Ambuj Mehrish

35 papers A* 2A 3C 2Misc 2Journal 21Unranked 5
YearRankTypeTitle / Venue / Authors
2026 A* conf
DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors.
AAAI
Tazeek Bin Abdur Rakib, Ambuj Mehrish, Lay-Ki Soon, Wern Han Lim, Soujanya Poria
2025 J jnl
DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors.
CoRR
Tazeek Bin Abdur Rakib, Ambuj Mehrish, Lay-Ki Soon, Wern Han Lim, Soujanya Poria
2025 J jnl
PROEMO: Prompt-Driven Text-to-Speech Synthesis Based on Emotion and Intensity Control.
CoRR
Shaozuo Zhang, Ambuj Mehrish, Yingting Li, Soujanya Poria
2025 — conf
Reward-Guided Tree Search for Inference Time Alignment of Large Language Models.
NAACL (Long Papers)
Chia-Yu Hung, Navonil Majumder, Ambuj Mehrish, Soujanya Poria
2025 J jnl
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering.
CoRR
Jan Melechovský, Ambuj Mehrish, Dorien Herremans
2024 J jnl
Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training.
CoRR
Jan Melechovský, Ambuj Mehrish, Berrak Sisman, Dorien Herremans
2024 C conf
Accent Conversion in Text-to-Speech Using Multi-Level VAE and Adversarial Training.
TENCON
Jan Melechovský, Ambuj Mehrish, Berrak Sisman, Dorien Herremans
2024 C conf
Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder.
TENCON
Jan Melechovský, Ambuj Mehrish, Berrak Sisman, Dorien Herremans
2024 — conf
CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models.
NAACL-HLT (Findings)
Xiang Li, FanBu FanBu, Ambuj Mehrish, Yingting Li, Jiale Han, Bo Cheng, Soujanya Poria
2024 J jnl
CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models.
CoRR
Xiang Li, Fan Bu, Ambuj Mehrish, Yingting Li, Jiale Han, Bo Cheng, Soujanya Poria
2024 J jnl
DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech.
CoRR
Jan Melechovský, Ambuj Mehrish, Berrak Sisman, Dorien Herremans
2024 — conf
HYPERTTS: Parameter Efficient Adaptation in Text to Speech Using Hypernetworks.
LREC/COLING
Yingting Li, Rishabh Bhardwaj, Ambuj Mehrish, Bo Cheng, Soujanya Poria
2024 J jnl
HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks.
CoRR
Yingting Li, Rishabh Bhardwaj, Ambuj Mehrish, Bo Cheng, Soujanya Poria
2024 J jnl
Improving Text-To-Audio Models with Synthetic Captions.
CoRR
Zhifeng Kong, Sang-gil Lee, Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Rafael Valle, Soujanya Poria, Bryan Catanzaro
2024 J jnl
Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation.
CoRR
Yingting Li, Ambuj Mehrish, Bryan Chew, Bo Cheng, Soujanya Poria
2024 J jnl
Reward Steering with Evolutionary Heuristics for Decoding-time Alignment.
CoRR
Chia-Yu Hung, Navonil Majumder, Ambuj Mehrish, Soujanya Poria
2024 J jnl
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization.
CoRR
Chia-Yu Hung, Navonil Majumder, Zhifeng Kong, Ambuj Mehrish, Rafael Valle, Bryan Catanzaro, Soujanya Poria
2023 J jnl
A review of deep learning techniques for speech processing.
Inf. Fusion
Ambuj Mehrish, Navonil Majumder, Rishabh Bharadwaj, Rada Mihalcea, Soujanya Poria
2023 A conf
ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation.
INTERSPEECH
Ambuj Mehrish, Abhinav Ramesh Kashyap, Yingting Li, Navonil Majumder, Soujanya Poria
2023 J jnl
ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation.
CoRR
Ambuj Mehrish, Abhinav Ramesh Kashyap, Yingting Li, Navonil Majumder, Soujanya Poria
2023 Misc conf
Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding.
ICASSP
Yingting Li, Ambuj Mehrish, Rishabh Bhardwaj, Navonil Majumder, Bo Cheng, Shuai Zhao, Amir Zadeh, Rada Mihalcea, Soujanya Poria
2023 J jnl
Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding.
CoRR
Yingting Li, Ambuj Mehrish, Shuai Zhao, Rishabh Bhardwaj, Amir Zadeh, Navonil Majumder, Rada Mihalcea, Soujanya Poria
2023 A* conf
Text-to-Audio Generation using Instruction Guided Latent Diffusion Model.
ACM Multimedia
Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya Poria
2023 J jnl
Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model.
CoRR
Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya Poria
2023 J jnl
Towards lifelong human assisted speaker diarization.
Comput. Speech Lang.
Meysam Shamsi, Anthony Larcher, Loïc Barrault, Sylvain Meignier, Yevhenii Prokopalo, Marie Tahon, Ambuj Mehrish, Simon Petitrenaud, Olivier Galibert, Samuel Gaist, André Anjos, Sébastien Marcel, Marta R. Costa-jussà
2022 J jnl
Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder.
CoRR
Jan Melechovský, Ambuj Mehrish, Berrak Sisman, Dorien Herremans
2022 — conf
Learning Accent Representation with Multi-Level VAE Towards Controllable Speech Synthesis.
SLT
Jan Melechovský, Ambuj Mehrish, Dorien Herremans, Berrak Sisman
2021 Misc conf
Speaker Embeddings for Diarization of Broadcast Data In The Allies Challenge.
ICASSP
Anthony Larcher, Ambuj Mehrish, Marie Tahon, Sylvain Meignier, Jean Carrive, David Doukhan, Olivier Galibert, Nicholas W. D. Evans
2021 A conf
The LIUM Human Active Correction Platform for Speaker Diarization.
Interspeech
Alexandre Flucha, Anthony Larcher, Ambuj Mehrish, Sylvain Meignier, Florian Plaut, Nicolas Poupon, Yevhenii Prokopalo, Adrien Puertolas, Meysam Shamsi, Marie Tahon
2020 J jnl
Egocentric Analysis of Dash-Cam Videos for Vehicle Forensics.
IEEE Trans. Circuits Syst. Video Technol.
Ambuj Mehrish, Prerna Singh, Puneet Jain, A. Venkata Subramanyam, Mohan S. Kankanhalli
2019 J jnl
Joint Spatial and Discrete Cosine Transform Domain-Based Counter Forensics for Adaptive Contrast Enhancement.
IEEE Access
Ambuj Mehrish, A. Venkata Subramanyam, Sabu Emmanuel
2018 J jnl
Robust PRNU estimation from probabilistic raw measurements.
Signal Process. Image Commun.
Ambuj Mehrish, A. Venkata Subramanyam, Sabu Emmanuel
2017 A conf
Multimedia signatures for vehicle forensics.
ICME
Ambuj Mehrish, A. Venkata Subramanyam, Mohan S. Kankanhalli
2016 — conf
Anti-forensic technique for median filtering using L1-L2 TV model.
WIFS
Shishir Sharma, A. Venkata Subramanyam, Monika Jain, Ambuj Mehrish, Sabu Emmanuel
2016 J jnl
Sensor Pattern Noise Estimation Using Probabilistically Estimated RAW Values.
IEEE Signal Process. Lett.
Ambuj Mehrish, A. Venkata Subramanyam, Sabu Emmanuel