[host]

app.py

@@ -0,0 +1,99 @@
+import gradio as gr
+import pandas as pd
+import matplotlib.pyplot as plt
+import numpy as np
+
+# Load the leaderboard data
+def load_data():
+    df = pd.read_csv("leaderboard_results.csv")
+    return df
+
+# Create a bar chart visualization of the accuracy scores
+def create_accuracy_chart(df):
+    fig, ax = plt.subplots(figsize=(10, 6))
+    
+    # Sort by accuracy for better visualization
+    df_sorted = df.sort_values(by='Test Acc', ascending=False)
+    
+    # Create bar chart
+    bars = ax.bar(df_sorted['Solution'], df_sorted['Test Acc'], color='skyblue')
+    
+    # Highlight the best performer
+    bars[0].set_color('gold')
+    
+    # Add labels and title
+    ax.set_xlabel('Solution')
+    ax.set_ylabel('Test Accuracy')
+    ax.set_title('Leaderboard Results by Accuracy')
+    
+    # Rotate x-axis labels for better readability
+    plt.xticks(rotation=45, ha='right')
+    
+    # Add text labels on bars
+    for bar in bars:
+        height = bar.get_height()
+        ax.text(bar.get_x() + bar.get_width()/2., height + 0.01,
+                f'{height:.5f}', ha='center', va='bottom')
+    
+    plt.tight_layout()
+    return fig
+
+# Display detailed information for a selected solution
+def display_solution_details(solution_name):
+    df = load_data()
+    if solution_name:
+        solution_data = df[df['Solution'] == solution_name].iloc[0]
+        details = f"""
+## {solution_data['Solution']} Details
+
+- **Test Accuracy**: {solution_data['Test Acc']:.5f}
+- **Institution**: {solution_data['Institution']}
+- **Region**: {solution_data['Region']}
+- **Paper**: {solution_data['Paper']}
+- **Lead Author**: {solution_data['Lead Author']}
+        """
+        return details
+    return "Please select a solution to see details."
+
+# Main interface
+def create_interface():
+    df = load_data()
+    
+    with gr.Blocks(title="Emotion Recognition Leaderboard") as demo:
+        gr.Markdown("# Speech-based Emotion Recognition Leaderboard")
+        
+        with gr.Row():
+            with gr.Column():
+                # Display the full leaderboard table
+                gr.DataFrame(
+                    df.sort_values(by='Test Acc', ascending=False),
+                    label="Leaderboard Results"
+                )
+            
+            with gr.Column():
+                # Display the visualization
+                gr.Plot(create_accuracy_chart(df))
+        
+        with gr.Row():
+            # Add dropdown for selecting a specific solution for more details
+            solution_dropdown = gr.Dropdown(
+                choices=df['Solution'].tolist(),
+                label="Select Solution for Details"
+            )
+            
+            # Display area for solution details
+            solution_details = gr.Markdown()
+        
+        # Update solution details when dropdown changes
+        solution_dropdown.change(
+            display_solution_details,
+            inputs=solution_dropdown,
+            outputs=solution_details
+        )
+            
+    return demo
+
+# Load data, create and launch the interface
+if __name__ == "__main__":
+    demo = create_interface()
+    demo.launch() 

leaderboard_results.csv

@@ -0,0 +1,6 @@
+Test Acc,Solution,Institution,Region,Paper,Lead Author
+0.75162,Mosaic,Florida International University,US,Improving Speech-based Emotion Recognition with Contextual Utterance Analysis and LLMs,Enshi Zhang
+0.75059,UoE,University of Edinburgh,UK,Context and System Fusion in Post-ASR Emotion Recognition with Large Language Models,Pavel Stepachev and Pinzhen Chen
+0.64522,SLAM,Academia Sinica,TW,"How Good is ChatGPT at Audiovisual Deepfake Detection: A Comparative Study of ChatGPT, AI Models and Human Perception","Speech, Language nad Music Processing (SLAM) Laboratory"
+0.58809,TeamBlack,Columbia University,US,Post-ASR LLM-Based Speech Emotion Recognition: A fight between top LLMs,Sounak Ray
+0.5518,GPT-3.5 Turbo,Baseline,Global,"Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition",Official