Cover Image

When Fine-Tuning Fails and when it Generalises: Role of Data Diversity and Mixed Training in LLM-based TTS

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Purwar, Anupam, Choudhary, Aditya
Format:	Preprint
Published:	2026
Subjects:	Sound Artificial Intelligence Emerging Technologies
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings
by: Purwar, Anupam, et al.
Published: (2026)

i-LAVA: Insights on Low Latency Voice-2-Voice Architecture for Agents
by: Purwar, Anupam, et al.
Published: (2025)

GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentanglement
by: Chen, Zhiwei, et al.
Published: (2026)

SoilSound: Smartphone-based Soil Moisture Estimation
by: Gao, Yixuan, et al.
Published: (2025)

AcousTools: A 'Full-Stack', Python-Based, Acoustic Holography Library
by: Mukherjee, Joshua, et al.
Published: (2025)

Quantum Approaches for Dysphonia Assessment in Small Speech Datasets
by: Tran, Ha, et al.
Published: (2025)

Improving snore detection under limited dataset through harmonic/percussive source separation and convolutional neural networks
by: Gonzalez-Martinez, F. D., et al.
Published: (2024)

VidyaRANG: Conversational Learning Based Platform powered by Large Language Model
by: Harbola, Chitranshu, et al.
Published: (2024)

Introducing a new hyper-parameter for RAG: Context Window Utilization
by: Juvekar, Kush, et al.
Published: (2024)

Harnessing AI Agents to Advance Research on Refugee Child Mental Health
by: Shrivastava, Aditya, et al.
Published: (2025)

Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework
by: Hu, Yulong, et al.
Published: (2025)

FOCAL: A Novel Benchmarking Technique for Multi-modal Agents
by: Purwar, Anupam, et al.
Published: (2026)

Towards Personalized Explanations for Health Simulations: A Mixed-Methods Framework for Stakeholder-Centric Summarization
by: Giabbanelli, Philippe J., et al.
Published: (2025)

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
by: Nguyen, Luong N.
Published: (2026)

Governed By Agents: A Survey On The Role Of Agentic AI In Future Computing Environments
by: Murad, Nauman Ali, et al.
Published: (2025)

CultureVo: The Serious Game of Utilizing Gen AI for Enhancing Cultural Intelligence
by: Agarwala, Ajita, et al.
Published: (2024)

Physics-Informed Autonomous LLM Agents for Explainable Power Electronics Modulation Design
by: Liu, Junhua, et al.
Published: (2024)

LSDTs: LLM-Augmented Semantic Digital Twins for Adaptive Knowledge-Intensive Infrastructure Planning
by: Li, Naiyi, et al.
Published: (2025)

Developing AI Agents with Simulated Data: Why, what, and how?
by: Liu, Xiaoran, et al.
Published: (2026)

When to Reason: Semantic Router for vLLM
by: Wang, Chen, et al.
Published: (2025)

Symbolic-AI-Fusion Deep Learning (SAIF-DL): Encoding Knowledge into Training with Answer Set Programming Loss Penalties by a Novel Loss Function Approach
by: Machot, Fadi Al, et al.
Published: (2024)

Sonified Quantum Seizures. Sonification of time series in epileptic seizures and simulation of seizures via quantum modelling
by: Mannone, Maria, et al.
Published: (2025)

On when is Reservoir Computing with Cellular Automata Beneficial?
by: Glover, Tom, et al.
Published: (2024)

Enhancing Software Quality Assurance with an Adaptive Differential Evolution based Quantum Variational Autoencoder-Transformer Model
by: Barma, Seshu Babu, et al.
Published: (2025)

Rubric-based Learner Modelling via Noisy Gates Bayesian Networks for Computational Thinking Skills Assessment
by: Adorni, Giorgia, et al.
Published: (2024)

A Large Language Model-based Multi-Agent Framework for Analog Circuits' Sizing Relationships Extraction
by: Liu, Chengjie, et al.
Published: (2025)

Measuring Accuracy and Energy-to-Solution of Quantum Fine-Tuning of Foundational AI Models
by: Knitter, Oliver, et al.
Published: (2026)

LLM4DS: Evaluating Large Language Models for Data Science Code Generation
by: Nascimento, Nathalia, et al.
Published: (2024)

QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming
by: Fu, Zhenxiao, et al.
Published: (2025)

Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
by: Ambrosini, Irene, et al.
Published: (2026)

The Relic Condition: When Published Scholarship Becomes Material for Its Own Replacement
by: Deng, Lin, et al.
Published: (2026)

When simulations look right but causal effects go wrong: Large language models as behavioral simulators
by: Li, Zonghan, et al.
Published: (2026)

Spike Encoding for Environmental Sound: A Comparative Benchmark
by: Larroza, Andres, et al.
Published: (2025)

Acoustic Anomaly Detection on UAM Propeller Defect with Acoustic dataset for Crack of drone Propeller (ADCP)
by: Lee, Juho, et al.
Published: (2025)

Quantum Fourier Transform Based Denoising: Unitary Filtering for Enhanced Speech Clarity
by: Tripathi, Rajeshwar, et al.
Published: (2025)

The Sound of Entanglement
by: Rodríguez, Enar de Dios, et al.
Published: (2025)

Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identification
by: Gautam, Aditya
Published: (2025)

LLM-Powered Quantum Code Transpilation
by: Siavash, Nazanin, et al.
Published: (2025)

The Roles of Generative Artificial Intelligence in Internet of Electric Vehicles
by: Zhang, Hanwen, et al.
Published: (2024)

Beyond the Data Mesh Illusion: Designing Modern AI-augmented Lakehouses to Bridge the Gap Between Theory and Practice
by: Angélil, Oliver, et al.
Published: (2026)