@misc{parakeet, author={{NVIDIA}}, title={Parakeet TDT 0.6B v3: Model Card}, year={2025}, url={https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3}, note={Accessed September 6, 2026}} @article{fastconformer, author={Rekesh, Dima and Koluguri, Nithin Rao and Kriman, Samuel and others}, title={Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition}, journal={arXiv:2305.05084}, year={2023}, url={https://arxiv.org/abs/2305.05084}} @inproceedings{tdt, author={Xu, Hainan and Jia, Fei and Majumdar, Somshubra and Huang, He and Watanabe, Shinji and Ginsburg, Boris}, title={Efficient Sequence Transduction by Jointly Predicting Tokens and Durations}, booktitle={ICML}, year={2023}, url={https://proceedings.mlr.press/v202/xu23g.html}} @inproceedings{leaf, author={Zeghidour, Neil and Teboul, Olivier and de Chaumont Quitry, F{\'e}lix and Tagliasacchi, Marco}, title={{LEAF}: A Learnable Frontend for Audio Classification}, booktitle={ICLR}, year={2021}, url={https://openreview.net/forum?id=jM76BCb6F9m}} @inproceedings{sincnet, author={Ravanelli, Mirco and Bengio, Yoshua}, title={Speaker Recognition from Raw Waveform with {SincNet}}, booktitle={SLT}, year={2018}, url={https://arxiv.org/abs/1808.00158}} @misc{fleurs, author={Conneau, Alexis and Ma, Min and Khanuja, Simran and others}, title={{FLEURS}: Few-shot Learning Evaluation of Universal Representations of Speech}, year={2022}, howpublished={arXiv:2205.12446}, url={https://arxiv.org/abs/2205.12446}} @inproceedings{librispeech, author={Panayotov, Vassil and Chen, Guoguo and Povey, Daniel and Khudanpur, Sanjeev}, title={{LibriSpeech}: An {ASR} Corpus Based on Public Domain Audio Books}, booktitle={ICASSP}, pages={5206--5210}, year={2015}, doi={10.1109/ICASSP.2015.7178964}, url={https://www.openslr.org/12}} @misc{native, author={{NVIDIA}}, title={{NeMo-Speech.cpp}, version 0.1.0}, year={2026}, url={https://github.com/NVIDIA/NeMo-Speech.cpp/tree/v0.1.0}} @inproceedings{pruning, author={Jiang, Huiqiang and Zhang, Li Lyna and Li, Yuang and others}, title={Accurate and Structured Pruning for Efficient Automatic Speech Recognition}, booktitle={Interspeech}, year={2023}, url={https://arxiv.org/abs/2305.19549}} @inproceedings{sarwar, title={Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks}, author={Sarwar, Syed Shakib and Panda, Priyadarshini and Roy, Kaushik}, booktitle={ISLPED}, year={2017}, url={https://arxiv.org/abs/1705.04748} }