Publications

Google Scholar Page

2021

1. Multimodal Speech Summarization through Semantic Concept Learning
   Shruti Palaskar, Ruslan Salakhutdinov, Alan W Black, Florian Metze
   The 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH), 2021

2. How2Sign: A Large-Scale Multimodal Dataset for Continuous American Sign Language
   Amanda Duarte, Shruti Palaskar, Lucas Ventura, Deepti Ghadiyaram, Kenneth DeHaan, Florian Metze, Jordi Torres, Xavier Giró-i-Nieto
   Computer Vision and Pattern Recognition (CVPR), 2021
   Paper

3. Hierarchical Learning for Multimodal Language Generation
   Shruti Palaskar, Florian Metze, Yonatan Bisk, Alan W Black
   In preparation

2020

1. Transfer Learning for Multimodal Dialog
   Shruti Palaskar*, Ramon Sanabria*, Florian Metze
   Elsevier Computer Speech and Language (CS&L)
   Paper

2. Grounded Sequence-to-Sequence Transduction
   Lucia Specia, Raman Arora, Loic Barrault, Ozan Caglayan, Amanda Duarte, Desmond Elliott, Spandana Gella, Nils Holzenberger, Chiraag Lala, Sun Jae Lee, Jindrich Libovick' y, Pranava Madhyastha, Florian Metze, Karl Mulligan, Alissa Ostapenko, Shruti Palaskar, Ramon Sanabria, Josiah Wang
   IEEE Journal for Select Topics in Signal Processing (JSTSP)
   Paper

3. Speech Technology for Unwritten Languages
   Odette Scharenborg, Laurent Besacier, Alan W Black, Mark Hasegawa-Johnson, Florian Metze, Graham Neubig, Sebastian Stüker, Pierre Godard, Markus Müller, Lucas Ondel, Shruti Palaskar, Philip Arthur, Francesco Ciannella, Mingxing Du, Erin Larsen, Danny Merkx, Rachid Riad, Liming Wang, Emmanuel Dupoux
   IEEE Transactions for Audio, Speech and Language Processing (TASLP)
   Paper

4. ASR Error Correction and Domain Adaptation using Machine Translation
   Anirudh Mani*, Shruti Palaskar*, Nimshi Venkat Meripo, Sandeep Konam, Florian Metze
   Oral Presentation International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020
   Paper

5. Towards understanding ASR error correction for medical conversations
   Anirudh Mani, Shruti Palaskar, Sandeep Konam
   First Workshop on Natural Language Processing for Medical Conversations, ACL 2020
   Paper

2019

1. Multimodal Abstractive Summarization for How2 Videos
   Shruti Palaskar, Jindrich Libovický, Spandana Gella, Florian Metze
   Association for Computational Linguistics (ACL), 2019
   Paper

2. Learned in Speech Recognition: Contextual Acoustic Word Embeddigs
   Shruti Palaskar*, Vikas Raunak*, Florian Metze
   International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
   Paper

3. Learning from Multiview Correlations in Open-Domain Videos
   Nils Holzenberger*, Shruti Palaskar*, Pranava Madhyastha, Florian Metze, Raman Arora
   International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
   Paper

4. Multimodal Grounding for Sequence-to-Sequence Speech Recognition
   Ozan Caglayan, Ramon Sanabria, Shruti Palaskar, Loïc Barrault, Florian Metze
   International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
   Paper

5. CMU Sinbad’s Submission to the DSTC7 AVSD Track
   Ramon Sanabria*, Shruti Palaskar*, Florian Metze
   Oral Presentation
   7th Dialog State Tracking Challenge (DSTC) at AAAI, 2019
   Paper

2018

1. Acoustic to Word Recognition with Sequence to Sequence Models
   Shruti Palaskar and Florian Metze
   IEEE Workshop on Spoken Language Technology (SLT), 2018
   Paper

2. How2: A Large-scale Dataset for Multimodal Language Understanding
   Ramon Sanabria, Ozan Caglayan, Shruti Palaskar, Desmond Elliott, Loïc Barrault, Lucia Specia, Florian Metze
   NeurIPS workshop on Visually Grounded Interaction and Language (ViGIL), 2018
   Paper

3. Multimodal Abstractive Summarization for Open-Domain Videos
   Jindrich Libovicky, Shruti Palaskar, Spandana Gella, Florian Metze
   Spotlight Presentation
   NeurIPS workshop on Visually Grounded Interaction and Language (ViGIL), 2018
   Paper

4. End-to-End Multimodal Speech Recognition
   Shruti Palaskar*, Ramon Sanabria*, Florian Metze
   International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018
   Paper

5. Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the “Speaking Rosetta” JSALT 2017 Workshop
   Odette Scharenborg, Laurent Besacier, Alan Black, Mark Hasegawa-Johnson, Florian Metze, Graham Neubig, Sebastian Stüker, Pierre Godard, Markus Müller, Lucas Ondel, Shruti Palaskar, Philip Arthur, Francesco Ciannella, Mingxing Du, Elin Larsen, Danny Merkx, Rachid Riad, Liming Wang, Emmanuel Dupoux
   International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018
   Paper

2017

1. Building an asr system for a low-resource language through the adaptation of a high-resource language asr system: Preliminary results
   Odette Scharenborg, Francesco Ciannella, Shruti Palaskar, Alan Black, Florian Metze, Lucas Ondel, Mark Hasegawa-Johnson
   ICNLSSP, 2017
   Paper

2. Combining LSTM and Latent Topic Modeling for Mortality Prediction
   Yohan Jo, Lisa Lee, Shruti Palaskar
   Preprint, 2017
   Paper

* - Equal contribution