torchaudio.functional.rtf_evd¶
- torchaudio.functional.rtf_evd(psd_s: Tensor) Tensor[source]¶
Estimate the relative transfer function (RTF) or the steering vector by eigenvalue decomposition.
- Parameters:
psd_s (Tensor) – The complex-valued power spectral density (PSD) matrix of target speech. Tensor of dimension (…, freq, channel, channel)
- Returns:
The estimated complex-valued RTF of target speech. Tensor of dimension (…, freq, channel)
- Return type:
Tensor
- Tutorials using
rtf_evd:
