53 citations · 63 across the 10 of their papers we have counts for
11 papers
Beyond Token-Level Cross-Entropy: Fréchet Distributional Post-Training for Autoregressive Image Generation
Jinhua Zhang, Yisong Lin, Wei Long +1
Autoregressive image generators are commonly pretrained with token-level cross-entropy under teacher forcing, yet evaluated by the distributional quality of decoded images. This cr…
From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
Shuchang Ye, Jinqiang Yu, Zhujun Xiao +6
Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external APIs, including adaptation t…
A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR
Van Tung Pham, Yist Lin, Tao Han +4
Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limi…
A Large-Scale Evaluation of Speech Foundation Models
Shu-wen Yang, Heng-Jui Chang, Zili Huang +18
The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling a…
Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition
Xianzhao Chen, Yist Y. Lin, Kang Wang +2
End-to-end (E2E) systems have shown comparable performance to hybrid systems for automatic speech recognition (ASR). Word timings, as a by-product of ASR, are essential in many app…
Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition
Yist Y. Lin, Tao Han, Haihua Xu +6
One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper,…
SUPERB: Speech processing Universal PERformance Benchmark
Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang +17
Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large…
Utilizing Self-supervised Representations for MOS Prediction
Wei-Cheng Tseng, Chien-yu Huang, Wei-Tsung Kao +2
Speech quality assessment has been a critical issue in speech processing for decades. Existing automatic evaluations usually require clean references or parallel ground truth data,…
S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations
Jheng-hao Lin, Yist Y. Lin, Chung-Ming Chien +1
Any-to-any voice conversion (VC) aims to convert the timbre of utterances from and to any speakers seen or unseen during training. Various any-to-any VC approaches have been propos…
FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention
Yist Y. Lin, Chung-Ming Chien, Jheng-Hao Lin +2
Any-to-any voice conversion aims to convert the voice from and to any speakers even unseen during training, which is much more challenging compared to one-to-one or many-to-many ta…
Defending Your Voice: Adversarial Attack on Voice Conversion
Chien-yu Huang, Yist Y. Lin, Hung-yi Lee +1
Substantial improvements have been achieved in recent years in voice conversion, which converts the speaker characteristics of an utterance into those of another speaker without ch…