Vocal Tract Length Warped Features for Spoken Keyword Spotting
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912179167428608 |
|---|---|
| author | Sarkar, Achintya kr. Dwivedi, Priyanka Tan, Zheng-Hua |
| author_facet | Sarkar, Achintya kr. Dwivedi, Priyanka Tan, Zheng-Hua |
| contents | In this paper, we propose several methods that incorporate vocal tract length (VTL) warped features for spoken keyword spotting (KWS). The first method, VTL-independent KWS, involves training a single deep neural network (DNN) that utilizes VTL features with various warping factors. During training, a specific VTL feature is randomly selected per epoch, allowing the exploration of VTL variations. During testing, the VTL features with different warping factors of a test utterance are scored against the DNN and combined with equal weight. In the second method scores the conventional features of a test utterance (without VTL warping) against the DNN. The third method, VTL-concatenation KWS, concatenates VTL warped features to form high-dimensional features for KWS. Evaluations carried out on the English Google Command dataset demonstrate that the proposed methods improve the accuracy of KWS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03523 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Vocal Tract Length Warped Features for Spoken Keyword Spotting Sarkar, Achintya kr. Dwivedi, Priyanka Tan, Zheng-Hua Sound Artificial Intelligence Machine Learning Audio and Speech Processing In this paper, we propose several methods that incorporate vocal tract length (VTL) warped features for spoken keyword spotting (KWS). The first method, VTL-independent KWS, involves training a single deep neural network (DNN) that utilizes VTL features with various warping factors. During training, a specific VTL feature is randomly selected per epoch, allowing the exploration of VTL variations. During testing, the VTL features with different warping factors of a test utterance are scored against the DNN and combined with equal weight. In the second method scores the conventional features of a test utterance (without VTL warping) against the DNN. The third method, VTL-concatenation KWS, concatenates VTL warped features to form high-dimensional features for KWS. Evaluations carried out on the English Google Command dataset demonstrate that the proposed methods improve the accuracy of KWS. |
| title | Vocal Tract Length Warped Features for Spoken Keyword Spotting |
| topic | Sound Artificial Intelligence Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.03523 |