Catalin Zorila

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 29

Top Topics

Language Understanding

Speech Recognition

Noisy Environments

Top Venues

Publications

Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios. ICASSP (2024)
Mohan Li, Catalin Zorila, Cong-Thanh Do, Rama Doddipatla
Towards a Unified End-to-End Language Understanding System for Speech and Text Inputs. ASRU (2023)
Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. INTERSPEECH (2023)
Mohan Li, Rama Doddipatla, Catalin Zorila
Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition. CoRR (2023)
Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. ICASSP (2023)
Catalin Zorila, Rama Doddipatla
On the Effectiveness of Monoaural Target Source Extraction for Distant end-to-end Automatic Speech Recognition. ICASSP (2023)
Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures. CoRR (2023)
Tobias Cord-Landwehr, Christoph Böddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
Monaural Source Separation: From Anechoic To Reverberant Environments. IWAENC (2022)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training. INTERSPEECH (2022)
Mohan Li, Shucong Zhang, Catalin Zorila, Rama Doddipatla
Transformer-based Streaming ASR with Cumulative Attention. CoRR (2022)
Catalin Zorila, Rama Doddipatla
Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition. ICASSP (2022)
Mohan Li, Shucong Zhang, Catalin Zorila, Rama Doddipatla
Transformer-Based Streaming ASR with Cumulative Attention. ICASSP (2022)
P. V. Muhammed Shifas, Catalin Zorila, Yannis Stylianou
End-to-End Neural Based Modification of Noisy Speech for Speech-in-Noise Intelligibility Improvement. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training. CoRR (2022)
Catalin Zorila, Rama Doddipatla
Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition. CoRR (2022)
Mohan Li, Rama Sanand Doddipatla, Catalin Zorila
Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition. INTERSPEECH (2022)
Tobias Cord-Landwehr, Christoph Böddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
Monaural source separation: From anechoic to reverberant environments. CoRR (2021)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism. ICASSP (2021)
Mohan Li, Catalin Zorila, Rama Doddipatla
Head-Synchronous Decoding for Transformer-Based Streaming ASR. ICASSP (2021)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation. CoRR (2021)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
Teacher-Student MixIT for Unsupervised and Semi-Supervised Speech Separation. Interspeech (2021)
Catalin Zorila, Mohan Li, Rama Doddipatla
An Investigation into the Multi-channel Time Domain Speaker Extraction Network. SLT (2021)
Mohan Li, Catalin Zorila, Rama Doddipatla
Transformer-Based Online Speech Recognition with Decoder-end Adaptive Computation Steps. SLT (2021)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism. CoRR (2021)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments. ICASSP (2020)
Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments. CoRR (2020)
Catalin Zorila, Christoph Böddeker, Rama Doddipatla, Reinhold Haeb-Umbach
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription. CoRR (2019)
Catalin Zorila, Rama Doddipatla
On Reducing the Effect of Speaker Overlap for Chime-5. ICASSP (2019)
Catalin Zorila, Christoph Böddeker, Rama Doddipatla, Reinhold Haeb-Umbach
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription. ASRU (2019)