paper-with-me

홈 › Papers

Keyword Transformer: A Self-Attention Model for Keyword Spotting

2021-04-01 · Axel Berg, Mark O'Connor, Miguel Tairum Cruz

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or recurrent encoders. We investigate a range of ways to adapt the Transformer architecture to keyword spotting and introduce the Keyword Transformer (KWT), a fully self-attentional architecture that exceeds state-of-the-art performance across multiple tasks without any pre-training or additional data. Surprisingly, this simple architecture outperforms more complex models that mix convolutional, recurrent and attentive layers. KWT can be used as a drop-in replacement for these models, setting two new benchmark records on the Google Speech Commands dataset with 98.6% and 97.7% accuracy on the 12 and 35-command tasks respectively.

📄 PDF Abstract BibTeX arXiv:2104.00769

Code (10)

ARM-software/keyword-transformer 공식 구현 tf
Arizona-Voice/Arizona-spotting pytorch
EscVM/EscVM_YT/blob/master/Notebooks/1%20-%20TF2.X%20DeepAI-Quickie/tf_2_keyword_transformer.ipynb tf
ID56/Torch-KWT pytorch
KrishnaDN/Keyword-Transformer
aau-es-ml/ssl_noise-robust_kws pytorch
holgerbovbjerg/data2vec-kws pytorch
intelligentmachines/keyword_spotting_transformer tf
mashrurmorshed/torch-kwt pytorch
phanxuanphucnd/Arizona-spotting

Tasks

Keyword SpottingSpeech Recognition

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Attention-Free Keyword Spotting

2021-10-14 · Mashrur M. Morshed, Ahmad Omar Ahsan

Till now, attention-based models have been used with great success in the keyword spotting problem domain. However, in light of recent advances in deep learning, the question arises whether self-attention is truly irrepl…

Keyword Spotting

Visual Keyword Spotting with Attention

2021-10-29 · K R Prajwal, Liliane Momeni, Triantafyllos Afouras, Andrew Zisserman

In this paper, we consider the task of spotting spoken keywords in silent video sequences -- also known as visual keyword spotting. To this end, we investigate Transformer-based models that ingest two streams, a visual e…

Lip ReadingVisual Keyword Spotting

Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings

2025-06-21 · Julian Herreilers, Christiaan Jacobs, Thomas Niesler

We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWEs) for the purpose of very low-resource keyword spotting. The ContrastiveTransformer, an encoder-only model, directly op…

Keyword SpottingWord Embeddings

Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention

2022-03-20 · Zuzana Jelčicová, Marian Verhelst

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. W…

Keyword Spotting

QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer

2022-06-23 · Jinmiao Huang, Waseem Gharbieh, Qianhui Wan, Han Suk Shim 외

Current keyword spotting systems are typically trained with a large amount of pre-defined keywords. Recognizing keywords in an open-vocabulary setting is essential for personalizing smart device interaction. Towards this…

Keyword Spotting