# Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition

arXiv: https://arxiv.org/abs/2304.01905 · HTML: https://mlsanity.com/paper/2304.01905/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 3 Apr 2023.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Efficient Content-Based Sparse Attention with Routing Transformers](https://mlsanity.com/paper/2003.05997/) (2020)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [LSTM: A Search Space Odyssey](https://mlsanity.com/paper/1503.04069/) (2015)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Transformer-Transducer: End-to-End Speech Recognition with Self-Attention](https://mlsanity.com/paper/1910.12977/) (2019)
- [A Better and Faster End-to-End Model for Streaming ASR](https://mlsanity.com/paper/2011.10798/) (2020)
- [Simple Recurrent Units for Highly Parallelizable Recurrence](https://mlsanity.com/paper/1709.02755/) (2017)
- [Contextual Adapters for Personalized Speech Recognition in Neural Transducers](https://mlsanity.com/paper/2205.13660/) (2022)
- [Context-Aware Transformer Transducer for Speech Recognition](https://mlsanity.com/paper/2111.03250/) (2021)
- [A Regularized Framework for Sparse and Structured Neural Attention](https://mlsanity.com/paper/1705.07704/) (2017)
- [Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1610.09975/) (2016)
- [Personalization Strategies for End-to-End Speech Recognition Systems](https://mlsanity.com/paper/2102.07739/) (2021)
- [Self-Attention Transducers for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.13037/) (2019)
- [No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models](https://mlsanity.com/paper/1712.01864/) (2017)
- [Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency](https://mlsanity.com/paper/2104.02176/) (2021)
- [Amortized Neural Networks for Low-Latency Speech Recognition](https://mlsanity.com/paper/2108.01553/) (2021)
- [ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition](https://mlsanity.com/paper/2209.14868/) (2022)
- [Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization](https://mlsanity.com/paper/2108.01704/) (2021)
- [Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models](https://mlsanity.com/paper/2106.06126/) (2021)
- [Compute Cost Amortized Transformer for Streaming ASR](https://mlsanity.com/paper/2207.02393/) (2022)

## Built on by (most cited first, 2 of 2)

- [Enhancing Voice Wake-Up for Dysarthria: Mandarin Dysarthria Speech Corpus Release and Customized System Design](https://mlsanity.com/paper/2406.10304/) (2024)
- [Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval](https://mlsanity.com/paper/2411.00664/) (2024)

## Abstract (arXiv)

We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks. This architecture enables a dynamic switch for its runtime compute paths by exploiting WW spotting to select which branch of its attention networks to execute for an input audio frame. With this approach, we effectively improve WW spotting accuracy while saving runtime compute cost as defined by floating point operations (FLOPs). Using an in-house de-identified dataset, we demonstrate that the proposed dual-attention network can reduce the compute cost by 90% for WW audio frames, with only 1% increase in the number of parameters. This architecture improves WW F1 score by 16% relative and improves generic rare word error rate by 3% relative compared to the baselines.