Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913521137090560 |
|---|---|
| author | Nilsson, Mattias Miccini, Riccardo Laroche, Clément Piechowiak, Tobias Zenke, Friedemann |
| author_facet | Nilsson, Mattias Miccini, Riccardo Laroche, Clément Piechowiak, Tobias Zenke, Friedemann |
| contents | As speech processing systems in mobile and edge devices become more commonplace, the demand for unintrusive speech quality monitoring increases. Deep learning methods provide high-quality estimates of objective and subjective speech quality metrics. However, their significant computational requirements are often prohibitive on resource-constrained devices. To address this issue, we investigated binary activation maps (BAMs) for speech quality prediction on a convolutional architecture based on DNSMOS. We show that the binary activation model with quantization aware training matches the predictive performance of the baseline model. It further allows using other compression techniques. Combined with 8-bit weight quantization, our approach results in a 25-fold memory reduction during inference, while replacing almost all dot products with summations. Our findings show a path toward substantial resource savings by supporting mixed-precision binary multiplication in hard- and software. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04578 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps Nilsson, Mattias Miccini, Riccardo Laroche, Clément Piechowiak, Tobias Zenke, Friedemann Sound Neural and Evolutionary Computing Audio and Speech Processing As speech processing systems in mobile and edge devices become more commonplace, the demand for unintrusive speech quality monitoring increases. Deep learning methods provide high-quality estimates of objective and subjective speech quality metrics. However, their significant computational requirements are often prohibitive on resource-constrained devices. To address this issue, we investigated binary activation maps (BAMs) for speech quality prediction on a convolutional architecture based on DNSMOS. We show that the binary activation model with quantization aware training matches the predictive performance of the baseline model. It further allows using other compression techniques. Combined with 8-bit weight quantization, our approach results in a 25-fold memory reduction during inference, while replacing almost all dot products with summations. Our findings show a path toward substantial resource savings by supporting mixed-precision binary multiplication in hard- and software. |
| title | Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps |
| topic | Sound Neural and Evolutionary Computing Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.04578 |