Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917572932272128 |
|---|---|
| author | Imamura, Kanami Nakamura, Tomohiko Takamune, Norihiro Yatabe, Kohei Saruwatari, Hiroshi |
| author_facet | Imamura, Kanami Nakamura, Tomohiko Takamune, Norihiro Yatabe, Kohei Saruwatari, Hiroshi |
| contents | In this paper, we propose algorithms for handling non-integer strides in sampling-frequency-independent (SFI) convolutional and transposed convolutional layers. The SFI layers have been developed for handling various sampling frequencies (SFs) by a single neural network. They are replaceable with their non-SFI counterparts and can be introduced into various network architectures. However, they could not handle some specific configurations when combined with non-SFI layers. For example, an SFI extension of Conv-TasNet, a standard audio source separation model, cannot handle some pairs of trained and target SFs because the strides of the SFI layers become non-integers. This problem cannot be solved by simple rounding or signal resampling, resulting in the significant performance degradation. To overcome this problem, we propose algorithms for handling non-integer strides by using windowed sinc interpolation. The proposed algorithms realize the continuous-time representations of features using the interpolation and enable us to sample instants with the desired stride. Experimental results on music source separation showed that the proposed algorithms outperformed the rounding- and signal-resampling-based methods at SFs lower than the trained SF. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_10718 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides Imamura, Kanami Nakamura, Tomohiko Takamune, Norihiro Yatabe, Kohei Saruwatari, Hiroshi Sound Audio and Speech Processing In this paper, we propose algorithms for handling non-integer strides in sampling-frequency-independent (SFI) convolutional and transposed convolutional layers. The SFI layers have been developed for handling various sampling frequencies (SFs) by a single neural network. They are replaceable with their non-SFI counterparts and can be introduced into various network architectures. However, they could not handle some specific configurations when combined with non-SFI layers. For example, an SFI extension of Conv-TasNet, a standard audio source separation model, cannot handle some pairs of trained and target SFs because the strides of the SFI layers become non-integers. This problem cannot be solved by simple rounding or signal resampling, resulting in the significant performance degradation. To overcome this problem, we propose algorithms for handling non-integer strides by using windowed sinc interpolation. The proposed algorithms realize the continuous-time representations of features using the interpolation and enable us to sample instants with the desired stride. Experimental results on music source separation showed that the proposed algorithms outperformed the rounding- and signal-resampling-based methods at SFs lower than the trained SF. |
| title | Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2306.10718 |