Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2017
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908336821108736 |
|---|---|
| author | AbdulKader, Ahmad Nassar, Kareem El-Geish, Mohamed Galvez, Daniel Patil, Chetan |
| author_facet | AbdulKader, Ahmad Nassar, Kareem El-Geish, Mohamed Galvez, Daniel Patil, Chetan |
| contents | We propose using cascaded classifiers for a keyword spotting (KWS) task on narrow-band (NB), 8kHz audio acquired in non-IID environments -- a more challenging task than most state-of-the-art KWS systems face. We present a model that incorporates Deep Neural Networks (DNNs), cascading, multiple-feature representations, and multiple-instance learning. The cascaded classifiers handle the task's class imbalance and reduce power consumption on computationally-constrained devices via early termination. The KWS system achieves a false negative rate of 6% at an hourly false positive rate of 0.75 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1711_08058 |
| institution | arXiv |
| publishDate | 2017 |
| record_format | arxiv |
| spellingShingle | Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio AbdulKader, Ahmad Nassar, Kareem El-Geish, Mohamed Galvez, Daniel Patil, Chetan Machine Learning Computation and Language Sound Audio and Speech Processing We propose using cascaded classifiers for a keyword spotting (KWS) task on narrow-band (NB), 8kHz audio acquired in non-IID environments -- a more challenging task than most state-of-the-art KWS systems face. We present a model that incorporates Deep Neural Networks (DNNs), cascading, multiple-feature representations, and multiple-instance learning. The cascaded classifiers handle the task's class imbalance and reduce power consumption on computationally-constrained devices via early termination. The KWS system achieves a false negative rate of 6% at an hourly false positive rate of 0.75 |
| title | Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio |
| topic | Machine Learning Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/1711.08058 |