nateanl
nateanl
For clarification, there is no `use_fft` argument in `reverberate` method, and `use_fft` is always True when computing `convolve1d`. So there is no issue when calling the method. That being said,...
According to `torch.linalg.lstsq`'s doc page, it mentioned: ``` This function computes X = A.pinverse() @ B in a faster and more numerically stable way than performing the computations separately. ```...
The issue of `torch.linalg.lstsq` is that there is no non-negative constraint, hence the generated spectrogram is not global optimal. The best solution should be implementing `L-BFGS-B` optimizer in PyTorch, which...
cc @fakufaku @mravanelli @sw005320
Thanks all for the discussions. - RE: Option1 & Option 2 Regarding the options for materials, it seems better to to use `float` or `Tensor` in the core API, which...
To support differentiability, the output shape needs to be stable. However, `room`, `mic_array`, `source`, and `max_order` all can affect the length of the RIR signal. To solve this issue, I...
Doc page: https://output.circle-artifacts.com/output/job/a26503b3-98a5-4272-8add-cacb33932fef/artifacts/0/docs/prototype.functional.html#simulate-rir-ism
ffprobe shows ``` Input #0, flac, from '5350-205002-0014.flac': Duration: 00:00:12.14, start: 0.000000, bitrate: 153 kb/s Stream #0:0: Audio: flac, 16000 Hz, mono, s16 ``` soxi shows: ``` Input File :...
hmm, it doesn't output the exact frame count: ``` ffprobe version 4.2.2 Copyright (c) 2007-2019 the FFmpeg developers built with clang version 4.0.1 (tags/RELEASE_401/final) configuration: --prefix=/miniconda3/envs/torch --cc=x86_64-apple-darwin13.4.0-clang --disable-doc --enable-avresample --enable-gmp...