Monophone-Based Background Modeling for Two-Stage On-Device Wake Word Detection

Wu, Minhua; Panchapagesan, Sankaran; Sun, Ming; Gu, Jiacheng; Thomas, Ryan; Vitaladevuni, Shiv; Hoffmeister, Björn; Mandal, Arindam

doi:10.1109/icassp.2018.8462227

Cited by 70 publications

(41 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Keyword spotting is the task of detecting a specific word in continuous speech signal. In recent years, keyword spotting gains substantial performance improvements with deep learning algorithms [1,2,3,4,5]. More recently, end-toend trained models have been successfully applied in automatic speech recognition (ASR) [6,7,8,9,10] and KWS [11,12,13,14].…”

Section: Introductionmentioning

confidence: 99%

Improving RNN Transducer Modeling for Small-Footprint Keyword Spotting

Tian

Yao

Cai

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The recurrent neural network transducer (RNN-T) model has been proved effective for keyword spotting (KWS) recently. However, compared with cross-entropy (CE) or connectionist temporal classification (CTC) based models, the additional prediction network in the RNN-T model increases the model size and computational cost. Besides, since the keyword training data usually only contain the keyword sequence, the prediction network might has over-fitting problems. In this paper, we improve the RNN-T modeling for small-footprint keyword spotting in three aspects. First, to address the overfitting issue, we explore multi-task training where a CTC loss is added to the encoder. The CTC loss is calculated with both KWS data and ASR data, while the RNN-T loss is calculated with ASR data so that only the encoder is augmented with KWS data. Second, we use the feed-forward neural network to replace the LSTM for prediction network modeling. Thus all possible prediction network outputs could be pre-computed for decoding. Third, we further improve the model with transfer learning, where a model trained with 160 thousand hours of ASR data is used to initialize the KWS model. On a self-collected far-field wake-word testset, the proposed RNN-T system greatly improves the performance comparing with a strong "keyword-filler" baseline.

show abstract

Section: Introductionmentioning

confidence: 99%

Improving RNN Transducer Modeling for Small-Footprint Keyword Spotting

Tian

Yao

Cai

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Traditional approaches of KWS are based on the keyword/filler Hidden Markov Model (HMM) [4,5], which are trained for both keyword and non-keyword audio segments. Techniques such as attention-based model [6] and time delay neural network [7] have also been explored for better performance.…”

Section: Introductionmentioning

confidence: 99%

RNN-T Based Open-Vocabulary Keyword Spotting in Mandarin with Multi-Level Detection

Liu

Zhang

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Despite the recent prevalence of keyword spotting (KWS) in smart-home, open-vocabulary KWS remains a keen but unmet need among the users. In this paper, we propose an RNN Transducer (RNN-T) based keyword spotting system with a constrained attention mechanism biasing module that biases the RNN-T model towards a specific keyword of interest. The atonal syllables are adopted as the modeling units, which addresses the out-ofvocabulary (OOV) problem. A multi-level detection is applied to the posterior probabilities for the judgement. Evaluating on the AISHELL-2 dataset shows our proposed method outperforms the RNN-T-based approach by 2.70% in false reject rate (FRR) at 1 false alarm (FA) per hour. We further provide insights into the role of each stage of the detection cascade, where most negative samples are filtered out by the first stage with high computational efficiency.

show abstract

“…They range from traditional approaches that make use of a Hidden Markov Model (HMM) to characterize acoustic features from a DNN into both "keyword" and "background" (i.e. nonkeyword speech and noise) classes [1,2,3,4,5]. Simpler derivatives of that approach perform a temporal integration computation that verifies the outputs of the acoustic model are high in the right sequence for the target keyword in order to produce a single detection likelihood score [6,7,8,9,10].…”

Section: Introductionmentioning

confidence: 99%

End-to-end Streaming Keyword Spotting

Álvarez

Park

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We present a system for keyword spotting that, except for a frontend component for feature generation, it is entirely contained in a deep neural network (DNN) model trained "end-to-end" to predict the presence of the keyword in a stream of audio. The main contributions of this work are, first, an efficient memoized neural network topology that aims at making better use of the parameters and associated computations in the DNN by holding a memory of previous activations distributed over the depth of the DNN. The second contribution is a method to train the DNN, end-to-end, to produce the keyword spotting score. This system significantly outperforms previous approaches both in terms of quality of detection as well as size and computation.

show abstract

Monophone-Based Background Modeling for Two-Stage On-Device Wake Word Detection

Cited by 70 publications

References 21 publications

Improving RNN Transducer Modeling for Small-Footprint Keyword Spotting

Improving RNN Transducer Modeling for Small-Footprint Keyword Spotting

RNN-T Based Open-Vocabulary Keyword Spotting in Mandarin with Multi-Level Detection

End-to-end Streaming Keyword Spotting

Contact Info

Product

Resources

About