refs.bib

@misc{baevski2020wav2vec,
      title={wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations}, 
      author={Alexei Baevski and Henry Zhou and Abdelrahman Mohamed and Michael Auli},
      year={2020},
      eprint={2006.11477},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{hsu2021hubert,
      title={HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units}, 
      author={Wei-Ning Hsu and Benjamin Bolte and Yao-Hung Hubert Tsai and Kushal Lakhotia and Ruslan Salakhutdinov and Abdelrahman Mohamed},
      year={2021},
      eprint={2106.07447},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{hannun2014deep,
      title={Deep Speech: Scaling up end-to-end speech recognition}, 
      author={Awni Hannun and Carl Case and Jared Casper and Bryan Catanzaro and Greg Diamos and Erich Elsen and Ryan Prenger and Sanjeev Satheesh and Shubho Sengupta and Adam Coates and Andrew Y. Ng},
      year={2014},
      eprint={1412.5567},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{graves2012sequence,
      title={Sequence Transduction with Recurrent Neural Networks}, 
      author={Alex Graves},
      year={2012},
      eprint={1211.3711},
      archivePrefix={arXiv},
      primaryClass={cs.NE}
}
@misc{collobert2016wav2letter,
      title={Wav2Letter: an End-to-End ConvNet-based Speech Recognition System}, 
      author={Ronan Collobert and Christian Puhrsch and Gabriel Synnaeve},
      year={2016},
      eprint={1609.03193},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
@misc{kalchbrenner2018efficient,
      title={Efficient Neural Audio Synthesis}, 
      author={Nal Kalchbrenner and Erich Elsen and Karen Simonyan and Seb Noury and Norman Casagrande and Edward Lockhart and Florian Stimberg and Aaron van den Oord and Sander Dieleman and Koray Kavukcuoglu},
      year={2018},
      eprint={1802.08435},
      archivePrefix={arXiv},
      primaryClass={cs.SD}
}
@article{Luo_2019,
   title={Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation},
   volume={27},
   ISSN={2329-9304},
   url={http://dx.doi.org/10.1109/TASLP.2019.2915167},
   DOI={10.1109/taslp.2019.2915167},
   number={8},
   journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Luo, Yi and Mesgarani, Nima},
   year={2019},
   month={Aug},
   pages={1256–1266}
}
@InProceedings{ brian_mcfee-proc-scipy-2015,
  author    = { {B}rian {M}c{F}ee and {C}olin {R}affel and {D}awen {L}iang and {D}aniel {P}.{W}. {E}llis and {M}att {M}c{V}icar and {E}ric {B}attenberg and {O}riol {N}ieto },
  title     = { librosa: {A}udio and {M}usic {S}ignal {A}nalysis in {P}ython },
  booktitle = { {P}roceedings of the 14th {P}ython in {S}cience {C}onference },
  pages     = { 18 - 24 },
  year      = { 2015 },
  editor    = { {K}athryn {H}uff and {J}ames {B}ergstra },
  doi       = { 10.25080/Majora-7b98e3ed-003 }
}
@INPROCEEDINGS{6701851,
  author={Perraudin, Nathanaël and Balazs, Peter and Søndergaard, Peter L.},
  booktitle={2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics}, 
  title={A fast Griffin-Lim algorithm}, 
  year={2013},
  volume={},
  number={},
  pages={1-4},
  doi={10.1109/WASPAA.2013.6701851}}
@INPROCEEDINGS{1172092,
  author={Griffin, D. and Jae Lim},
  booktitle={ICASSP '83. IEEE International Conference on Acoustics, Speech, and Signal Processing}, 
  title={Signal estimation from modified short-time Fourier transform}, 
  year={1983},
  volume={8},
  number={},
  pages={804-807},
  doi={10.1109/ICASSP.1983.1172092}}
@INPROCEEDINGS{6854049,
  author={Ghahremani, Pegah and BabaAli, Bagher and Povey, Daniel and Riedhammer, Korbinian and Trmal, Jan and Khudanpur, Sanjeev},
  booktitle={2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={A pitch extraction algorithm tuned for automatic speech recognition}, 
  year={2014},
  volume={},
  number={},
  pages={2494-2498},
  doi={10.1109/ICASSP.2014.6854049}}
@inproceedings{shen2018natural,
  title={Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions},
  author={Shen, Jonathan and Pang, Ruoming and Weiss, Ron J and Schuster, Mike and Jaitly, Navdeep and Yang, Zongheng and Chen, Zhifeng and Zhang, Yu and Wang, Yuxuan and Skerrv-Ryan, Rj and others},
  booktitle={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={4779--4783},
  year={2018},
  organization={IEEE}
}
@inproceedings{souden2009optimal,
  title={On optimal frequency-domain multichannel linear filtering for noise reduction},
  author={Souden, Mehrez and Benesty, Jacob and Affes, Sofiene},
  booktitle={IEEE Transactions on audio, speech, and language processing},
  volume={18},
  number={2},
  pages={260--276},
  year={2009},
  publisher={IEEE}
}
@inproceedings{higuchi2016robust,
  title={Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise},
  author={Higuchi, Takuya and Ito, Nobutaka and Yoshioka, Takuya and Nakatani, Tomohiro},
  booktitle={2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={5210--5214},
  year={2016},
  organization={IEEE}
}
@article{mises1929praktische,
  title={Praktische Verfahren der Gleichungsaufl{\"o}sung.},
  author={Mises, RV and Pollaczek-Geiringer, Hilda},
  journal={ZAMM-Journal of Applied Mathematics and Mechanics/Zeitschrift f{\"u}r Angewandte Mathematik und Mechanik},
  volume={9},
  number={1},
  pages={58--77},
  year={1929},
  publisher={Wiley Online Library}
}
@article{higuchi2017online,
  title={Online MVDR beamformer based on complex Gaussian mixture model with spatial prior for noise robust ASR},
  author={Higuchi, Takuya and Ito, Nobutaka and Araki, Shoko and Yoshioka, Takuya and Delcroix, Marc and Nakatani, Tomohiro},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={25},
  number={4},
  pages={780--793},
  year={2017},
  publisher={IEEE}
}