Please wait ...
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
Presentation of a New Decoder Based on Quantum Cellular Automata Technology Along with an Analysis of Energy Consumption
- - -
Improving Privacy Protection in a Collaborative Blockchain-based E-Health Records System
Arman Emam-Hoseini - Samane Sobuti - دکتر سیاوش خرسندی - Alireza Hashemi-Golpayeghani
بهبود تشخیص نفوذ به شبکه اینترنت اشیاء با استفاده از مدل ترکیبی الگوریتم های بهینهسازی ازدحام ذرات، گرگ خاکستری و جنگل تصادفی
مهدی علیرضانژاد - عمار عبیس حسین المعموری
Fast Online Character Recognition Using a Novel Local-Global Feature Extraction Method
Ayoub Parvizi - Dr Mohammad Kazemifard - Ziba Imani
Energy-Saving for User-Centric Dynamic 5G HetNets Using DRL Method
Erfan Rasti - Mohammad Ali Arami - Abbas Mohammadi
امنیت در اینترنت اشیا؛ معماری، کاربردها، چالشها و راهکارها
مهدی موسی وند - دکتر پیام محمودی نصر مهدی موسی وند - پیام محمودی نصر -
بهبود معاملات الگوریتمی سهام مبتنی بر رویکرد یادگیری تقویتی
مها العطوان - جعفر پورامینی
Combinatorial Auction Based on Social Choice in the Internet of Things
Maede Esmaeili - Faria Nassiri-Mofakham - Fatemeh Hassanvand
شناسایی حسابهای چندکاربره بر اساس ویژگیهای شخصیتی کاربران در پلتفرمهای پخش فیلم
مهسا رضائی - مرجان کائدی
پیشبینی بستری مجدد بیماران با استفاده از استخراج مفاهیم زیستپزشکی از متون بالینی
فهیمه شاهرخ شهرکی - رسول سامانی - دکتر ناصر قدیری فهیمه شاهرخ شهرکی - رسول سامانی - ناصر قدیری -
more
Samin Hamayesh - Version 45.0.1