Streaming Intended Query Detection using E2E Modeling for Continued Conversation
Not on the map. Why?
Abstract (arXiv)
In voice-enabled applications, a predetermined hotword isusually used to activate a device in order to attend to the query.However, speaking queries followed by a hotword each timeintroduces a cognitive burden in continued conversations. Toavoid repeating a hotword, we propose a streaming end-to-end(E2E) intended query detector that identifies the utterancesdirected towards the device and filters out other utterancesnot directed towards device. The proposed approach incor-porates the intended query detector into the E2E model thatalready folds different components of the speech recognitionpipeline into one neural network.The E2E modeling onspeech decoding and intended query detection also allows us todeclare a quick intended query detection based on early partialrecognition result, which is important to decrease latencyand make the system responsive. We demonstrate that theproposed E2E approach yields a 22% relative improvement onequal error rate (EER) for the detection accuracy and 600 mslatency improvement compared with an independent intendedquery detector. In our experiment, the proposed model detectswhether the user is talking to the device with a 8.7% EERwithin 1.4 seconds of median latency after user starts speaking.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 29 Aug 2022.
Builds on
14 of 25 references.
References · 14
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
- 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 257
- 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
- 2020Hybrid Autoregressive Transducer (hat)cited by 108
- 2016Quasi-Recurrent Neural Networkscited by 87
- 2020FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularizationcited by 69
- 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
- 2019Improving RNN Transducer Modeling for End-to-End Speech Recognitioncited by 68
- 2020On the Comparison of Popular End-to-End Models for Large Scale Speech Recognitioncited by 63
- 2020Towards Fast and Accurate Streaming End-to-End ASRcited by 47
- 2021Tied & Reduced RNN-T Decodercited by 36
- 2020A New Training Pipeline for an Improved Neural Transducercited by 34
Built on by
Citing papers per year: 2023: 2; 2024: 1.
3 papers.