Karthikeyan Saravanan

25 papers A 5C 2Misc 3Journal 14Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	FlowW2N: Whispered-to-Normal Speech Conversion via Flow-Matching. CoRR Fabian Ritter-Gutierrez, Md Asif Jalal, Pablo Peso Parada, Karthikeyan Saravanan, Yusun Shul, Minseung Kim, Gun-Woo Lee, Han-Gil Moon
2025	Misc	`conf`	Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning. ICASSP Jisi Zhang, Pablo Peso Parada, Md Asif Jalal, Karthikeyan Saravanan
2025	J	`jnl`	Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning. CoRR Jisi Zhang, Pablo Peso Parada, Md Asif Jalal, Karthikeyan Saravanan
2025	—	`conf`	Retrieval Augmented Generation based context discovery for ASR. EMNLP (Findings) Dimitrios Siskos, Stavros Papadopoulos, Pablo Peso Parada, Jisi Zhang, Karthikeyan Saravanan, Anastasios Drosou
2025	J	`jnl`	Retrieval Augmented Generation based context discovery for ASR. CoRR Dimitrios Siskos, Stavros Papadopoulos, Pablo Peso Parada, Jisi Zhang, Karthikeyan Saravanan, Anastasios Drosou
2025	A	`conf`	Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling. INTERSPEECH Md Asif Jalal, Luca Remaggi, Vasileios Moschopoulos, Thanasis Kotsiopoulos, Vandana Rajan, Karthikeyan Saravanan, Anastasios Drosou, Junho Heo, Hyuk Oh, Seokyeong Jeong
2025	J	`jnl`	Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling. CoRR Md Asif Jalal, Luca Remaggi, Vasileios Moschopoulos, Thanasis Kotsiopoulos, Vandana Rajan, Karthikeyan Saravanan, Anastasios Drosou, Junho Heo, Hyuk Oh, Seokyeong Jeong
2025	Misc	`conf`	ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR Personalization. ICASSP Haaris Mehmood, Karthikeyan Saravanan, Pablo Peso Parada, David Tuckey, Mete Ozay, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2025	J	`jnl`	ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR Personalization. CoRR Haaris Mehmood, Karthikeyan Saravanan, Pablo Peso Parada, David Tuckey, Mete Ozay, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2025	Misc	`conf`	persoDA: Personalized Data Augmentation for Personalized ASR. ICASSP Pablo Peso Parada, Spyros Fontalis, Md Asif Jalal, Karthikeyan Saravanan, Anastasios Drosou, Mete Ozay, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2025	J	`jnl`	persoDA: Personalized Data Augmentation for Personalized ASR. CoRR Pablo Peso Parada, Spyros Fontalis, Md Asif Jalal, Karthikeyan Saravanan, Anastasios Drosou, Mete Ozay, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2024	J	`jnl`	Consistency Based Unsupervised Self-training For ASR Personalisation. CoRR Jisi Zhang, Vandana Rajan, Haaris Mehmood, David Tuckey, Pablo Peso Parada, Md Asif Jalal, Karthikeyan Saravanan, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2024	J	`jnl`	DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation. CoRR Jie Xu, Karthikeyan Saravanan, Rogier van Dalen, Haaris Mehmood, David Tuckey, Mete Ozay
2024	A	`conf`	Exploring compressibility of transformer based text-to-music (TTM) models. INTERSPEECH Vasileios Moschopoulos, Thanasis Kotsiopoulos, Pablo Peso Parada, Konstantinos Nikiforidis, Alexandros Stergiadis, Gerasimos Papakostas, Md Asif Jalal, Jisi Zhang, Anastasios Drosou, Karthikeyan Saravanan
2024	J	`jnl`	Exploring compressibility of transformer based text-to-music (TTM) models. CoRR Vasileios Moschopoulos, Thanasis Kotsiopoulos, Pablo Peso Parada, Konstantinos Nikiforidis, Alexandros Stergiadis, Gerasimos Papakostas, Md Asif Jalal, Jisi Zhang, Anastasios Drosou, Karthikeyan Saravanan
2024	J	`jnl`	Locality enhanced dynamic biasing and sampling strategies for contextual ASR. CoRR Md Asif Jalal, Pablo Peso Parada, George Pavlidis, Vasileios Moschopoulos, Karthikeyan Saravanan, Chrysovalantis-Giorgos Kontoulis, Jisi Zhang, Anastasios Drosou, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2023	C	`conf`	Consistency Based Unsupervised Self-Training for ASR Personalisation. ASRU Jisi Zhang, Vandana Rajan, Haaris Mehmood, David Tuckey, Pablo Peso Parada, Md Asif Jalal, Karthikeyan Saravanan, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2023	C	`conf`	Locality Enhanced Dynamic Biasing and Sampling Strategies For Contextual ASR. ASRU Md Asif Jalal, Pablo Peso Parada, George Pavlidis, Vasileios Moschopoulos, Karthikeyan Saravanan, Chrysovalantis-Giorgos Kontoulis, Jisi Zhang, Anastasios Drosou, Gil Ho Lee, Jungin Lee, Seokyeong Jung
2023	A	`conf`	On-Device Speaker Anonymization of Acoustic Embeddings for ASR based on Flexible Location Gradient Reversal Layer. INTERSPEECH Md Asif Jalal, Pablo Peso Parada, Jisi Zhang, Mete Ozay, Karthikeyan Saravanan, Myoungji Han, Jungin Lee, Seokyeong Jung
2023	J	`jnl`	On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer. CoRR Md Asif Jalal, Pablo Peso Parada, Jisi Zhang, Karthikeyan Saravanan, Mete Ozay, Myoungji Han, Jungin Lee, Seokyeong Jung
2023	J	`jnl`	Privacy-preserving Federated Learning and its application to natural language processing. Knowl. Based Syst. Balázs Nagy, István Hegedüs, Noémi Sándor, Balázs Egedi, Haaris Mehmood, Karthikeyan Saravanan, Gábor Lóki, Ákos Kiss
2022	A	`conf`	FedNST: Federated Noisy Student Training for Automatic Speech Recognition. INTERSPEECH Haaris Mehmood, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay
2022	J	`jnl`	FedNST: Federated Noisy Student Training for Automatic Speech Recognition. CoRR Haaris Mehmood, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay
2022	A	`conf`	pMCT: Patched Multi-Condition Training for Robust Speech Recognition. INTERSPEECH Pablo Peso Parada, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay
2022	J	`jnl`	pMCT: Patched Multi-Condition Training for Robust Speech Recognition. CoRR Pablo Peso Parada, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay