Jianbo Ma

@article{guo2024gotta,
  title = {Gotta hear them all: Sound source aware vision to audio generation},
  author = {Guo, Wei and Wang, Heng and Ma, Jianbo and Cai, Weidong},
  journal = {arXiv preprint arXiv:2411.15447},
  year = {2024},
}

@inproceedings{10888882,
  author = {Kushwaha, Saksham Singh and Ma, Jianbo and Thomas, Mark R. P. and Tian, Yapeng and Bruni, Avery},
  booktitle = {ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models},
  year = {2025},
  volume = {},
  number = {},
  pages = {1-5},
  keywords = {Measurement;Scalability;Spatial audio;Semantics;Phase estimation;Noise;Diffusion models;MONOS devices;Speech processing;Spectrogram;Spatial audio generation;Ambisonics},
  doi = {10.1109/ICASSP49660.2025.10888882},
}

@article{zhao2024unified,
  title = {A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model},
  author = {Zhao, Dongdi and Ma, Jianbo and Lu, Lu and Li, Jinke and Ji, Xuan and Zhu, Lei and Fang, Fuming and Liu, Ming and Jiang, Feijun},
  journal = {arXiv preprint arXiv:2401.02673},
  url = {https://arxiv.org/pdf/2401.02673},
  year = {2024},
}

@inproceedings{wang2024v2a,
  title = {V2a-mapper: A lightweight solution for vision-to-audio generation by connecting foundation models},
  author = {Wang, Heng and Ma, Jianbo and Pascual, Santiago and Cartwright, Richard and Cai, Weidong},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {38},
  number = {14},
  pages = {15492--15501},
  year = {2024},
}

@article{ma2023low,
  title = {A low latency attention module for streaming self-supervised speech representation learning (second version of 'low latency attention')},
  author = {Ma, Jianbo and Pan, Siqi and Chandran, Deepak and Fanelli, Andrea and Cartwright, Richard},
  journal = {arXiv preprint arXiv:2302.13451},
  year = {2024},
  url = {https://arxiv.org/abs/2302.13451},
}

@article{ma2023lox,
  title = {Low latency transformers for speech processing},
  author = {Ma, Jianbo and Pan, Siqi and Chandran, Deepak and Fanelli, Andrea and Cartwright, Richard},
  journal = {arXiv preprint arXiv:2302.13451},
  year = {2023},
  url = {https://arxiv.org/abs/2302.13451},
}

@inproceedings{ma2022hmmctc,
  title = {Hidden Markov Models and Connectionist Temporal Classification},
  author = {Ma, Jianbo},
  year = {2022},
}