Skip To Main Content
Debmalya Chakrabarty on Muck Rack

Debmalya Chakrabarty

As seen in: Amazon Science
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile

Get in touch with Debmalya

Contact Debmalya, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Is this you?

As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile

Articles

AMuSE: Attentive multilingual speech encoding for zero-prior ASR

|
By Ashutosh Varshney, Debmalya Chakrabarty, Harish Arsikere, Akshat Jaiswal
| Amazon Science
Multilingual ASR offers training, deployment and overall performance benefits, but models trained via simple data pooling are known to suffer from cross-lingual interference. Oracle language information (exact-prior) and language-specific parameters are usually leveraged to overcome this, but such approaches cannot enable seamless, truly multilingual experiences.
Open in Who Shared Issue with article?

Multi-modal pre-training for automated speech recognition

|
By David Chan, Shalini Ghosh, Debmalya Chakrabarty, Bjorn Hoffmeister, Björn Hoffmeister
| Amazon Science
Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to be vulnerable to both local-level corruption (such as audio-frame drops, or loud noises) and global-level noise (such as environmental noise, or background noise) that has not been seen during training.
Open in Who Shared View Duplicates (5) Issue with article?
See all 2 articles