Add Ray tracing method for RIR (#2850)

Summary:
This PR adds the `ray_tracing()` helper to compute a RIR (part of #2624). The implementation is heavily based on `pyroomacoustics`.

Pull Request resolved: #2850

Differential Revision: D41764237

Pulled By: nateanl

fbshipit-source-id: f54d8e5f39d5b26d806dd9a1fba1f30adab0f40e

Author: NicolasHug

docs/source/prototype.functional.rst

@@ -30,4 +30,5 @@ Room Impulse Response Simulation
    :toctree: generated
    :nosignatures:
 
+   ray_tracing
    simulate_rir_ism

docs/source/refs.bib

@@ -66,7 +66,7 @@ @misc{ljspeech17
   year         = {2017}
 }
 @misc{conneau2020unsupervised,
-      title={Unsupervised Cross-lingual Representation Learning for Speech Recognition}, 
+      title={Unsupervised Cross-lingual Representation Learning for Speech Recognition},
       author={Alexis Conneau and Alexei Baevski and Ronan Collobert and Abdelrahman Mohamed and Michael Auli},
       year={2020},
       eprint={2006.13979},
@@ -80,7 +80,7 @@ @inproceedings{Gales2014SpeechRA
   year={2014}
 }
 @misc{ardila2020common,
-      title={Common Voice: A Massively-Multilingual Speech Corpus}, 
+      title={Common Voice: A Massively-Multilingual Speech Corpus},
       author={Rosana Ardila and Megan Branson and Kelly Davis and Michael Henretty and Michael Kohler and Josh Meyer and Reuben Morais and Lindsay Saunders and Francis M. Tyers and Gregor Weber},
       year={2020},
       eprint={1912.06670},
@@ -99,16 +99,16 @@ @article{Pratap_2020
 }
 @INPROCEEDINGS{librilight,
   author={J. {Kahn} and M. {Rivière} and W. {Zheng} and E. {Kharitonov} and Q. {Xu} and P. E. {Mazaré} and J. {Karadayi} and V. {Liptchinsky} and R. {Collobert} and C. {Fuegen} and T. {Likhomanenko} and G. {Synnaeve} and A. {Joulin} and A. {Mohamed} and E. {Dupoux}},
-  booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
-  title={Libri-Light: A Benchmark for ASR with Limited or No Supervision}, 
+  booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  title={Libri-Light: A Benchmark for ASR with Limited or No Supervision},
   year={2020},
   pages={7669-7673},
   note = {\url{https://github.com/facebookresearch/libri-light}},
 }
 @INPROCEEDINGS{7178964,
   author={Panayotov, Vassil and Chen, Guoguo and Povey, Daniel and Khudanpur, Sanjeev},
-  booktitle={2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
-  title={Librispeech: An ASR corpus based on public domain audio books}, 
+  booktitle={2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  title={Librispeech: An ASR corpus based on public domain audio books},
   year={2015},
   volume={},
   number={},
@@ -122,47 +122,47 @@ @inproceedings{ott2019fairseq
   year = {2019},
 }
 @misc{baevski2020wav2vec,
-      title={wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations}, 
+      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}, 
+      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}, 
+      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}, 
+      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}, 
+      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}, 
+      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},
@@ -202,26 +202,26 @@ @InProceedings{ brian_mcfee-proc-scipy-2015
 }
 @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}, 
+  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}, 
+  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}, 
+  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={},
@@ -254,16 +254,16 @@ @inproceedings{higuchi2016robust
   organization={IEEE}
 }
 @inproceedings{shi2021emformer,
-  title={Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition}, 
+  title={Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition},
   author={Shi, Yangyang and Wang, Yongqiang and Wu, Chunyang and Yeh, Ching-Feng and Chan, Julian and Zhang, Frank and Le, Duc and Seltzer, Mike},
-  booktitle={ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
+  booktitle={ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
   pages={6783-6787},
   year={2021}
 }
 @inproceedings{9747706,
   author={Shi, Yangyang and Wu, Chunyang and Wang, Dilin and Xiao, Alex and Mahadeokar, Jay and Zhang, Xiaohui and Liu, Chunxi and Li, Ke and Shangguan, Yuan and Nagaraja, Varun and Kalinli, Ozlem and Seltzer, Mike},
-  booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
-  title={Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution}, 
+  booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  title={Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution},
   year={2022},
   volume={},
   number={},
@@ -441,8 +441,8 @@ @article{coucke2018snips
 }
 @INPROCEEDINGS{9746490,
   author={Srivastava, Sangeeta and Wang, Yun and Tjandra, Andros and Kumar, Anurag and Liu, Chunxi and Singh, Kritika and Saraf, Yatharth},
-  booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
-  title={Conformer-Based Self-Supervised Learning For Non-Speech Audio Tasks}, 
+  booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  title={Conformer-Based Self-Supervised Learning For Non-Speech Audio Tasks},
   year={2022},
   volume={},
   number={},