6 citations · 7 across the 13 of their papers we have counts for
18 papers
MQAScore: Fine-Grained Text-Music Alignment Evaluation via Large Audio Language Model
Wei-Jaw Lee, Chun-Ping Wang, Xuanjun Chen +1
Text-to-music alignment is commonly evaluated by the global similarity between text and audio embeddings, which collapses all described attributes into a single score and obscures…
What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities
Hua-Hsuan Chen, Xuanjun Chen, Wei-Chung Lu +5
Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvements may reflect adaptation to s…
Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?
Xuanjun Chen, Zixiong Su, Hao Shi +4
Although reinforcement learning (RL) post-training repairs the localized segmental errors of zero-shot text-to-speech (TTS), arriving at a working recipe still relies on tedious ma…
MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses
Xuanjun Chen, Hua-Hsuan Chen, Wei-Chung Lu +3
Rapid progress in Large Language Models (LLMs) is saturating static benchmarks faster than they can be designed. While existing automated evolution frameworks attempt to generate h…
Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech
Xuanjun Chen, Yun-Shing Wu, Wei-Chung Lu +4
Recent neural audio codec-based speech generation (CodecFake) produces highly realistic audio, posing a challenge to existing deepfake countermeasure models. While using codec resy…
Training-Efficient Text-to-Music Generation with State-Space Modeling
Wei-Jaw Lee, Fang-Chih Hsieh, Xuanjun Chen +2
Recent advances in text-to-music generation (TTM) have yielded high-quality results, but often at the cost of extensive compute and the use of large proprietary internal data. To i…
How Does Instrumental Music Help SingFake Detection?
Xuanjun Chen, Chia-Yu Hu, I-Ming Lin +8
Although many models exist to detect singing voice deepfakes (SingFake), how these models operate, particularly with instrumental accompaniment, is unclear. We investigate how inst…
Exploring State-Space-Model based Language Model in Music Generation
Wei-Jaw Lee, Fang-Chih Hsieh, Xuanjun Chen +2
The recent surge in State Space Models (SSMs), particularly the emergence of Mamba, has established them as strong alternatives or complementary modules to Transformers across dive…
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…
A Preliminary Exploration with GPT-4o Voice Mode
Yu-Xiang Lin, Chih-Kai Yang, Wei-Chih Chen +4
With the rise of multimodal large language models, GPT-4o stands out as a pioneering model, driving us to evaluate its capabilities. This report assesses GPT-4o across various task…
CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech
Xuanjun Chen, Jiawei Du, Haibin Wu +8
With the rapid advancement of neural audio codecs, codec-based speech generation (CoSG) systems have become highly powerful. Unfortunately, CoSG also enables the creation of highly…
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…
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang +77
Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spo…
Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models
Haibin Wu, Xuanjun Chen, Yi-Cheng Lin +13
Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling. The i…
DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset
Jiawei Du, I-Ming Lin, I-Hsiang Chiu +6
Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, hu…
Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancement
Wenze Ren, Haibin Wu, Yi-Cheng Lin +7
In multichannel speech enhancement, effectively capturing spatial and spectral information across different microphones is crucial for noise reduction. Traditional methods, such as…
Towards audio language modeling -- an overview
Haibin Wu, Xuanjun Chen, Yi-Cheng Lin +4
Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency. Researchers recently discovered the potential of codecs as su…
Codec-SUPERB: An In-Depth Analysis of Sound Codec Models
Haibin Wu, Ho-Lam Chung, Yi-Cheng Lin +7
The sound codec's dual roles in minimizing data transmission latency and serving as tokenizers underscore its critical importance. Recent years have witnessed significant developme…