Siddharth Dalmia

72 papers A* 3A 8B 1C 2Misc 8Journal 36Unranked 13

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	LOFT: Scalable and More Realistic Long-Context Evaluation. NAACL (Findings) Jinhyuk Lee, Anthony Chen, Zhuyun Dai, Dheeru Dua, Devendra Singh Sachan, Michael Boratko, Yi Luan, Sébastien M. R. Arnold, Vincent Perot, Siddharth Dalmia, Hexiang Hu, Xudong Lin, Panupong Pasupat, Aida Amini, Jeremy R. Cole, Sebastian Riedel, Iftekhar Naim, Ming-Wei Chang, Kelvin Guu
2025	—	`conf`	Revisiting In-Context Learning with Long Context Language Models. ACL (Findings) Jinheon Baek, Sun Jae Lee, Prakhar Gupta, Geunseob Oh, Siddharth Dalmia, Prateek Kolhar
2024	J	`jnl`	Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? CoRR Jinhyuk Lee, Anthony Chen, Zhuyun Dai, Dheeru Dua, Devendra Singh Sachan, Michael Boratko, Yi Luan, Sébastien M. R. Arnold, Vincent Perot, Siddharth Dalmia, Hexiang Hu, Xudong Lin, Panupong Pasupat, Aida Amini, Jeremy R. Cole, Sebastian Riedel, Iftekhar Naim, Ming-Wei Chang, Kelvin Guu
2024	A*	`conf`	LLM Augmented LLMs: Expanding Capabilities through Composition. ICLR Rachit Bansal, Bidisha Samanta, Siddharth Dalmia, Nitish Gupta, Sriram Ganapathy, Abhishek Bapna, Prateek Jain, Partha Talukdar
2024	J	`jnl`	LLM Augmented LLMs: Expanding Capabilities through Composition. CoRR Rachit Bansal, Bidisha Samanta, Siddharth Dalmia, Nitish Gupta, Shikhar Vashishth, Sriram Ganapathy, Abhishek Bapna, Prateek Jain, Partha Talukdar
2024	Misc	`conf`	Multimodal Modeling for Spoken Language Identification. ICASSP Shikhar Bharadwaj, Min Ma, Shikhar Vashishth, Ankur Bapna, Sriram Ganapathy, Vera Axelrod, Siddharth Dalmia, Wei Han, Yu Zhang, Daan van Esch, Sandy Ritchie, Partha Talukdar, Jason Riesa
2024	J	`jnl`	Revisiting In-Context Learning with Long Context Language Models. CoRR Jinheon Baek, Sun Jae Lee, Prakhar Gupta, Geunseob Oh, Siddharth Dalmia, Prateek Kolhar
2024	J	`jnl`	Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems. CoRR Frank Palma Gomez, Ramon Sanabria, Yun-Hsuan Sung, Daniel Cer, Siddharth Dalmia, Gustavo Hernández Ábrego
2023	Misc	`conf`	Align, Write, Re-Order: Explainable End-to-End Speech Translation via Operation Sequence Generation. ICASSP Motoi Omachi, Brian Yan, Siddharth Dalmia, Yuya Fujita, Shinji Watanabe
2023	A	`conf`	CTC Alignments Improve Autoregressive Translation. EACL Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W. Black, Shinji Watanabe
2023	—	`conf`	ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit. ACL (demo) Brian Yan, Jiatong Shi, Yun Tang, Hirofumi Inaguma, Yifan Peng, Siddharth Dalmia, Peter Polak, Patrick Fernandes, Dan Berrebbi, Tomoki Hayashi, Xiaohui Zhang, Zhaoheng Ni, Moto Hira, Soumi Maiti, Juan Pino, Shinji Watanabe
2023	—	`—`	Exploiting Compositionality in Sequence Models Siddharth Dalmia
2023	J	`jnl`	LegoNN: Building Modular Encoder-Decoder Models. IEEE ACM Trans. Audio Speech Lang. Process. Siddharth Dalmia, Dmytro Okhonko, Mike Lewis, Sergey Edunov, Shinji Watanabe, Florian Metze, Luke Zettlemoyer, Abdelrahman Mohamed
2023	J	`jnl`	Multimodal Modeling For Spoken Language Identification. CoRR Shikhar Bharadwaj, Min Ma, Shikhar Vashishth, Ankur Bapna, Sriram Ganapathy, Vera Axelrod, Siddharth Dalmia, Wei Han, Yu Zhang, Daan van Esch, Sandy Ritchie, Partha Talukdar, Jason Riesa
