Skip to Content

Changes for page Social Robot

Last modified by Sofia Vlachopanou on 2025/04/24 23:04
From version 4.4
edited by Nikolaos Soumpeniotis
on 2025/03/01 20:48
Change comment: There is no comment for this version
To version 4.5
edited by Nikolaos Soumpeniotis
on 2025/03/01 20:49
Change comment: There is no comment for this version

Summary

Details

Page properties
Content
... ... @@ -7,18 +7,7 @@
7 7  
8 8  
9 9  
10 -(% style="line-height:1.38; margin-top:16px; margin-bottom:16px" %)
11 -(% style="background-color:#ffffff; color:#212121; font-family:Arial,sans-serif; font-size:11pt; font-style:normal; font-variant:normal; font-weight:400; text-decoration:none; white-space:pre-wrap" %)Another important technology to consider is Cloud Computing, which enables access to external libraries, enhancing the robot’s ability to interact by enriching dialogues. Additionally, cloud computing allows for real-time monitoring of the robot’s interactions and facilitates adaptive decision-making when needed [1].
12 12  
13 -(% style="line-height:1.38; margin-top:16px; margin-bottom:16px" %)
14 -(% style="background-color:#ffffff; color:#212121; font-family:Arial,sans-serif; font-size:11pt; font-style:normal; font-variant:normal; font-weight:400; text-decoration:none; white-space:pre-wrap" %)Equally important aspect of our system is speech recognition, which begins with signal processing through feature extraction. Feature extraction transforms raw audio into a format that machines can process, typically using spectrograms. Spectrograms provide a visual representation of sound frequency over time.
15 -
16 -(% style="line-height:1.38; margin-top:16px; margin-bottom:16px" %)
17 -(% style="background-color:#ffffff; color:#212121; font-family:Arial,sans-serif; font-size:11pt; font-style:normal; font-variant:normal; font-weight:400; text-decoration:none; white-space:pre-wrap" %)After the feature extraction, Deep Neural Networks (DNNs) play a crucial role in mapping these features to words.Additionally, Convolutional Neural Networks (CNNs) are often utilized to process spectrograms, helping to extract meaningful spatial patterns from the data [3].
18 -
19 -(% style="line-height:1.38; margin-top:16px; margin-bottom:16px" %)
20 -(% style="background-color:#ffffff; color:#212121; font-family:Arial,sans-serif; font-size:11pt; font-style:normal; font-variant:normal; font-weight:400; text-decoration:none; white-space:pre-wrap" %) After the neural network processes the speech, a language model is applied to improve recognition accuracy by selecting the most probable word sequence. Traditional approaches relied on n-gram models.
21 -
22 22  **References:**
23 23  
24 24  [1] Neerincx, M.A., van Vught, W., Blanson Henkemans, O., Oleari, E., Broekens, J., Peters, R., Kaptein, F., Demiris, Y., Kiefer, B., Fumagalli, D. and Bierman, B. (2019). Socio-Cognitive Engineering of a Robotic Partner for Child’s Diabetes Self-Management. //Frontiers in Robotics and AI//, 6. doi:https:~/~/doi.org/10.3389/frobt.2019.00118.
... ... @@ -25,6 +25,5 @@
25 25  
26 26  [2] (% style="background-color:#ffffff; color:#212121; font-family:Ubuntu,sans-serif; font-size:12pt; font-style:normal; font-variant:normal; font-weight:400; text-decoration:none; white-space:pre-wrap" %)Abdel-Hamid, O., Mohamed, A., Jiang, H., & Penn, G. (2014). Convolutional neural networks for speech recognition. (% style="background-color:#ffffff; color:#212121; font-family:Ubuntu,sans-serif; font-size:12pt; font-style:italic; font-variant:normal; font-weight:400; text-decoration:none; white-space:pre-wrap" %)//IEEE/ACM Transactions on Audio, Speech, and Language Processing//(% style="background-color:#ffffff; color:#212121; font-family:Ubuntu,sans-serif; font-size:12pt; font-style:normal; font-variant:normal; font-weight:400; text-decoration:none; white-space:pre-wrap" %), 22(10), 1533-1545.
27 27  
28 -
29 29  
30 30