Rama Doddipatla

67 papers A 10C 6Misc 16Journal 27Unranked 8

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Conditional Multi-Stage Failure Recovery for Embodied Agents. CoRR Youmna Farag, Svetlana Stoyanchev, Mohan Li, Simon Keizer, Rama Doddipatla
2025	J	`jnl`	Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models. CoRR Cong-Thanh Do, Rama Doddipatla, Kate M. Knill
2024	J	`jnl`	Entity Resolution in Situated Dialog With Unimodal and Multimodal Transformers. IEEE ACM Trans. Audio Speech Lang. Process. Alejandro Santorum Varela, Svetlana Stoyanchev, Simon Keizer, Rama Doddipatla, Kate M. Knill
2024	Misc	`conf`	Geodesic Interpolation of Frame-Wise Speaker Embeddings for the Diarization of Meeting Scenarios. ICASSP Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2024	—	`conf`	Improving Accented Speech Recognition Using Data Augmentation Based on Unsupervised Text-to-Speech Synthesis. EUSIPCO Cong-Thanh Do, Shuhei Imai, Rama Doddipatla, Thomas Hain
2024	J	`jnl`	Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis. CoRR Cong-Thanh Do, Shuhei Imai, Rama Doddipatla, Thomas Hain
2024	A	`conf`	Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding. INTERSPEECH Mohan Li, Simon Keizer, Rama Doddipatla
2024	—	`conf`	WHISMA: A Speech-LLM to Perform Zero-Shot Spoken Language Understanding. SLT Mohan Li, Cong-Thanh Do, Simon Keizer, Youmna Farag, Svetlana Stoyanchev, Rama Doddipatla
2024	J	`jnl`	WHISMA: A Speech-LLM to Perform Zero-shot Spoken Language Understanding. CoRR Mohan Li, Cong-Thanh Do, Simon Keizer, Youmna Farag, Svetlana Stoyanchev, Rama Doddipatla
2023	A	`conf`	A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures. INTERSPEECH Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2023	J	`jnl`	A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures. CoRR Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2023	J	`jnl`	Adversarial learning of neural user simulators for dialogue policy optimisation. CoRR Simon Keizer, Caroline Dockes, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
2023	Misc	`conf`	Cumulative Attention Based Streaming Transformer ASR with Internal Language Model Joint Training and Rescoring. ICASSP Mohan Li, Cong-Thanh Do, Rama Doddipatla
2023	A	`conf`	Domain Adaptive Self-supervised Training of Automatic Speech Recognition. INTERSPEECH Cong-Thanh Do, Rama Doddipatla, Mohan Li, Thomas Hain
2023	J	`jnl`	Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues. CoRR Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
2023	Misc	`conf`	Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization. ICASSP Tobias Cord-Landwehr, Christoph Böddeker, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2023	J	`jnl`	Non-autoregressive End-to-end Approaches for Joint Automatic Speech Recognition and Spoken Language Understanding. CoRR Mohan Li, Rama Doddipatla
2023	Misc	`conf`	On the Effectiveness of Monoaural Target Source Extraction for Distant end-to-end Automatic Speech Recognition. ICASSP Catalin Zorila, Rama Doddipatla
2023	C	`conf`	Robust Recognition of Speaker Emotion With Difference Feature Extraction Using a Few Enrollment Utterances. ASRU Daichi Hayakawa, Takehiko Kagoshima, Kenji Iwata, Norbert Braunschweiler, Rama Doddipatla
2023	J	`jnl`	Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition. CoRR Mohan Li, Rama Doddipatla, Catalin Zorila
2023	C	`conf`	Towards a Unified End-to-End Language Understanding System for Speech and Text Inputs. ASRU Mohan Li, Catalin Zorila, Cong-Thanh Do, Rama Doddipatla
2022	J	`jnl`	A study on cross-corpus speech emotion recognition and data augmentation. CoRR Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
2022	J	`jnl`	Dialogue Strategy Adaptation to New Action Sets Using Multi-dimensional Modelling. CoRR Simon Keizer, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
2022	J	`jnl`	Factors in Emotion Recognition With Deep Learning Models Using Speech and Text on Multiple Corpora. IEEE Signal Process. Lett. Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
2022	—	`conf`	Monaural Source Separation: From Anechoic To Reverberant Environments. IWAENC Tobias Cord-Landwehr, Christoph Böddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2022	A	`conf`	Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer. INTERSPEECH Cong-Thanh Do, Mohan Li, Rama Doddipatla
2022	J	`jnl`	Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer. CoRR Cong-Thanh Do, Mohan Li, Rama Doddipatla
2022	—	`conf`	Non-Autoregressive End-to-End Approaches for Joint Automatic Speech Recognition and Spoken Language Understanding. SLT Mohan Li, Rama Doddipatla
2022	A	`conf`	On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training. INTERSPEECH Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2022	J	`jnl`	On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training. CoRR Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2022	Misc	`conf`	Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition. ICASSP Catalin Zorila, Rama Doddipatla
2022	J	`jnl`	Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition. CoRR Catalin Zorila, Rama Doddipatla