2022	—	`conf`	A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding. SLT Yifan Peng, Siddhant Arora, Yosuke Higuchi, Yushi Ueda, Sujay Kumar, Karthik Ganesan, Siddharth Dalmia, Xuankai Chang, Shinji Watanabe
2022	J	`jnl`	A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding. CoRR Yifan Peng, Siddhant Arora, Yosuke Higuchi, Yushi Ueda, Sujay Kumar, Karthik Ganesan, Siddharth Dalmia, Xuankai Chang, Shinji Watanabe
2022	J	`jnl`	Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation. CoRR Motoi Omachi, Brian Yan, Siddharth Dalmia, Yuya Fujita, Shinji Watanabe
2022	A*	`conf`	Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding. ICML Yifan Peng, Siddharth Dalmia, Ian R. Lane, Shinji Watanabe
2022	J	`jnl`	Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding. CoRR Yifan Peng, Siddharth Dalmia, Ian R. Lane, Shinji Watanabe
2022	—	`conf`	CMU's IWSLT 2022 Dialect Speech Translation System. IWSLT@ACL Brian Yan, Patrick Fernandes, Siddharth Dalmia, Jiatong Shi, Yifan Peng, Dan Berrebbi, Xinyi Wang, Graham Neubig, Shinji Watanabe
2022	J	`jnl`	CTC Alignments Improve Autoregressive Translation. CoRR Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W. Black, Shinji Watanabe
2022	Misc	`conf`	ESPnet-SLU: Advancing Spoken Language Understanding Through ESPnet. ICASSP Siddhant Arora, Siddharth Dalmia, Pavel Denisov, Xuankai Chang, Yushi Ueda, Yifan Peng, Yuekai Zhang, Sujay Kumar, Karthik Ganesan, Brian Yan, Ngoc Thang Vu, Alan W. Black, Shinji Watanabe
2022	—	`conf`	FLEURS: FEW-Shot Learning Evaluation of Universal Representations of Speech. SLT Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, Ankur Bapna
2022	J	`jnl`	FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech. CoRR Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, Ankur Bapna
2022	Misc	`conf`	Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorization. ICASSP Brian Yan, Chunlei Zhang, Meng Yu, Shi-Xiong Zhang, Siddharth Dalmia, Dan Berrebbi, Chao Weng, Shinji Watanabe, Dong Yu
2022	J	`jnl`	LegoNN: Building Modular Encoder-Decoder Models. CoRR Siddharth Dalmia, Dmytro Okhonko, Mike Lewis, Sergey Edunov, Shinji Watanabe, Florian Metze, Luke Zettlemoyer, Abdelrahman Mohamed
2022	—	`conf`	Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models. EMNLP (Findings) Siddhant Arora, Siddharth Dalmia, Brian Yan, Florian Metze, Alan W. Black, Shinji Watanabe
2022	J	`jnl`	Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models. CoRR Siddhant Arora, Siddharth Dalmia, Brian Yan, Florian Metze, Alan W. Black, Shinji Watanabe
2022	A	`conf`	Two-Pass Low Latency End-to-End Spoken Language Understanding. INTERSPEECH Siddhant Arora, Siddharth Dalmia, Xuankai Chang, Brian Yan, Alan W. Black, Shinji Watanabe
2022	J	`jnl`	Two-Pass Low Latency End-to-End Spoken Language Understanding. CoRR Siddhant Arora, Siddharth Dalmia, Xuankai Chang, Brian Yan, Alan W. Black, Shinji Watanabe
2021	A	`conf`	Differentiable Allophone Graphs for Language-Universal Speech Recognition. Interspeech Brian Yan, Siddharth Dalmia, David R. Mortensen, Florian Metze, Shinji Watanabe
2021	J	`jnl`	Differentiable Allophone Graphs for Language-Universal Speech Recognition. CoRR Brian Yan, Siddharth Dalmia, David R. Mortensen, Florian Metze, Shinji Watanabe
2021	J	`jnl`	ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet. CoRR Siddhant Arora, Siddharth Dalmia, Pavel Denisov, Xuankai Chang, Yushi Ueda, Yifan Peng, Yuekai Zhang, Sujay Kumar, Karthik Ganesan, Brian Yan, Ngoc Thang Vu, Alan W. Black, Shinji Watanabe
