paper-with-me

Papers

Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss

2021-02-14 · Jinmiao Huang, Waseem Gharbieh, Han Suk Shim, Eugene Kim

This paper proposes a neural network architecture for tackling the query-by-example user-defined keyword spotting task. A multi-head attention module is added on top of a multi-layered GRU for effective feature extraction, and a normalized multi-head attention module is proposed for feature aggregation. We also adopt the softtriple loss - a combination of triplet loss and softmax loss - and showcase its effectiveness. We demonstrate the performance of our model on internal datasets with different languages and the public Hey-Snips dataset. We compare the performance of our model to a baseline system and conduct an ablation study to show the benefit of each component in our architecture. The proposed work shows solid performance while preserving simplicity.

📄 PDF Abstract BibTeX arXiv:2102.07061

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword SpottingTriplet

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…
Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping

2023-04-19 · Paul M. Reuter, Christian Rollwage, Bernd T. Meyer

In this paper, we propose a multilingual query-by-example keyword spotting (KWS) system based on a residual neural network. The model is trained as a classifier on a multilingual keyword dataset extracted from Common Voi…

Keyword SpottingMetric LearningWord Embeddings

DONUT: CTC-based Query-by-Example Keyword Spotting

2018-10-22 · NIPS Workshop IRASL 2018 · Anonymous

Keyword spotting—or wakeword detection—is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might want to choose a personalized custom wakeword…

Keyword Spotting

DONUT: CTC-based Query-by-Example Keyword Spotting

2018-11-26 · Loren Lugosch, Samuel Myer, Vikrant Singh Tomar

Keyword spotting--or wakeword detection--is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might want to choose a personalized custom wakewo…

Keyword Spotting

Query-by-example on-device keyword spotting

2019-10-11 · Byeonggeun Kim, Mingu Lee, Jinkyu Lee, Yeonseok Kim 외

A keyword spotting (KWS) system determines the existence of, usually predefined, keyword in a continuous speech stream. This paper presents a query-by-example on-device KWS system which is user-specific. The proposed sys…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Keyword Spottingspeech-recognition+1

Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning

2024-08-27 · Zhenyu Wang, Shuyu Kong, Li Wan, Biqiao Zhang 외

Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions with intelligent devices. In this paper, w…

Keyword SpottingMulti-Task Learning