Saved in:
Bibliographic Details
Main Authors: Ai, Zhiqi, Chen, Zhiyong, Xu, Shugong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.07310
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917690491273216
author Ai, Zhiqi
Chen, Zhiyong
Xu, Shugong
author_facet Ai, Zhiqi
Chen, Zhiyong
Xu, Shugong
contents In this paper, we propose MM-KWS, a novel approach to user-defined keyword spotting leveraging multi-modal enrollments of text and speech templates. Unlike previous methods that focus solely on either text or speech features, MM-KWS extracts phoneme, text, and speech embeddings from both modalities. These embeddings are then compared with the query speech embedding to detect the target keywords. To ensure the applicability of MM-KWS across diverse languages, we utilize a feature extractor incorporating several multilingual pre-trained models. Subsequently, we validate its effectiveness on Mandarin and English tasks. In addition, we have integrated advanced data augmentation tools for hard case mining to enhance MM-KWS in distinguishing confusable words. Experimental results on the LibriPhrase and WenetPhrase datasets demonstrate that MM-KWS outperforms prior methods significantly.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07310
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting
Ai, Zhiqi
Chen, Zhiyong
Xu, Shugong
Audio and Speech Processing
Computation and Language
Sound
In this paper, we propose MM-KWS, a novel approach to user-defined keyword spotting leveraging multi-modal enrollments of text and speech templates. Unlike previous methods that focus solely on either text or speech features, MM-KWS extracts phoneme, text, and speech embeddings from both modalities. These embeddings are then compared with the query speech embedding to detect the target keywords. To ensure the applicability of MM-KWS across diverse languages, we utilize a feature extractor incorporating several multilingual pre-trained models. Subsequently, we validate its effectiveness on Mandarin and English tasks. In addition, we have integrated advanced data augmentation tools for hard case mining to enhance MM-KWS in distinguishing confusable words. Experimental results on the LibriPhrase and WenetPhrase datasets demonstrate that MM-KWS outperforms prior methods significantly.
title MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2406.07310