2021	—	`conf`	ESPnet-ST IWSLT 2021 Offline Speech Translation System. IWSLT Hirofumi Inaguma, Brian Yan, Siddharth Dalmia, Pengcheng Guo, Jiatong Shi, Kevin Duh, Shinji Watanabe
2021	J	`jnl`	ESPnet-ST IWSLT 2021 Offline Speech Translation System. CoRR Hirofumi Inaguma, Brian Yan, Siddharth Dalmia, Pengcheng Guo, Jiatong Shi, Kevin Duh, Shinji Watanabe
2021	C	`conf`	Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates. ASRU Hirofumi Inaguma, Siddharth Dalmia, Brian Yan, Shinji Watanabe
2021	J	`jnl`	Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates. CoRR Hirofumi Inaguma, Siddharth Dalmia, Brian Yan, Shinji Watanabe
2021	J	`jnl`	Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorization. CoRR Brian Yan, Chunlei Zhang, Meng Yu, Shi-Xiong Zhang, Siddharth Dalmia, Dan Berrebbi, Chao Weng, Shinji Watanabe, Dong Yu
2021	A	`conf`	NoiseQA: Challenge Set Evaluation for User-Centric Question Answering. EACL Abhilasha Ravichander, Siddharth Dalmia, Maria Ryskina, Florian Metze, Eduard H. Hovy, Alan W. Black
2021	J	`jnl`	NoiseQA: Challenge Set Evaluation for User-Centric Question Answering. CoRR Abhilasha Ravichander, Siddharth Dalmia, Maria Ryskina, Florian Metze, Eduard H. Hovy, Alan W. Black
2021	A	`conf`	Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding. Interspeech Siddhant Arora, Alissa Ostapenko, Vijay Viswanathan, Siddharth Dalmia, Florian Metze, Shinji Watanabe, Alan W. Black
2021	J	`jnl`	Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding. CoRR Siddhant Arora, Alissa Ostapenko, Vijay Viswanathan, Siddharth Dalmia, Florian Metze, Shinji Watanabe, Alan W. Black
2021	—	`conf`	Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks. NAACL-HLT Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe
2021	J	`jnl`	Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks. CoRR Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe
2021	Misc	`conf`	Transformer-Transducers for Code-Switched Speech Recognition. ICASSP Siddharth Dalmia, Yuzong Liu, Srikanth Ronanki, Katrin Kirchhoff
2020	—	`conf`	On Long-Tailed Phenomena in Neural Machine Translation. EMNLP (Findings) Vikas Raunak, Siddharth Dalmia, Vivek Gupta, Florian Metze
2020	J	`jnl`	On Long-Tailed Phenomena in Neural Machine Translation. CoRR Vikas Raunak, Siddharth Dalmia, Vivek Gupta, Florian Metze
2020	A*	`conf`	Towards Zero-Shot Learning for Automatic Phonemic Transcription. AAAI Xinjian Li, Siddharth Dalmia, David R. Mortensen, Juncheng Li, Alan W. Black, Florian Metze
2020	J	`jnl`	Towards Zero-shot Learning for Automatic Phonemic Transcription. CoRR Xinjian Li, Siddharth Dalmia, David R. Mortensen, Juncheng Li, Alan W. Black, Florian Metze
2020	J	`jnl`	Transformer-Transducers for Code-Switched Speech Recognition. CoRR Siddharth Dalmia, Yuzong Liu, Srikanth Ronanki, Katrin Kirchhoff
2020	Misc	`conf`	Universal Phone Recognition with a Multilingual Allophone System. ICASSP Xinjian Li, Siddharth Dalmia, Juncheng Li, Matthew Lee, Patrick Littell, Jiali Yao, Antonios Anastasopoulos, David R. Mortensen, Graham Neubig, Alan W. Black, Florian Metze
2020	J	`jnl`	Universal Phone Recognition with a Multilingual Allophone System. CoRR Xinjian Li, Siddharth Dalmia, Juncheng Li, Matthew Lee, Patrick Littell, Jiali Yao, Antonios Anastasopoulos, David R. Mortensen, Graham Neubig, Alan W. Black, Florian Metze
