Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting
Not on the map. Why?
Abstract (arXiv)
In this paper, we present a novel approach to adapt a sequence-to-sequence Transformer-Transducer ASR system to the keyword spotting (KWS) task. We achieve this by replacing the keyword in the text transcription with a special token <kw> and training the system to detect the <kw> token in an audio stream. At inference time, we create a decision function inspired by conventional KWS approaches, to make our approach more suitable for the KWS task. Furthermore, we introduce a specific keyword spotting loss by adapting the sequence-discriminative Minimum Bayes-Risk training technique. We find that our approach significantly outperforms ASR based KWS systems. When compared with a conventional keyword spotting system, our proposal has similar performance while bringing the advantages and flexibility of sequence-to-sequence training. Additionally, when combined with the conventional KWS system, our approach can improve the performance at any operation point.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 11 Nov 2022.
Builds on
16 of 32 references.
References · 16
- 2017Attention Is All You Needcited by 60,361
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
- 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 235
- 2017Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Modelscited by 68
- 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
- 2017Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spottingcited by 32
- 2021Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detectioncited by 32
- 2018End-to-End Streaming Keyword Spottingcited by 25
- 2019Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognitioncited by 23
- 2020Multi-task Language Modeling for Improving Speech Recognition of Rare Wordscited by 21
- 2017End-to-End ASR-free Keyword Search from Speechcited by 19
4 more
- 2017Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Modelscited by 19
- 2017Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spottingcited by 15
- 2020Learning To Detect Keyword Parts And Whole By Smoothed Max Poolingcited by 10
- 2021Meta-Learning for improving rare word recognition in end-to-end ASRcited by 4
Built on by
Citing papers per year: 2023: 2.
2 papers.