22 citations · 44 across the 20 of their papers we have counts for
23 papers
DEFINE: Exemplar-Guided Accent Control for Zero-Shot TTS
Ambuj Mehrish, Abhinaba Roy, Alex Ivanov +2
Zero-shot text-to-speech (TTS) can reproduce an unseen speaker from a short reference recording, but typically entangles speaker identity and accent within the same reference. We i…
Query-Conditioned Spherical Centroid Aggregation for Multimodal Retrieval
Ambuj Mehrish, Anindya Nag, Sebastiano Vascon
Multimodal retrieval integrates video, audio, subtitles, and text; however, recent geometric aggregators, such as Gramian volumes, hyperbolic volumes, and spectral objectives, trea…
Hypergraph-Regularized Gramian Volumes for Multimodal Retrieval
Anindya Nag, Ambuj Mehrish, Sebastiano Vascon
Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures higher-order within-candidate a…
RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction
Ambuj Mehrish, Sebastiano Vascon
Brain-to-audio reconstruction is limited by \emph{prior domination}: when a pretrained generator is conditioned on a weak neural signal, it produces realistic but stimulus-inaccura…
CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning
Ambuj Mehrish, Sebastiano Vascon
On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding those that match the majority…
Constrained Dominant Sets for Multimodal Document Question Answering
Ambuj Mehrish, Sebastiano Vascon
Long multimodal document question answering is limited by which evidence reaches the reader, rather than by the quantity retrieved. In lengthy documents, findings often recur acros…
Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents
Ambuj Mehrish, Sebastiano Vascon
Answering questions about long multimodal documents requires distributing a fixed evidence budget across relevant facets in text, tables, figures, and slides while avoiding near-du…
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
Jan Melechovsky, Ambuj Mehrish, Abhinaba Roy +1
Music recordings often suffer from audio quality issues such as excessive reverberation, distortion, clipping, tonal imbalances, and a narrowed stereo image, especially when create…
DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors
Tazeek Bin Abdur Rakib, Ambuj Mehrish, Lay-Ki Soon +2
Large-language-model (LLM) agents excel at reactive dialogue but struggle with proactive, goal-driven interactions due to myopic decoding and costly planning. We introduce DialogXp…
PROEMO: Prompt-Driven Text-to-Speech Synthesis Based on Emotion and Intensity Control
Shaozuo Zhang, Ambuj Mehrish, Yingting Li +1
Speech synthesis has significantly advanced from statistical methods to deep neural network architectures, leading to various text-to-speech (TTS) models that closely mimic human s…
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
Chia-Yu Hung, Navonil Majumder, Zhifeng Kong +6
We introduce TangoFlux, an efficient Text-to-Audio (TTA) generative model with 515M parameters, capable of generating up to 30 seconds of 44.1kHz audio in just 3.7 seconds on a sin…
DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech
Jan Melechovsky, Ambuj Mehrish, Berrak Sisman +1
Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by…
Improving Text-To-Audio Models with Synthetic Captions
Zhifeng Kong, Sang-gil Lee, Deepanway Ghosal +5
It is an open challenge to obtain high quality training data, especially captions, for text-to-audio models. Although prior methods have leveraged \textit{text-only language models…
Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation
Yingting Li, Ambuj Mehrish, Bryan Chew +2
Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise…
Inference Time Alignment with Reward-Guided Tree Search
Chia-Yu Hung, Navonil Majumder, Ambuj Mehrish +1
Inference-time computation methods enhance the performance of Large Language Models (LLMs) by leveraging additional computational resources to achieve superior results. Common tech…
Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training
Jan Melechovsky, Ambuj Mehrish, Berrak Sisman +1
With rapid globalization, the need to build inclusive and representative speech technology cannot be overstated. Accent is an important aspect of speech that needs to be taken into…
HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks
Yingting Li, Rishabh Bhardwaj, Ambuj Mehrish +2
Neural speech synthesis, or text-to-speech (TTS), aims to transform a signal from the text domain to the speech domain. While developing TTS architectures that train and test on th…
CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
Xiang Li, Fan Bu, Ambuj Mehrish +4
Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), hold…
A Review of Deep Learning Techniques for Speech Processing
Ambuj Mehrish, Navonil Majumder, Rishabh Bhardwaj +2
The field of speech processing has undergone a transformative shift with the advent of deep learning. The use of multiple processing layers has enabled the creation of models capab…
ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation
Ambuj Mehrish, Abhinav Ramesh Kashyap, Li Yingting +2
There are significant challenges for speaker adaptation in text-to-speech for languages that are not widely spoken or for speakers with accents or dialects that are not well-repres…
Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model
Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish +1
The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly…
Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding
Yingting Li, Ambuj Mehrish, Shuai Zhao +5
Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the…
Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder
Jan Melechovsky, Ambuj Mehrish, Berrak Sisman +1
Accent plays a significant role in speech communication, influencing one's capability to understand as well as conveying a person's identity. This paper introduces a novel and effi…