Papers by Grant Strimel
Multi-Modal Retrieval For Large Language Model Based Speech Recognition (2024.findings-acl)
Copied to clipboard
Aditya Gourav, Jari Kolehmainen, Prashanth Shivakumar, Yile Gu, Grant Strimel, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko
| Challenge: | kNN-LM and cross-attention techniques are used to extend text based retrieval to other modalities . wide adoption of large language models has driven new application areas leveraging this technology . |
| Approach: | They propose to use kNN-LM and cross-attention techniques to extend text retrieval methods to other modalities. |
| Outcome: | The proposed methods outperform text-based retrieval and improve word error rate on a speech recognition dataset. |
SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning (2025.acl-long)
Copied to clipboard
Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish, Arunasish Sen, Jian. Xie, Grant Strimel, Andreas Schwarz
| Challenge: | Recent years have witnessed significant advancements in integrating speech and audio capabilities into large language models. |
| Approach: | They propose a 50M-example dataset for instruction fine-tuning and pre-training of speech-text large language models (LLMs) the dataset spans five languages and enables a diverse range of speech understanding and controllable speech generation instructions. |
| Outcome: | The proposed dataset outperforms existing speech-text LLMs on instruction-following benchmarks while achieving competitive performance on foundational speech tasks. |
PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding (2026.findings-acl)
Copied to clipboard
Masao Someki, Chien-yu Huang, Siddhant Arora, Samuele Cornell, Markus Müller, Nathan Susanj, Rupak Vignesh Swaminathan, Grant Strimel, Jing Liu, Shinji Watanabe
| Challenge: | Long-form audio understanding poses significant challenges due to the extreme length of audio sequences and the need to reason over heterogeneous acoustic cues distributed over time. |
| Approach: | They propose a retrieval-augmented generation framework for scalable long-form audio understanding . planRAG-Audio explicitly plans which modalities and temporal spans are required for a given query . |
| Outcome: | Experiments show that planRAG-Audio reduces the length of inputs for long-form audio models . the proposed framework can efficiently reason over long-term speech data . |