Amber Nigam
I am a data science professional with a demonstrated history of building products at scale using machine learning and natural language processing and publishing research at top tier conferences.
In my entrepreneurial stint as co-founder and CTO at kydots.ai, I led a team of engineers and psychometric researchers to build a product in career progression domain using deep learning. In this process, we filed two patents and published a research paper on the algorithms we developed.
My research has been presented in machine learning conferences like NeurIPS, IEEE ICSE, IEEE CCIS, and Europhras and top journals like Lancet and Springer. I am also a co-author of one of the chapters in the book "Leveraging Data Science for Global Health" due for publication early next year. Besides, I have spoken on Artificial Intelligence in events like AI in Dentistry Conference by MIT, Dupont Technology Conference, and Webinar on AI by Udacity. I also recently led my team to be among the top-10 teams in MIT COVID-19 datathon where we developed a fact-checking engine for the misinformation on COVID-19.
In my entrepreneurial stint as co-founder and CTO at kydots.ai, I led a team of engineers and psychometric researchers to build a product in career progression domain using deep learning. In this process, we filed two patents and published a research paper on the algorithms we developed.
My research has been presented in machine learning conferences like NeurIPS, IEEE ICSE, IEEE CCIS, and Europhras and top journals like Lancet and Springer. I am also a co-author of one of the chapters in the book "Leveraging Data Science for Global Health" due for publication early next year. Besides, I have spoken on Artificial Intelligence in events like AI in Dentistry Conference by MIT, Dupont Technology Conference, and Webinar on AI by Udacity. I also recently led my team to be among the top-10 teams in MIT COVID-19 datathon where we developed a fact-checking engine for the misinformation on COVID-19.
less
Related Authors
Uploads
Papers by Amber Nigam
intonation based feature for scoring the English speech of non-
native English speakers in Indian context. For this, we created an
automated spoken English scoring engine to learn from the
manual evaluation of spoken English. This involved using an
existing Automatic Speech Recognition (ASR) engine to convert
the speech to text. Thereafter, macro features like accuracy,
fluency and prosodic features were used to build a scoring model.
In the process, we introduced SimIntonation, short for similarity
between spoken intonation pattern and “ideal” i.e. training
intonation pattern. Our results show that it is a highly predictive
feature under controlled environment. We also categorized inter-
word pauses into 4 distinct types for a granular evaluation of
pauses and their impact on speech evaluation. Moreover, we took
steps to moderate test difficulty through its evaluation across
parameters like difficult word count, average sentence
readability and lexical density. Our results show that macro
features like accuracy and intonation, and micro features like
pause-topography are strongly predictive. The scoring of spoken
English is not within the purview of this paper.
intonation based feature for scoring the English speech of non-
native English speakers in Indian context. For this, we created an
automated spoken English scoring engine to learn from the
manual evaluation of spoken English. This involved using an
existing Automatic Speech Recognition (ASR) engine to convert
the speech to text. Thereafter, macro features like accuracy,
fluency and prosodic features were used to build a scoring model.
In the process, we introduced SimIntonation, short for similarity
between spoken intonation pattern and “ideal” i.e. training
intonation pattern. Our results show that it is a highly predictive
feature under controlled environment. We also categorized inter-
word pauses into 4 distinct types for a granular evaluation of
pauses and their impact on speech evaluation. Moreover, we took
steps to moderate test difficulty through its evaluation across
parameters like difficult word count, average sentence
readability and lexical density. Our results show that macro
features like accuracy and intonation, and micro features like
pause-topography are strongly predictive. The scoring of spoken
English is not within the purview of this paper.