Picture for Kevin El Haddad

Kevin El Haddad

ASR Benchmarking: Need for a More Representative Conversational Dataset

Add code
Sep 18, 2024
Figure 1 for ASR Benchmarking: Need for a More Representative Conversational Dataset
Figure 2 for ASR Benchmarking: Need for a More Representative Conversational Dataset
Figure 3 for ASR Benchmarking: Need for a More Representative Conversational Dataset
Figure 4 for ASR Benchmarking: Need for a More Representative Conversational Dataset
Viaarxiv icon

Efficacy of Synthetic Data as a Benchmark

Add code
Sep 18, 2024
Viaarxiv icon

A New Perspective on Smiling and Laughter Detection: Intensity Levels Matter

Add code
Mar 04, 2024
Viaarxiv icon

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs

Add code
Feb 20, 2024
Figure 1 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Figure 2 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Figure 3 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Figure 4 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Viaarxiv icon

Deep learning-based stereo camera multi-video synchronization

Add code
Mar 22, 2023
Viaarxiv icon

Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS system

Add code
Mar 06, 2021
Figure 1 for Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS system
Figure 2 for Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS system
Figure 3 for Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS system
Figure 4 for Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS system
Viaarxiv icon

ICE-Talk: an Interface for a Controllable Expressive Talking Machine

Add code
Aug 25, 2020
Figure 1 for ICE-Talk: an Interface for a Controllable Expressive Talking Machine
Figure 2 for ICE-Talk: an Interface for a Controllable Expressive Talking Machine
Viaarxiv icon

Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning

Add code
Aug 20, 2020
Figure 1 for Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning
Figure 2 for Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning
Figure 3 for Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning
Figure 4 for Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning
Viaarxiv icon

The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach

Add code
Oct 14, 2019
Figure 1 for The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach
Figure 2 for The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach
Figure 3 for The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach
Figure 4 for The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach
Viaarxiv icon

Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis through Audio Analysis

Add code
Mar 27, 2019
Figure 1 for Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis through Audio Analysis
Figure 2 for Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis through Audio Analysis
Figure 3 for Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis through Audio Analysis
Figure 4 for Visualization and Interpretation of Latent Spaces for Controlling Expressive Speech Synthesis through Audio Analysis
Viaarxiv icon