3 citations · 3 across the 15 of their papers we have counts for
15 papers
CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models
Chun-Wei Chen, Tzu-Quan Lin, Ke-Han Lu +2
Speech Language Models achieve reasoning capabilities, but are often hindered by massive parameter counts and a tendency to prioritize linguistic priors over acoustic features. Whi…
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
Wei-Ping Huang, Chee-En Yu, Guan-Ting Lin +1
Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application to generative autoregressive models remains theoreticall…
Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models
Chun-Yi Kuan, Wei-Ping Huang, Hung-yi Lee
Recent audio-aware large language models (ALLMs) have demonstrated strong capabilities across diverse audio understanding and reasoning tasks, but they still frequently produce hal…
How Contrastive Decoding Enhances Large Audio Language Models
Tzu-Quan Lin, Wei-Ping Huang, Yi-Cheng Lin +1
While Contrastive Decoding (CD) has been proposed to enhance Large Audio Language Models (LALMs), it has not been evaluated at scale, and the underlying mechanisms driving its succ…
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu +25
We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Langu…
SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR
Wei-Ping Huang, Guan-Ting Lin, Hung-yi Lee
Despite progress in end-to-end ASR, real-world domain mismatches still cause performance drops, which Test-Time Adaptation (TTA) aims to mitigate by adjusting models during inferen…
Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization
Tzu-Quan Lin, Wei-Ping Huang, Hao Tang +1
Fine-tuning speech representation models can enhance performance on specific tasks but often compromises their cross-task generalization ability. This degradation is often caused b…
Building a Taiwanese Mandarin Spoken Language Model: A First Attempt
Chih-Kai Yang, Yu-Kuan Fu, Chen-An Li +18
This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech…
Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation
Chun-Yi Kuan, Chih-Kai Yang, Wei-Ping Huang +2
In this work, we introduce Speech-Copilot, a modular framework for instruction-oriented speech-processing tasks that minimizes human effort in toolset construction. Unlike end-to-e…
Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models
Chun-Yi Kuan, Wei-Ping Huang, Hung-yi Lee
Large audio-language models (LALMs) enhance traditional large language models by integrating audio perception capabilities, allowing them to tackle audio-related tasks. Previous re…
Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech
Guan-Ting Lin, Wei-Ping Huang, Hung-yi Lee
Deep Learning-based end-to-end Automatic Speech Recognition (ASR) has made significant strides but still struggles with performance on out-of-domain samples due to domain shifts in…
Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initialization
Wei-Ping Huang, Sung-Feng Huang, Hung-yi Lee
This paper presents an effective transfer learning framework for language adaptation in text-to-speech systems, with a focus on achieving language adaptation using minimal labeled…
Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond
Jiatong Shi, William Chen, Dan Berrebbi +10
The 2023 Multilingual Speech Universal Performance Benchmark (ML-SUPERB) Challenge expands upon the acclaimed SUPERB framework, emphasizing self-supervised models in multilingual s…
On the Utility of Self-supervised Models for Prosody-related Tasks
Guan-Ting Lin, Chi-Luen Feng, Wei-Ping Huang +5
Self-Supervised Learning (SSL) from speech data has produced models that have achieved remarkable performance in many tasks, and that are known to implicitly represent many aspects…
Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding
Wei-Ping Huang, Po-Chun Chen, Sung-Feng Huang +1
This paper studies a transferable phoneme embedding framework that aims to deal with the cross-lingual text-to-speech (TTS) problem under the few-shot setting. Transfer learning is…