Accès ouvert
2026
preprint
OpenAlex
Michael L. Chrzan, Meghavarshini Krishnaswamy, Robert Gibboni, Katie Wetstone et autres
Automated analysis of K-12 classroom dynamics faces challenges due to background noise and variable child speech, often confounding acoustic-only models. This study evaluates a multimodal speaker identification framework anchoring acoustic embeddings with LLM-derived semantic context. Using a subset of the EDSI dataset …
Accès ouvert
2026
preprint
OpenAlex
Michael L. Chrzan, Meghavarshini Krishnaswamy, Robert Gibboni, Katie Wetstone et autres
Automated analysis of K-12 classroom dynamics faces challenges due to background noise and variable child speech, often confounding acoustic-only models. This study evaluates a multimodal speaker identification framework anchoring acoustic embeddings with LLM-derived semantic context. Using a subset of the EDSI dataset …
us, cn
(code pays fourni par la source)
Accès ouvert
2026
other
OpenAlex
Gregory T. Chism, Carlos Lizarraga-Celaya, Enrique Noriega-Atala, Jeffrey K. Gillan et autres
This work is licensed under a Creative Commons Attribution 4.0 International License. This is a self-paced, asynchronous online workshop designed to help academics, researchers, and educators learn to effectively use generative AI tools. All materials are freely available online and can be …
us
(code pays fourni par la source)
Accès ouvert
2026
other
OpenAlex
Gregory T. Chism, Carlos Lizarraga-Celaya, Enrique Noriega-Atala, Jeffrey K. Gillan et autres
This work is licensed under a Creative Commons Attribution 4.0 International License. This is a self-paced, asynchronous online workshop designed to help academics, researchers, and educators learn to effectively use generative AI tools. All materials are freely available online and can be …
us
(code pays fourni par la source)
Accès ouvert
2025
conference-paper
OpenAlex
Adarsh Pyarelal, John Culnan, Ayesha Qamar, Meghavarshini Krishnaswamy et autres
Adarsh Pyarelal, John M Culnan, Ayesha Qamar, Meghavarshini Krishnaswamy, Yuwei Wang, Cheonkam Jeong, Chen Chen, Md Messal Monem Miah, Shahriar Hormozi, Jonathan Tong, Ruihong Huang. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
us
(code pays fourni par la source)
2023
conference-paper
OpenAlex
Adarsh Pyarelal, Eric Duong, Caleb Shibu, Paulo Soares et autres
Accès ouvert
2021
conference-paper
OpenAlex
John Culnan, Seongjin Park, Meghavarshini Krishnaswamy, Rebecca Sharp
In deployment, systems that use speech as input must make use of automated transcriptions. Yet, typically when these systems are evaluated, gold transcriptions are assumed. We explicitly examine the impact of transcription errors on the downstream performance of a multi-modal system on …
2020
conference-abstract
OpenAlex
Meghavarshini Krishnaswamy, Indranil Dutta, Maumita Bhaumik
Tight coronal contrasts in Malayalam geminates (V1t̪:V2 vs. V1t:V2 vs. V1t:V2) are examined in an Ultrasound study of tongue contours to understand the nature of coarticulatory resistance and aggressiveness. Degree of Articulatory Constraint (DAC) predicts that articulatory complexity mitigates the nature of …
us, in
(code pays fourni par la source)
2018
conference-abstract
OpenAlex
Ushasi Banerjee, Indranil Dutta, Meghavarshini Krishnaswamy
Geminate voicing requires both active and passive cavity expansion in order to delay the equalization of subglottal and supraglottal pressure (Ohala 1983, Ham 2001). Studies report differences in stop closure duration (Lahiri & Hankamer 1988) and pre-geminate vowel duration as cues to …
in
(code pays fourni par la source)
2018
conference-abstract
OpenAlex
Meghavarshini Krishnaswamy, Indranil Dutta, Ushasi Banerjee
Geminate voicing is cross-linguistically not preferred (Ohala 1997). Voicing requires both active and passive cavity expansion to maintain a pressure gradient across the vocal tract. Maintainting length contrast and sustained voicing during closure is key for languages like Bengali that make both …
in
(code pays fourni par la source)