# Written Term Detection Improves Spoken Term Detection

arXiv: https://arxiv.org/abs/2407.04601 · HTML: https://mlsanity.com/paper/2407.04601/

## 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 5 Jul 2024.

## 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)

End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of training and indexing complexity when compared to approaches which use the output of automatic speech recognition (ASR) systems. This simplification however has drawbacks due to the loss of modularity. In particular, where ASR-based KWS systems can benefit from external unpaired text via a language model, current formulations of E2E KWS systems have no such mechanism. Therefore, in this paper, we propose a multitask training objective which allows unpaired text to be integrated into E2E KWS without complicating indexing and search. In addition to training an E2E KWS model to retrieve text queries from spoken documents, we jointly train it to retrieve text queries from masked written documents. We show empirically that this approach can effectively leverage unpaired text for KWS, with significant improvements in search performance across a wide variety of languages. We conduct analysis which indicates that these improvements are achieved because the proposed method improves document representations for words in the unpaired text. Finally, we show that the proposed method can be used for domain adaptation in settings where in-domain paired data is scarce or nonexistent.