paper-with-me

홈 › Papers

Learning Efficient Representations for Keyword Spotting with Triplet Loss

2021-01-12 · SPECOM 2021 · Roman Vygon, Nikolay Mikhaylovskiy

In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most no-tably, person reidentification. On the other hand, in the area of speech recognition the metric embeddings generated by the triplet loss are rarely used even for classification problems. We fill this gap showing that a combination of two representation learning techniques: a triplet loss-based embedding and a variant of kNN for classification instead of cross-entropy loss significantly (by 26% to 38%) improves the classification accuracy for convolutional networks on a LibriSpeech-derived LibriWords datasets. To do so, we propose a novel phonetic similarity based triplet mining approach. We also improve the current best published SOTA for Google Speech Commands dataset V1 10+2 -class classification by about 34%, achieving 98.55% accuracy, V2 10+2-class classification by about 20%, achieving 98.37% accuracy, and V2 35-class classification by over 50%, achieving 97.0% accuracy.

📄 PDF Abstract BibTeX arXiv:2101.04792

Code (1)

roman-vygon/triplet_loss_kws 공식 구현 pytorch

Tasks

ClassificationKeyword SpottingRepresentation Learningspeech-recognitionSpeech RecognitionTriplet

Similar Papers 제목 키워드 기반

GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting

2024-10-22 · Pai Zhu, Jacob W. Bartel, Dhruuv Agarwal, Kurt Partridge 외

We propose GE2E-KWS -- a generalized end-to-end training and evaluation framework for customized keyword spotting. Specifically, enrollment utterances are separated and grouped by keywords from the training batch and the…

Keyword SpottingTriplet

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 extractio…

Keyword SpottingTriplet

Relational Proxy Loss for Audio-Text based Keyword Spotting

2024-06-08 · Youngmoon Jung, Seungjin Lee, Joon-Young Yang, Jaeyoung Roh 외

In recent years, there has been an increasing focus on user convenience, leading to increased interest in text-based keyword enrollment systems for keyword spotting (KWS). Since the system utilizes text input during the …

Keyword SpottingMetric LearningTriplet

Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting

2022-06-30 · Hyeon-Kyeong Shin, Hyewon Han, Doyeon Kim, Soo-Whan Chung 외

In this paper, we propose a novel end-to-end user-defined keyword spotting method that utilizes linguistically corresponding patterns between speech and text sequences. Unlike previous approaches requiring speech keyword…

Keyword Spotting

Discriminatory and orthogonal feature learning for noise robust keyword spotting

2022-10-20 · Donghyeon Kim, Kyungdeuk Ko, David K. Han, Hanseok Ko

Keyword Spotting (KWS) is an essential component in a smart device for alerting the system when a user prompts it with a command. As these devices are typically constrained by computational and energy resources, the KWS …

Keyword SpottingTriplet