam Ghosh

Machine Learning for Speech & NLU @3M/Solventum Health

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

publications

Throughput and energy efficiency of a cooperative hybrid ARQ protocol for underwater acoustic sensor networks

Published in Sensors (MDPI), 2013

In this paper, we propose and analyze a retransmission protocol named Cooperative-Hybrid Automatic Repeat reQuest (C-HARQ) for underwater acoustic sensor networks, which exploits both the reliability of cooperative ARQ (CARQ) and the efficiency of incremental redundancy-hybrid ARQ (IR-HARQ) using rate-compatible punctured convolution (RCPC) codes.

Recommended citation: Ghosh, Arindam, Jae-Won Lee, and Ho-Shin Cho. "Throughput and energy efficiency of a cooperative hybrid ARQ protocol for underwater acoustic sensor networks." Sensors 13.11 (2013): 15385-15408.
Download Paper

SEP of dual-ring star-QAM over FSO channels with atmospheric turbulence

Published in International Conference on Signal Processing and Communications (SPCOM), 2014

In this paper, accurate and analytically tractable symbol-error probability (SEP) expressions have been derived for a free-space optics (FSO) communication system that employs M-ary dual-ring star-quadrature amplitude modulation (QAM) and operates over atmospheric turbulent channels.

Recommended citation: Ghosh, Arindam, Gourab Ghatak, and Aniruddha Chandra. "SEP of dual-ring star-QAM over FSO channels with atmospheric turbulence." 2014 International Conference on Signal Processing and Communications (SPCOM). IEEE, 2014.
Download Paper

Mixture-based modeling of spatially correlated interference in a Poisson field of interferers

Published in IEEE Communications Letters, 2017

In this paper, we present an approach to model the correlated interferences in Poisson Point Process (PPP) network using a correlation framework constructed using mixtures of random variables.

Recommended citation: Ghosh, Arindam. "Mixture-based modeling of spatially correlated interference in a Poisson field of interferers." IEEE Communications Letters 21.11 (2017): 2496-2499
Download Paper

Performance analysis of MRC under spatially correlated interference using mixture-based method

Published in IEEE Communications Letters, 2018

In this paper, we analytically derive the MRC outage probability for an arbitrary N by employing the mixture-based method of modeling the correlation in the interference powers.

Recommended citation: Ghosh, Arindam, and Harpreet S. Dhillon. "Performance analysis of MRC under spatially correlated interference using mixture-based method." IEEE Communications Letters 22.11 (2018): 2314-2317
Download Paper

Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations

Published in EMNLP, 2021

In this paper, we explore the feasibility of using pretrained transformer models (BART) for summarizing doctor-patient conversations directly from transcripts.

Recommended citation: Zhang, Longxiang, Renato Negrinho, Arindam Ghosh, Vasudevan Jagannathan, Hamid Reza Hassanzadeh, Thomas Schaaf, and Matthew R. Gormley. "Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations." In Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 3693-3712. 2021.
Download Paper

Low-resource Low-footprint Wake-word Detection using Knowledge Distillation

Published in Interspeech, 2022

This paper explores two techniques to leverage acoustic modeling data for large-vocabulary speech recognition to improve a purpose-built wake-word detector: transfer learning and knowledge distillation.

Recommended citation: Ghosh, A., Fuhs, M., Bagchi, D., Farahani, B., Woszczyna, M. (2022) Low-resource Low-footprint Wake-word Detection using Knowledge Distillation. Proc. Interspeech 2022, 3739-3743, doi: 10.21437/Interspeech.2022-529.
Download Paper

Adafocal: Calibration-aware adaptive focal loss

Published in Advances in Neural Information Processing Systems 35, 2022

This paper proposes Adafocal training algorithm that produces better calibrated models without any significant loss in accuracy/performance.

Recommended citation: Ghosh, Arindam, Thomas Schaaf, and Matthew Gormley. “Adafocal: Calibration-aware adaptive focal loss.” Advances in Neural Information Processing Systems 35 (2022): 1583-1595.
Download Paper

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.