all AI news
Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
June 5, 2024, 4:52 a.m. | Hao Yen, Pin-Jui Ku, Sabato Marco Siniscalchi, Chin-Hui Lee
cs.CL updates on arXiv.org arxiv.org
Abstract: We propose a novel language-universal approach to end-to-end automatic spoken keyword recognition (SKR) leveraging upon (i) a self-supervised pre-trained model, and (ii) a set of universal speech attributes (manner and place of articulation). Specifically, Wav2Vec2.0 is used to generate robust speech representations, followed by a linear output layer to produce attribute sequences. A non-trainable pronunciation model then maps sequences of attributes into spoken keywords in a multilingual setting. Experiments on the Multilingual Spoken Words Corpus …
abstract arxiv attributes cs.cl cs.sd eess.as generate language modeling multilingual novel pre-trained model recognition robust set speech spoken type universal wav2vec2 zero-shot
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
AI Focused Biochemistry Postdoctoral Fellow
@ Lawrence Berkeley National Lab | Berkeley, CA
Senior Data Engineer
@ Displate | Warsaw
Hybrid Cloud Engineer
@ Vanguard | Wayne, PA
Senior Software Engineer
@ F5 | San Jose
Software Engineer, Backend, 3+ Years of Experience
@ Snap Inc. | Bellevue - 110 110th Ave NE
Global Head of Commercial Data Foundations
@ Sanofi | Cambridge