دانلود رایگان مقاله انگلیسی ارزیابی معماری یادگیری عمیق برای تشخیص گفتار احساسی - الزویر 2017

عنوان فارسی
ارزیابی معماری یادگیری عمیق برای تشخیص گفتار احساسی
عنوان انگلیسی
Evaluating deep learning architectures for Speech Emotion Recognition
صفحات مقاله فارسی
0
صفحات مقاله انگلیسی
9
سال انتشار
2017
نشریه
الزویر - Elsevier
فرمت مقاله انگلیسی
PDF
نوع مقاله
ISI
نوع نگارش
مقالات پژوهشی (تحقیقاتی)
رفرنس
دارد
پایگاه
اسکوپوس
کد محصول
E10738
رشته های مرتبط با این مقاله
مهندسی کامپیوتر، فناوری اطلاعات
گرایش های مرتبط با این مقاله
هوش مصنوعی، شبکه های کامپیوتری
مجله
شبکه های عصبی - Neural Networks
دانشگاه
School of Engineering - RMIT University - Melbourne VIC - Australia
کلمات کلیدی
محاسبات عاطفی، یادگیری عمیق، شناخت احساسی، شبکه های عصبی، تشخیص گفتار
doi یا شناسه دیجیتال
http://dx.doi.org/10.1016/j.neunet.2017.02.013
چکیده

abstract


Speech Emotion Recognition (SER) can be regarded as a static or dynamic classification problem, which makes SER an excellent test bed for investigating and comparing various deep learning architectures. We describe a frame-based formulation to SER that relies on minimal speech processing and end-to-end deep learning to model intra-utterance dynamics. We use the proposed SER system to empirically explore feed-forward and recurrent neural network architectures and their variants. Experiments conducted illuminate the advantages and limitations of these architectures in paralinguistic speech recognition and emotion recognition in particular. As a result of our exploration, we report state-of-the-art results on the IEMOCAP database for speaker-independent SER and present quantitative and qualitative assessments of the models’ performances.

نتیجه گیری

Conclusion


Various deep learning architectures were explored on a Speech Emotion Recognition (SER) task. Experiments conducted illuminate how feed-forward and recurrent neural network architectures and their variants could be employed for paralinguistic speech recognition, particularly emotion recognition. Convolutional Neural Networks (ConvNets) demonstrated better discriminative performance compared to other architectures. As a result of our exploration, the proposed SER system which relies on minimal speech processing and end-to-end deep learning, in a framebased formulation, yields state-of-the-art results on the IEMOCAP database for speaker-independent SER. Future work can be pursued in several directions. The proposed SER system can be integrated with automatic speech recognition, employing joint knowledge of the linguistic and paralinguistic components of speech to achieve a unified model for speech processing. More generally, observations made in this work as a result of exploring various architectures could be beneficial for devising further architectural innovations in deep learning that can exploit advantages of current models and address their limitations.


بدون دیدگاه