Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Singh, Anup, Arora, Vipul, Demuynck, Kris
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.16395
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917278623203328
author Singh, Anup
Arora, Vipul
Demuynck, Kris
author_facet Singh, Anup
Arora, Vipul
Demuynck, Kris
contents Fast and accurate spoken content retrieval is vital for applications such as voice search. Query-by-Example Spoken Term Detection (STD) involves retrieving matching segments from an audio database given a spoken query. Token-based STD systems, which use discrete speech representations, enable efficient search but struggle with robustness to noise and reverberation, and with inefficient token utilization. We address these challenges by proposing a noise and reverberation-augmented training strategy to improve tokenizer robustness. In addition, we introduce optimal transport-based regularization to ensure balanced token usage and enhance token efficiency. To further speed up retrieval, we adopt a TF-IDF-based search mechanism. Empirical evaluations demonstrate that the proposed method outperforms STD baselines across various distortion levels while maintaining high search efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BEST-STD2.0: Balanced and Efficient Speech Tokenizer for Spoken Term Detection
Singh, Anup
Arora, Vipul
Demuynck, Kris
Audio and Speech Processing
Fast and accurate spoken content retrieval is vital for applications such as voice search. Query-by-Example Spoken Term Detection (STD) involves retrieving matching segments from an audio database given a spoken query. Token-based STD systems, which use discrete speech representations, enable efficient search but struggle with robustness to noise and reverberation, and with inefficient token utilization. We address these challenges by proposing a noise and reverberation-augmented training strategy to improve tokenizer robustness. In addition, we introduce optimal transport-based regularization to ensure balanced token usage and enhance token efficiency. To further speed up retrieval, we adopt a TF-IDF-based search mechanism. Empirical evaluations demonstrate that the proposed method outperforms STD baselines across various distortion levels while maintaining high search efficiency.
title BEST-STD2.0: Balanced and Efficient Speech Tokenizer for Spoken Term Detection
topic Audio and Speech Processing
url https://arxiv.org/abs/2512.16395