Sang-Hoon Lee

About audio quality evaluation

3

## ❓ Questions Thank you for nice work. I have some question about objective evaluation metrics. 1. Are these metrics (SI-SNR and ViSQOL) consistent with audio quality perceptually? I know...

@Vaibhavs10 Thanks for sharing our work! We have changed the license to MIT License. (So please change our license information in ReadMe.MD!) Now, you can use for commercial product. Please...

[Inconsistency with paper] I reproduced audio signal by RELU + MLP.

1

To compare SIREN layer with RELU +MLP, we implement two models. 1. audio signal (B, T, 1) --> Linear(B, T, 128) +RELU --> Linear(B, T, 128) +RELU --> Linear(B, T,...

@hubertsiuzdak Thanks for nice work! I have a question about the VISQOL. For the evaluation, you utilized an audio mode of VISQOL. However, input waveform should be a 48kHz sampling...

UTMOSv2 was released

2

Hi @tarepan Thanks for your simple implementation again. Today, UTMOSv2 was released. https://github.com/sarulab-speech/UTMOSv2 Could you integrate UTMOSv2 with HuggingFace Hub like SpeechMOS?

About the STFT Loss

2

Hi Thanks for nice work! I have a question about the STFT Loss. Previously, I have tried to directly adopt the STFT loss on the estimated vector field, and this...