# CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting

arXiv: https://arxiv.org/abs/2406.07923 · HTML: https://mlsanity.com/paper/2406.07923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Multi-view Recurrent Neural Acoustic Word Embeddings](https://mlsanity.com/paper/1611.04496/) (2016)
- [DONUT: CTC-based Query-by-Example Keyword Spotting](https://mlsanity.com/paper/1811.10736/) (2018)
- [Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding](https://mlsanity.com/paper/2308.06472/) (2023)

## Abstract (arXiv)

This paper introduces a novel approach for streaming openvocabulary keyword spotting (KWS) with text-based keyword enrollment. For every input frame, the proposed method finds the optimal alignment ending at the frame using connectionist temporal classification (CTC) and aggregates the frame-level acoustic embedding (AE) to obtain higher-level (i.e., character, word, or phrase) AE that aligns with the text embedding (TE) of the target keyword text. After that, we calculate the similarity of the aggregated AE and the TE. To the best of our knowledge, this is the first attempt to dynamically align the audio and the keyword text on-the-fly to attain the joint audio-text embedding for KWS. Despite operating in a streaming fashion, our approach achieves competitive performance on the LibriPhrase dataset compared to the non-streaming methods with a mere 155K model parameters and a decoding algorithm with time complexity O(U), where U is the length of the target keyword at inference time.