Broadcasted Residual Learning for Efficient Keyword Spotting

Kim, Byeonggeun; Chang, Simyung; Lee, Jin-Kyu; Sung, Dooyong

doi:10.48550/arxiv.2106.04140

Cited by 8 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the kernels from the spatially separable convolution turn into the frequency-side kernel and temporal-side kernels. According to previous studies with the spatially separable convolution in audio fields, the keyword spotting [32] and ASC [11] tasks have been shown to be beneficial in modeling fewer parameters as well as for performance improvements.…”

Section: Feature Map Extractormentioning

confidence: 99%

Instance-level loss based multiple-instance learning framework for acoustic scene classification

Choi¹,

Chang²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

In acoustic scene classification (ASC) task, an acoustic scene consists of diverse attributes and is inferred by identifying combinations of some distinct attributes among them. This study aims to extract and cluster these attributes effectively using a multiple-instance learning (MIL) framework for ASC. MIL, known as one of the weakly supervised learning methods, is a way to extract instances from input data and infer a scene corresponding to the input data with those unlabeled instances. We develop the MIL framework more suitable for ASC systems, adopting instance-level labels and instance-level loss, which are effective in extracting and clustering instances. As a result, the witness rate increases significantly compared to the framework without instance-level loss and labels. Also in several MIL-based ASC systems, the classification accuracy improves by about 5 to 11% than without instance-level loss. In addition, we designed a fully separated convolutional module which is a low-complexity neural network consisting of pointwise, frequency-sided depthwise, and temporal-sided depthwise convolutional filters. Considering both complexity and performance, our proposed system is more practical compared to previous systems on the DCASE 2019 challenge task 1-A leader board. We surpassed the third-place model by achieving a performance of 82.3% with only the model complexity of 417K, which is at least 40 times fewer than other systems.

show abstract

Section: Feature Map Extractormentioning

confidence: 99%

Instance-level loss based multiple-instance learning framework for acoustic scene classification

Choi¹,

Chang²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In trigger words detection, false rejection rate (FRR) and false accepts per hour (FAs) are commonly used as the evaluation metrics [27,28,29,30]. In speech command recognition, accuracy is commonly used for evaluation [31,32,33]. CSKWS can borrow the evaluation metrics from these related tasks.…”

Section: Evaluation Metricsmentioning

confidence: 99%

An Anchor-Free Detector for Continuous Speech Keyword Spotting

Zhao¹,

Tang²,

Yao³

et al. 2022

Interspeech 2022

View full text Add to dashboard Cite

Continuous Speech Keyword Spotting (CSKWS) is a task to detect predefined keywords in a continuous speech. In this paper, we regard CSKWS as a one-dimensional object detection task and propose a novel anchor-free detector, named AF-KWS, to solve the problem. AF-KWS directly regresses the center locations and lengths of the keywords through a single-stage deep neural network. In particular, AF-KWS is tailored for this speech task as we introduce an auxiliary unknown class to exclude other words from non-speech or silent background. We have built two benchmark datasets named LibriTop-20 and continuous meeting analysis keywords (CMAK) dataset for CSKWS. Evaluations on these two datasets show that our proposed AF-KWS outperforms reference schemes by a large margin, and therefore provides a decent baseline for future research.

show abstract

“…In general, KWS systems predetermine target keywords and are directly optimized for selected keywords. Although existing predefined KWS models show high detection performance [1,2,3], the necessity of a large dataset containing target keywords and inflexibility of changing target keywords hinder KWS models from expanding to various applications. When it comes to userdefined KWS, users can customize the target keywords with only a few enrollment samples [4,5,6,7] or in the form of string [8,9].…”

Section: Introductionmentioning

confidence: 99%

Fully Unsupervised Training of Few-shot Keyword Spotting

Lee¹,

Kim²,

Mun³

et al. 2022

Preprint

View full text Add to dashboard Cite

For training a few-shot keyword spotting (FS-KWS) model, a large labeled dataset containing massive target keywords has known to be essential to generalize to arbitrary target keywords with only a few enrollment samples. To alleviate the expensive data collection with labeling, in this paper, we propose a novel FS-KWS system trained only on synthetic data. The proposed system is based on metric learning enabling target keywords to be detected using distance metrics. Exploiting the speech synthesis model that generates speech with pseudo phonemes instead of texts, we easily obtain a large collection of multi-view samples with the same semantics. These samples are sufficient for training, considering metric learning does not intrinsically necessitate labeled data. All of the components in our framework do not require any supervision, making our method unsupervised. Experimental results on real datasets show our proposed method is competitive even without any labeled and real datasets.

show abstract

Broadcasted Residual Learning for Efficient Keyword Spotting

Cited by 8 publications

References 24 publications

Instance-level loss based multiple-instance learning framework for acoustic scene classification

Instance-level loss based multiple-instance learning framework for acoustic scene classification

An Anchor-Free Detector for Continuous Speech Keyword Spotting

Fully Unsupervised Training of Few-shot Keyword Spotting

Contact Info

Product

Resources

About