Picture for Ajinkya Kulkarni

Ajinkya Kulkarni

MULTISPEECH

Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems

Add code
Mar 02, 2025
Viaarxiv icon

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR

Add code
Jan 17, 2025
Viaarxiv icon

SSL-TTS: Leveraging Self-Supervised Embeddings and kNN Retrieval for Zero-Shot Multi-speaker TTS

Add code
Aug 20, 2024
Viaarxiv icon

What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark

Add code
Jun 14, 2024
Viaarxiv icon

The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese

Add code
Feb 12, 2024
Viaarxiv icon

Training Convolutional Neural Networks with the Forward-Forward algorithm

Add code
Jan 07, 2024
Viaarxiv icon

ArTST: Arabic Text and Speech Transformer

Add code
Oct 25, 2023
Viaarxiv icon

Yet Another Model for Arabic Dialect Identification

Add code
Oct 20, 2023
Figure 1 for Yet Another Model for Arabic Dialect Identification
Figure 2 for Yet Another Model for Arabic Dialect Identification
Viaarxiv icon

Adapting the adapters for code-switching in multilingual ASR

Add code
Oct 11, 2023
Figure 1 for Adapting the adapters for code-switching in multilingual ASR
Figure 2 for Adapting the adapters for code-switching in multilingual ASR
Viaarxiv icon

Self-supervised learning with diffusion-based multichannel speech enhancement for speaker verification under noisy conditions

Add code
Jul 05, 2023
Viaarxiv icon