Catalin Zorila

According to our database, Catalin Zorila authored at least 18 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2023

A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures.

Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach

CoRR, 2023

On the Effectiveness of Monoaural Target Source Extraction for Distant end-to-end Automatic Speech Recognition.

Catalin Zorila, Rama Doddipatla

Proceedings of the IEEE International Conference on Acoustics, 2023

Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization.

Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach

Proceedings of the IEEE International Conference on Acoustics, 2023

Towards a Unified End-to-End Language Understanding System for Speech and Text Inputs.

Mohan Li, Catalin Zorila, Cong-Thanh Do, Rama Doddipatla

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

End-to-End Neural Based Modification of Noisy Speech for Speech-in-Noise Intelligibility Improvement.

P. V. Muhammed Shifas, Catalin Zorila, Yannis Stylianou

IEEE ACM Trans. Audio Speech Lang. Process., 2022

Monaural Source Separation: From Anechoic To Reverberant Environments.

Tobias Cord-Landwehr, Christoph Böddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach

Proceedings of the 17th International Workshop on Acoustic Signal Enhancement, 2022

On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training.

Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker

Proceedings of the Interspeech 2022, 2022

Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition.

Mohan Li, Rama Sanand Doddipatla, Catalin Zorila

Proceedings of the Interspeech 2022, 2022

Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition.

Catalin Zorila, Rama Doddipatla

Proceedings of the IEEE International Conference on Acoustics, 2022

Transformer-Based Streaming ASR with Cumulative Attention.

Mohan Li, Shucong Zhang, Catalin Zorila, Rama Doddipatla

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

An Investigation into the Multi-channel Time Domain Speaker Extraction Network.

Catalin Zorila, Mohan Li, Rama Doddipatla

Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Transformer-Based Online Speech Recognition with Decoder-end Adaptive Computation Steps.

Mohan Li, Catalin Zorila, Rama Doddipatla

Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Teacher-Student MixIT for Unsupervised and Semi-Supervised Speech Separation.

Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism.

Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker

Proceedings of the IEEE International Conference on Acoustics, 2021

Head-Synchronous Decoding for Transformer-Based Streaming ASR.

Mohan Li, Catalin Zorila, Rama Doddipatla

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments.

Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

On Reducing the Effect of Speaker Overlap for Chime-5.

Catalin Zorila, Rama Doddipatla

Proceedings of the IEEE International Conference on Acoustics, 2019

An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription.

Catalin Zorila, Christoph Böddeker, Rama Doddipatla, Reinhold Haeb-Umbach

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019