# Neural Network based End-to-End Query by Example Spoken Term Detection

arXiv: https://arxiv.org/abs/1911.08332 · HTML: https://mlsanity.com/paper/1911.08332/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering](https://mlsanity.com/paper/2401.13463/) (2024)
- [Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages](https://mlsanity.com/paper/2103.14583/) (2021)
- [Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili](https://mlsanity.com/paper/2306.00410/) (2023)
- [NUVA: A Naming Utterance Verifier for Aphasia Treatment](https://mlsanity.com/paper/2102.05408/) (2021)
- [BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection](https://mlsanity.com/paper/2411.14100/) (2024)
- [End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations](https://mlsanity.com/paper/2308.08027/) (2023)
- [Written Term Detection Improves Spoken Term Detection](https://mlsanity.com/paper/2407.04601/) (2024)
- [Cross-Lingual Query-by-Example Spoken Term Detection: A Transformer-Based Approach](https://mlsanity.com/paper/2410.04091/) (2024)

## Abstract (arXiv)

This paper focuses on the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. State-of-the-art approaches primarily rely on dynamic time warping (DTW) based template matching techniques using phone posterior or bottleneck features extracted from a deep neural network (DNN). We use both monolingual and multilingual bottleneck features, and show that multilingual features perform increasingly better with more training languages. Previously, it has been shown that the DTW based matching can be replaced with a CNN based matching while using posterior features. Here, we show that the CNN based matching outperforms DTW based matching using bottleneck features as well. In this case, the feature extraction and pattern matching stages of our QbE-STD system are optimized independently of each other. We propose to integrate these two stages in a fully neural network based end-to-end learning framework to enable joint optimization of those two stages simultaneously. The proposed approaches are evaluated on two challenging multilingual datasets: Spoken Web Search 2013 and Query by Example Search on Speech Task 2014, demonstrating in each case significant improvements.