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
A Blockchain Architecture for Secure, High-Speed P2P Energy Trades with Game-Theoretic Coalition Formation
Amin Aboutalebi Najafabadi - Seyed Hossein Hosseinian
Revolutionizing Credit Scoring: The Synergy of Mamba State Space and CNN Models
Behnam Sabzalian
An efficient hybrid approach for performance-based alternative design evaluation in systems engineering
Abbas Chaman Para - Maryam Nooraei Abadeh - Sondos Bahadori
روشی چندوجهی برای تحلیل احساسات در زبان فارسی با استفاده نشریه ساختار بلاغی و ترنسفرمرها
ریحانه احمدی علیائی - امینه امینی - عباس جلیلوند
Architectural Insights: Comparing Weight Stationary and Output Stationary Systolic Arrays for Efficient Computation
Mahdi Kalbasi
Attention-Enhanced Ensemble Learning for Automated Stenosis Detection in X-ray Coronary Angiography Videos
Marzieh Sadat Hosseini - Ahmad R. Naghsh-Nilchi - Mehran Safayani - Masoumeh Sadeghi
Evaluation of Machine Learning Models in Persian Text Classification for Depression Detection with Improved Feature Selection
Rasool TayebMoghadam - Amirhossein Damia - Hadi Bahrampoor - Maryam Zarghani
Using Deconvolutional Variational Autoencoder for Answer Selection in Community Question Answering
Golshan Afzali Boroujeni - Heshaam Faili
Effective Design of Reversible 2×2 Vedic Multiplier With Low Cost
Mojtaba Noorallahzadeh - Mohammad Mosleh - Ali Shahidikia
ارائه یک سیستم توصیهگر آگاه به زمینه مبتنی بر رفتار کاربر در شبکه اجتماعی با استفاده از پیامهای برچسب شده جغرافیایی
زهرا امینی - سید علیرضا هاشمی گلپایگانی - علی میرزائی
more
Samin Hamayesh - Version 42.5.2