2019	A	`conf`	Cross-Attention End-to-End ASR for Two-Party Conversations. INTERSPEECH Suyoun Kim, Siddharth Dalmia, Florian Metze
2019	J	`jnl`	Cross-Attention End-to-End ASR for Two-Party Conversations. CoRR Suyoun Kim, Siddharth Dalmia, Florian Metze
2019	J	`jnl`	Enforcing Encoder-Decoder Modularity in Sequence-to-Sequence Models. CoRR Siddharth Dalmia, Abdelrahman Mohamed, Mike Lewis, Florian Metze, Luke Zettlemoyer
2019	—	`conf`	Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion. ACL (1) Suyoun Kim, Siddharth Dalmia, Florian Metze
2019	J	`jnl`	Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion. CoRR Suyoun Kim, Siddharth Dalmia, Florian Metze
2019	A	`conf`	Multilingual Speech Recognition with Corpus Relatedness Sampling. INTERSPEECH Xinjian Li, Siddharth Dalmia, Alan W. Black, Florian Metze
2019	J	`jnl`	Multilingual Speech Recognition with Corpus Relatedness Sampling. CoRR Xinjian Li, Siddharth Dalmia, Alan W. Black, Florian Metze
2019	Misc	`conf`	Phoneme Level Language Models for Sequence Based Low Resource ASR. ICASSP Siddharth Dalmia, Xinjian Li, Alan W. Black, Florian Metze
2019	J	`jnl`	Phoneme Level Language Models for Sequence Based Low Resource ASR. CoRR Siddharth Dalmia, Xinjian Li, Alan W. Black, Florian Metze
2019	A	`conf`	SANTLR: Speech Annotation Toolkit for Low Resource Languages. INTERSPEECH Xinjian Li, Zhong Zhou, Siddharth Dalmia, Alan W. Black, Florian Metze
2019	J	`jnl`	SANTLR: Speech Annotation Toolkit for Low Resource Languages. CoRR Xinjian Li, Zhong Zhou, Siddharth Dalmia, Alan W. Black, Florian Metze
2019	J	`jnl`	The ARIEL-CMU Systems for LoReHLT18. CoRR Aditi Chaudhary, Siddharth Dalmia, Junjie Hu, Xinjian Li, Austin Matthews, Aldrian Obaja Muis, Naoki Otani, Shruti Rijhwani, Zaid Sheikh, Nidhi Vyas, Xinyi Wang, Jiateng Xie, Ruochen Xu, Chunting Zhou, Peter J. Jansen, Yiming Yang, Lori S. Levin, Florian Metze, Teruko Mitamura, David R. Mortensen, Graham Neubig, Eduard H. Hovy, Alan W. Black, Jaime G. Carbonell, Graham Horwood, Shabnam Tafreshi, Mona T. Diab, Efsun Sarioglu Kayi, Noura Farra, Kathleen R. McKeown
2018	—	`conf`	Domain Robust Feature Extraction for Rapid Low Resource ASR Development. SLT Siddharth Dalmia, Xinjian Li, Florian Metze, Alan W. Black
2018	J	`jnl`	Domain Robust Feature Extraction for Rapid Low Resource ASR Development. CoRR Siddharth Dalmia, Xinjian Li, Florian Metze, Alan W. Black
2018	B	`conf`	Epitran: Precision G2P for Many Languages. LREC David R. Mortensen, Siddharth Dalmia, Patrick Littell
2018	Misc	`conf`	Sequence-Based Multi-Lingual Low Resource Speech Recognition. ICASSP Siddharth Dalmia, Ramon Sanabria, Florian Metze, Alan W. Black
2018	J	`jnl`	Sequence-based Multi-lingual Low Resource Speech Recognition. CoRR Siddharth Dalmia, Ramon Sanabria, Florian Metze, Alan W. Black
2017	J	`jnl`	A novel similarity measure: Voronoi audio similarity for genre classification. Int. J. Intell. Syst. Technol. Appl. Prafulla Kalapatapu, N. N. Tejas, Siddharth Dalmia, Prakhar Gupta, Bhaswant Inguva, Aruna Malapati
2017	—	`conf`	An approach for self-training audio event detectors using web data. EUSIPCO Benjamin Elizalde, Ankit Shah, Siddharth Dalmia, Min Hun Lee, Rohan Badlani, Anurag Kumar, Bhiksha Raj, Ian R. Lane
2015	C	`conf`	Robust ASR using neural network based speech enhancement and feature simulation. ASRU Sunit Sivasankaran, Aditya Arie Nugraha, Emmanuel Vincent, Juan Andres Morales-Cordovilla, Siddharth Dalmia, Irina Illina, Antoine Liutkus