0% Complete
فارسی
Home
/
پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Embedded speech encoder for low-resource languages
Authors :
Alireza A.Tabatabaei
1
Pouria Sameti
2
Ali Bohlooli
3
1- University of Isfahan
2- University of Isfahan
3- University of Isfahan
Keywords :
Embedded Systems،Embedded AI،Embedded Speech embedding
Abstract :
Although high-performance artificial intelligence (AI) models require substantial computational resources, embedded systems are constrained by limited hardware capabilities, such as memory and processing power. On the other hand, embedded systems have a broad range of applications, making the integration of AI and embedded systems a prominent topic in both hardware and AI research. Creating powerful speech embeddings for embedded systems is challenging, as such models, like Wave2Vec, are typically computationally intensive. Additionally, the scarcity of data for many low-resource languages further complicates the development of high-performance models. To address these challenges, we utilized BERT to generate speech embeddings. BERT was selected because, in addition to producing meaningful embeddings, it is trained on numerous low-resource languages and facilitates the design of efficient decoders. This study introduces a compact speech encoder tailored for low-resource languages, capable of functioning as an encoder across a diverse range of speech tasks. To achieve this, we utilized BERT to generate meaningful embeddings. However, due to the high dimensionality of BERT embeddings, which imposes significant computational demands on many embedded systems, we applied dimensionality reduction techniques. The reduced-dimensional vectors were subsequently used as labels for speech data to train a model composed of convolutional neural networks (CNNs) and fully connected layers. Finally, we demonstrated the encoder's effectiveness through an application in speech command recognition.
Papers List
List of archived papers
بکارگیری الگوریتم بهینه سازی فاخته و منطق فازی به منظور بهبود زمانبندی وظایف در محیط محاسبات مه
فاطمه دوامی - حمید جلیلوند - فاطمه نجفی
Optimal selection of seed nodes by reducing the influence of common nodes in the influence maximization problem
Farzaneh Kazemzadeh - Ali Asghar Safaei - Mitra Mirzarezaee
AI-Driven Approach to Detect Equivalent Elements within Domain Models
Mohammad-Sajad Kasaei - Mohammadreza Sharbaf - Afsaneh Fatemi - Bahman Zamani
کشف برخط تقلب پیشنهاد ساختگی (Bid-Shielding) در مناقصه و مزایدههای الکترونیکی هلندی با رویکرد تحلیل شبکه اجتماعی
فاطمه الثلایا - دکتر سید علیرضا هاشمی گلپایگانی فاطمه الثلایا - سید علیرضا هاشمی گلپایگانی -
An Eco-Friendly Cosmopolitan (EFC) by Recycling Scientific/Industrial Towns (RSITs)
Engineer Reza Khalilian - Dr. Abdalhossein Rezai - Dr. Mohammadreza Talakesh
IoT-Driven Water Quality Management System using Deep Q-Network
Shakiba Rajabi - Komeil Moghaddasi
KGLM-QA: A Novel Approach for Knowledge Graph-Enhanced Large Language Models for Question Answering
Alireza Akhavan safaei - Pegah Saboori - Reza Ramezani - Mohammadali Nematbakhsh
Improving Long-Term Engagement of Insurance Brokerages by Providing Gamified Configurations Based on The Delphi Method
Hosein Bayati - Fattaneh Taghiyareh - Sahand Hashemi
شناسایی جایگاه مالونیلاسیون در پروتئینها با بهرهگیری از استخراج ویژگی و تکنیکهای پردازش زبان طبیعی
حنانه رجبیون - محمد قاسم زاده - وحید رنجبر بافقی
User Preferences Elicitation in Bilateral Automated Negotiation Using Recursive Least Square Estimation
Farnaz Salmanian - Dr Hamid Jazayeri - Dr Javad Kazemitabar
more
Samin Hamayesh - Version 42.5.2