2022	Misc	`conf`	Transformer-Based Streaming ASR with Cumulative Attention. ICASSP Mohan Li, Shucong Zhang, Catalin Zorila, Rama Doddipatla
2022	J	`jnl`	Transformer-based Streaming ASR with Cumulative Attention. CoRR Mohan Li, Shucong Zhang, Catalin Zorila, Rama Doddipatla
2021	C	`conf`	A Study on Cross-Corpus Speech Emotion Recognition and Data Augmentation. ASRU Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
2021	Misc	`conf`	Action State Update Approach to Dialogue Management. ICASSP Svetlana Stoyanchev, Simon Keizer, Rama Doddipatla
2021	—	`conf`	An Investigation into the Multi-channel Time Domain Speaker Extraction Network. SLT Catalin Zorila, Mohan Li, Rama Doddipatla
2021	C	`conf`	Dialogue Strategy Adaptation to New Action Sets Using Multi-Dimensional Modelling. ASRU Simon Keizer, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
2021	Misc	`conf`	Head-Synchronous Decoding for Transformer-Based Streaming ASR. ICASSP Mohan Li, Catalin Zorila, Rama Doddipatla
2021	C	`conf`	Improving HS-DACS Based Streaming Transformer ASR with Deep Reinforcement Learning. ASRU Mohan Li, Rama Doddipatla
2021	J	`jnl`	Monaural source separation: From anechoic to reverberant environments. CoRR Tobias Cord-Landwehr, Christoph Böddeker, Thilo von Neumann, Catalin Zorila, Rama Doddipatla, Reinhold Haeb-Umbach
2021	Misc	`conf`	Multiple-Hypothesis CTC-Based Semi-Supervised Adaptation of End-to-End Speech Recognition. ICASSP Cong-Thanh Do, Rama Doddipatla, Thomas Hain
2021	J	`jnl`	Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition. CoRR Cong-Thanh Do, Rama Doddipatla, Thomas Hain
2021	A	`conf`	Teacher-Student MixIT for Unsupervised and Semi-Supervised Speech Separation. Interspeech Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2021	J	`jnl`	Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation. CoRR Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2021	Misc	`conf`	Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism. ICASSP Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2021	J	`jnl`	Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism. CoRR Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2021	—	`conf`	Towards Handling Unconstrained User Preferences in Dialogue. IWSDS Suraj Pandey, Svetlana Stoyanchev, Rama Doddipatla
2021	J	`jnl`	Towards Handling Unconstrained User Preferences in Dialogue. CoRR Suraj Pandey, Svetlana Stoyanchev, Rama Doddipatla
2021	Misc	`conf`	Train Your Classifier First: Cascade Neural Networks Training from Upper Layers to Lower Layers. ICASSP Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
2021	J	`jnl`	Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers. CoRR Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
2021	—	`conf`	Transformer-Based Online Speech Recognition with Decoder-end Adaptive Computation Steps. SLT Mohan Li, Catalin Zorila, Rama Doddipatla
2020	J	`jnl`	Action State Update Approach to Dialogue Management. CoRR Svetlana Stoyanchev, Simon Keizer, Rama Doddipatla
2020	Misc	`conf`	Learning Noise Invariant Features Through Transfer Learning For Robust End-to-End Speech Recognition. ICASSP Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Steve Renals
2020	Misc	`conf`	On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments. ICASSP Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2020	J	`jnl`	On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments. CoRR Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
2019	J	`jnl`	An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription. CoRR Catalin Zorila, Christoph Böddeker, Rama Doddipatla, Reinhold Haeb-Umbach
2019	C	`conf`	An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription. ASRU Catalin Zorila, Christoph Böddeker, Rama Doddipatla, Reinhold Haeb-Umbach
2019	Misc	`conf`	An Unsupervised Learning Approach to Neural-net-supported Wpe Dereverberation. ICASSP Petko Nikolov Petkov, Vasileios Tsiaras, Rama Doddipatla, Yannis Stylianou
2019	Misc	`conf`	On Reducing the Effect of Speaker Overlap for Chime-5. ICASSP Catalin Zorila, Rama Doddipatla
2017	A	`conf`	Speaker Adaptation in DNN-Based Speech Synthesis Using d-Vectors. INTERSPEECH Rama Doddipatla, Norbert Braunschweiler, Ranniery Maia
2016	Misc	`conf`	Speaker adaptive training in deep neural networks using speaker dependent bottleneck features. ICASSP Rama Doddipatla
2015	A	`conf`	Noise-matched training of CRF based sentence end detection models. INTERSPEECH Madina Hasan, Rama Doddipatla, Thomas Hain
2015	J	`jnl`	The USFD Spoken Language Translation System for IWSLT 2014. CoRR Raymond W. M. Ng, Mortaza Doulaty, Rama Doddipatla, Wilker Aziz, Kashif Shah, Oscar Saz, Madina Hasan, Ghada AlHarbi, Lucia Specia, Thomas Hain
2014	A	`conf`	Multi-pass sentence-end detection of lecture speech. INTERSPEECH Madina Hasan, Rama Doddipatla, Thomas Hain
2014	A	`conf`	Speaker dependent bottleneck layer training for speaker adaptation in automatic speech recognition. INTERSPEECH Rama Doddipatla, Madina Hasan, Thomas Hain
2014	—	`conf`	The USFD SLT system for IWSLT 2014. IWSLT (Evaluation Campaign) Raymond W. M. Ng, Mortaza Doulaty, Rama Doddipatla, Wilker Aziz, Kashif Shah, Oscar Saz, Madina Hasan, Ghada AlHaribi, Lucia Specia, Thomas Hain