Karan Thakkar

According to our database, Karan Thakkar authored at least 11 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Using LLMs for Late Multimodal Sensor Fusion for Activity Recognition.

Ilker Demirel, Karan Thakkar, Benjamin Elizalde, Miquel Espi Marques, Shirley You Ren, Jaya Narain

CoRR, September, 2025

CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech.

Helin Wang, Jiarui Hai, Dading Chong, Karan Thakkar, Tiantian Feng, Dongchao Yang, Junhyeok Lee, Laureano Moro-Velázquez, Jesús Villalba, Zengyi Qin, Shrikanth Narayanan, Mounya Elhilali, Najim Dehak

CoRR, June, 2025

Foundation Model Hidden Representations for Heart Rate Estimation from Auscultation.

Jingping Nie, Dung T. Tran, Karan Thakkar, Vasudha Kowtha, Jonathan Huang, Carlos Avendaño, Erdrin Azemi, Vikramjit Mitra

CoRR, May, 2025

Foundation Model Hidden Representations for Heart Rate Estimation from Auscultation.

Jingping Nie, Tien Dung Tran, Karan Thakkar, Vasudha Kowtha, Jon Huang, Carlos Avendaño, Erdrin Azemi, Vikramjit Mitra

Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025

SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer.

Helin Wang, Jiarui Hai, Yen-Ju Lu, Karan Thakkar, Mounya Elhilali, Najim Dehak

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

DreamVoice: Text-Guided Voice Conversion.

Jiarui Hai, Karan Thakkar, Helin Wang, Zengyi Qin, Mounya Elhilali

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Investigating Self-Supervised Deep Representations for EEG-Based Auditory Attention Decoding.

Karan Thakkar, Jiarui Hai, Mounya Elhilali

Proceedings of the IEEE International Conference on Acoustics, 2024

DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction.

Jiarui Hai, Helin Wang, Dongchao Yang, Karan Thakkar, Najim Dehak, Mounya Elhilali

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Explicit-memory multiresolution adaptive framework for speech and music separation.

Ashwin Bellur, Karan Thakkar, Mounya Elhilali

EURASIP J. Audio Speech Music. Process., December, 2023

Stress Testing Chain-of-Thought Prompting for Large Language Models.

Aayush Mishra, Karan Thakkar

CoRR, 2023

2020

Emergence of deep learning as a potential solution for detection, recovery and de-noising of signals in communication systems.

Karan Thakkar, Apoorv Goyal, Budhaditya Bhattacharyya

Int. J. Intell. Networks, 2020