# End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations

arXiv: https://arxiv.org/abs/2308.08027 · HTML: https://mlsanity.com/paper/2308.08027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 94 references that are in the map.
- First posted on arXiv 15 Aug 2023.

## Builds on (most cited first, 25 of 25)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [Self-Training for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.09116/) (2019)
- [MAESTRO: Matched Speech Text Representations through Modality Matching](https://mlsanity.com/paper/2204.03409/) (2022)
- [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://mlsanity.com/paper/2107.05782/) (2021)
- [Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems](https://mlsanity.com/paper/1912.09257/) (2019)
- [Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training](https://mlsanity.com/paper/2011.13439/) (2020)
- [Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models](https://mlsanity.com/paper/2202.13155/) (2022)
- [Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems](https://mlsanity.com/paper/2203.00006/) (2022)
- [End-to-End ASR-free Keyword Search from Speech](https://mlsanity.com/paper/1701.04313/) (2017)
- [Multitask Training with Text Data for End-to-End Speech Recognition](https://mlsanity.com/paper/2010.14318/) (2020)
- [Multi-Modal Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/1803.10299/) (2018)
- [A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning](https://mlsanity.com/paper/2006.02547/) (2020)
- [EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition](https://mlsanity.com/paper/2104.07474/) (2021)
- [Predicting detection filters for small footprint open-vocabulary keyword spotting](https://mlsanity.com/paper/1912.07575/) (2019)
- [SpeechYOLO: Detection and Localization of Speech Objects](https://mlsanity.com/paper/1904.07704/) (2019)
- [Neural Network based End-to-End Query by Example Spoken Term Detection](https://mlsanity.com/paper/1911.08332/) (2019)
- [USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder](https://mlsanity.com/paper/2202.06045/) (2022)
- [CNN-based Spoken Term Detection and Localization without Dynamic Programming](https://mlsanity.com/paper/2103.05468/) (2021)
- [End-to-End Open Vocabulary Keyword Search](https://mlsanity.com/paper/2108.10357/) (2021)
- [Spoken Term Detection and Relevance Score Estimation using Dot-Product of Pronunciation Embeddings](https://mlsanity.com/paper/2210.11895/) (2022)
- [Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer](https://mlsanity.com/paper/2210.11885/) (2022)

## Abstract (arXiv)

Conventional keyword search systems operate on automatic speech recognition (ASR) outputs, which causes them to have a complex indexing and search pipeline. This has led to interest in ASR-free approaches to simplify the search procedure. We recently proposed a neural ASR-free keyword search model which achieves competitive performance while maintaining an efficient and simplified pipeline, where queries and documents are encoded with a pair of recurrent neural network encoders and the encodings are combined with a dot-product. In this article, we extend this work with multilingual pretraining and detailed analysis of the model. Our experiments show that the proposed multilingual training significantly improves the model performance and that despite not matching a strong ASR-based conventional keyword search system for short queries and queries comprising in-vocabulary words, the proposed model outperforms the ASR-based system for long queries and queries that do not appear in the training data.