Garima Lalwani — accepted AI-conference papers

2025

AMuSE: Attentive Multilingual Speech Encoding for Zero-Prior ASR

Ashutosh Varshney, Debmalya Chakrabarty, Akshat Jaiswal, Harish Arsikere, Abhinav Jain, Swayambhu Nath Ray +6

ICASSP 2025accepted

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 a…

Cited by 0 Source ↗Scholar ↗

2024

An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems

Hitesh Tulsiani, David Chan, Shalini Ghosh, Garima Lalwani, Prabhat Pandey, Ankish Bansal +3

ICML 2024poster

Dialog systems, such as voice assistants, are expected to engage with users in complex, evolving conversations. Unfortunately, traditional automatic speech recognition (ASR) systems deployed in such applications are usually trained to recognize each turn independently and lack the ability to adapt t…

Cited by 0 Source ↗PDF ↗Scholar ↗

2021

Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings

Sawsan Alqahtani, Garima Lalwani, Yi Zhang, Salvatore Romeo, Saab Mansour

EMNLP 2021finding

Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces. For contextualized embeddings, alignment becomes more complex as we additionally take context into consid…

Cited by 21 Source ↗PDF ↗Scholar ↗