KWDOA: Adapted dataset for detection of the direction of arrival of the keyword

8 pages•Published: January 24, 2024

Abstract

This paper describes a simulated audio dataset of spoken words which accommodate microphone array design for training and evaluating keywords spotting systems. With this dataset you could train a neural network for the detection direction of the speaker. Which is an advanced version of the original, with added noises during a speech in random locations and different rooms with different reverb. Hence it should be closer to real-world long-range applications. This task could be a new challenge for the direction of arrival activated by keyword spotting systems. Let’s call this task KWDOA. This dataset could serve as the intro level for microphone array designs.

Keyphrases: ai, direction of arrival, keyword, kwdoa, speech

In: Krishna Kambhampaty, Gongzhu Hu and Indranil Roy (editors). Proceedings of 36th International Conference on Computer Applications in Industry and Engineering, vol 97, pages 30-37.

Links:	https://easychair.org/publications/paper/vsB3p
	https://doi.org/10.29007/5k86

BibTeX entry

@inproceedings{CAINE2023:KWDOA_Adapted_dataset_detection,
  author    = {David Beneš and Luboš Šmídl},
  title     = {KWDOA: Adapted dataset for detection of the direction of arrival of the keyword},
  booktitle = {Proceedings of 36th International Conference on Computer Applications in Industry and Engineering},
  editor    = {Krishna Kambhampaty and Gongzhu Hu and Indranil Roy},
  series    = {EPiC Series in Computing},
  volume    = {97},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/vsB3p},
  doi       = {10.29007/5k86},
  pages     = {30-37},
  year      = {2024}}

Download PDF Open PDF in browser