0% Complete
English
صفحه اصلی
/
پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Embedded speech encoder for low-resource languages
نویسندگان :
Alireza A.Tabatabaei
1
Pouria Sameti
2
Ali Bohlooli
3
1- University of Isfahan
2- University of Isfahan
3- University of Isfahan
کلمات کلیدی :
Embedded Systems،Embedded AI،Embedded Speech embedding
چکیده :
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.
لیست مقالات
لیست مقالات بایگانی شده
شناسایی حملات فیشینگ با استفاده از الگوریتم عقاب آتشین و شبکه عصبی کانولوشن
علی کوشاری - مهدی فرتاش
Target-driven Navigation of a Mobile Robot using an End-to-end Deep Learning Approach
Mohammad Matin Hosni - Ali Kheiri - Esmaeil Najafi
A Community-Based Method for Identifying Influential Nodes using Network Embedding
Nargess Vafaei - Dr Mohammad Reza Keyvanpour
Evaluating LLMs in Persian News Summarization
Arya VarastehNezhad - Reza Tavasoli - Mostafa Masumi - Seyed Soroush Majd - Mehrnoush Shamsfard
یک روش انتخاب ویژگی نیمهنظارتی جدید بر اساس منظمسازی هسین
دکتر راضیه شیخ پور راضیه شیخ پور -
انتخاب ویژگی با استفاده از الگوریتم بهینه سازی ذرات مبتنی بر استراتژی خود تطبیقی دودویی جهت تشخیص بیماری
الهام صالحی - دکتر محمدرضا کرمی ملایی - دکتر حسام عمرانپور الهام صالحی - محمدرضا کرمی ملایی - حسام عمرانپور -
Improving Deep Neural Network Accelerator for Malaria Diseased Blood Cells using FPGA
Hadi Rezaeikarjani - Mojtaba Valinataj
قطعه بندی خودکار توده کلیه در تصاویر توموگرافی کامپیوتری با استفاده از همافزایی شبکه عصبی عمیق U-Net و الگوریتم فراابتکاری نهنگ
علی خلیلی - محمد مصلح - محمد خیراندیش
نقشه های شناختی فازی پیشرفته (FCM) رویکردی برای مدل سازی سیستم های پیچیده ی پویا
فریبا اسلامی امیرآبادی - کمال میرزایی بدرآبادی
Effective Classifier for Predicting Churn in Payment Terminals Using RFM model and Deep Neural Network
Dr Mahila Dadfarnia - Ali Alemi Matinpour - Dr Monireh Abdoos
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.2