paper-with-me

홈 › Papers

Few-Shot Keyword Spotting in Any Language

2021-04-03 · Mark Mazumder, Colby Banbury, Josh Meyer, Pete Warden, Vijay Janapa Reddi

We introduce a few-shot transfer learning method for keyword spotting in any language. Leveraging open speech corpora in nine languages, we automate the extraction of a large multilingual keyword bank and use it to train an embedding model. With just five training examples, we fine-tune the embedding model for keyword spotting and achieve an average F1 score of 0.75 on keyword classification for 180 new keywords unseen by the embedding model in these nine languages. This embedding model also generalizes to new languages. We achieve an average F1 score of 0.65 on 5-shot models for 260 keywords sampled across 13 new languages unseen by the embedding model. We investigate streaming accuracy for our 5-shot models in two contexts: keyword spotting and keyword search. Across 440 keywords in 22 languages, we achieve an average streaming keyword spotting accuracy of 87.4% with a false acceptance rate of 4.3%, and observe promising initial results on keyword search.

📄 PDF Abstract BibTeX arXiv:2104.01454

Code (2)

harvard-edge/multilingual_kws 공식 구현 tf
harvard-edge/dataperf-speech-example tf

Tasks

Keyword SpottingTransfer Learning

Similar Papers 제목 키워드 기반

Few-Shot Keyword Spotting With Prototypical Networks

2020-07-25 · arXiv 2020 6 · Archit Parnami, Minwoo Lee

Recognizing a particular command or a keyword, keyword spotting has been widely used in many voice interfaces such as Amazon's Alexa and Google Home. In order to recognize a set of keywords, most of the recent deep learn…

Keyword SpottingMetric Learning

Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting

2022-06-28 · Byeonggeun Kim, Seunghan Yang, Inseop Chung, Simyung Chang

Keyword spotting is the task of detecting a keyword in streaming audio. Conventional keyword spotting targets predefined keywords classification, but there is growing attention in few-shot (query-by-example) keyword spot…

Keyword SpottingMetric LearningOpen Set Learning

PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords

2023-08-31 · Yong-Hyeok Lee, Namhyun Cho

This study presents a novel zero-shot user-defined keyword spotting model that utilizes the audio-phoneme relationship of the keyword to improve performance. Unlike the previous approach that estimates at utterance level…

Keyword Spotting

Text-Aware Adapter for Few-Shot Keyword Spotting

2024-12-24 · Youngmoon Jung, Jinyoung Lee, Seungjin Lee, Myunghun Jung 외

Recent advances in flexible keyword spotting (KWS) with text enrollment allow users to personalize keywords without uttering them during enrollment. However, there is still room for improvement in target keyword performa…

Keyword SpottingTransfer Learning

Seeing wake words: Audio-visual Keyword Spotting

2020-09-02 · Liliane Momeni, Triantafyllos Afouras, Themos Stafylakis, Samuel Albanie 외

The goal of this work is to automatically determine whether and when a word of interest is spoken by a talking face, with or without the audio. We propose a zero-shot method suitable for in the wild videos. Our key contr…

Keyword SpottingLip ReadingVisual Keyword Spotting