Author name cluster

Hung-yi Lee

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

TMLR Journal 2025 Journal Article

Discrete Audio Tokens: More Than a Survey!

Pooneh Mousavi
Gallil Maimon
Adel Moumen
Darius Petermann
Jiatong Shi
Haibin Wu
Haici Yang
Anastasia Kuznetsova

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and inference, as well as competitive performance across diverse downstream tasks. They provide a practical alternative to continuous features, enabling the integration of speech and audio into modern large language models (LLMs). As interest in token-based audio processing grows, various tokenization methods have emerged, and several surveys have reviewed the latest progress in the field. However, existing studies often focus on specific domains or tasks and lack a unified comparison across various benchmarks. This paper presents a systematic review and benchmark of discrete audio tokenizers, covering three domains: speech, music, and general audio. We propose a taxonomy of tokenization approaches based on encoder-decoder, quantization techniques, training paradigm, streamability, and application domains. We evaluate tokenizers on multiple benchmarks for reconstruction, downstream performance, and acoustic language modeling, and analyze trade-offs through controlled ablation studies. Our findings highlight key limitations, practical considerations, and open challenges, providing insight and guidance for future research in this rapidly evolving area. For more information, including our main results and tokenizer database, please refer to our website: https://poonehmousavi.github.io/dates-website/.

PDF Details

ICML Conference 2025 Conference Paper

Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction

Shu-Wen Yang
Byeonggeun Kim
Kuan-Po Huang
Qingming Tang
Huy Phan
Bo-Ru Lu
Harshavardhan Sundar
Shalini Ghosh

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio poses unique challenges due to its inherently continuous nature. We research audio generation with a causal language model (LM) without discrete tokens. We leverage token-wise diffusion to model the continuous distribution of the next continuous-valued token. Our approach delivers significant improvements over previous discrete solution, AudioGen, achieving 20% and 40% relative gains on AudioCaps in Frechet Audio Distance (FAD) and Kullback-Leibler (KL) divergence, respectively. Additionally, we propose a novel masked next-token prediction task that incorporates masked prediction into the causal LM framework. On AudioCaps, the innovation yields 41% and 33% relative FAD improvements over AudioGen Base (285M) and AudioGen Large (1B) models, respectively, and is on par with the state-of-the-art (SOTA) diffusion models. Furthermore, we achieve these results with significantly fewer parameters—193M for our Base and 462M for our Large models.

Details

ICML Conference 2025 Conference Paper

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling

Kuan-Po Huang
Shu-Wen Yang
Huy Phan
Bo-Ru Lu
Byeonggeun Kim
Sashank Macha
Qingming Tang
Shalini Ghosh

Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in text-to-audio generation. Despite achieving high audio fidelity, they incur significant inference latency due to the slow diffusion sampling process. MAGNET, a mask-based model operating on discrete tokens, addresses slow inference through iterative mask-based parallel decoding. However, its audio quality still lags behind that of diffusion-based models. In this work, we introduce IMPACT, a text-to-audio generation framework that achieves high performance in audio quality and fidelity while ensuring fast inference. IMPACT utilizes iterative mask-based parallel decoding in a continuous latent space powered by diffusion modeling. This approach eliminates the fidelity constraints of discrete tokens while maintaining competitive inference speed. Results on AudioCaps demonstrate that IMPACT achieves state-of-the-art performance on key metrics including Fréchet Distance (FD) and Fréchet Audio Distance (FAD) while significantly reducing latency compared to prior models. The project website is available at https: //audio-impact. github. io/.

Details

NeurIPS Conference 2025 Conference Paper

Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning

Chao-Chung Wu
Zhi Rui Tam
Chieh-Yen Lin
Yun-Nung (Vivian) Chen
Shao-Hua Sun
Hung-yi Lee

Maintaining consistent model performance across domains is a fundamental challenge in machine learning. While recent work has explored using LLM-generated data for fine-tuning, its impact on cross-domain generalization remains poorly understood. This paper presents a systematic analysis revealing that fine-tuning with LLM-generated data not only improves target task performance but also reduces non-target task degradation compared to fine-tuning with ground truth data. Through analyzing the data sequence in tasks of various domains, we demonstrate that this enhancement of non-target task robustness stems from the reduction of high perplexity tokens found in LLM-generated sequences. Following our findings, we showed that masking high perplexity tokens in ground truth training data achieves similar non-target task performance preservation, comparable to using LLM-generated data. Extensive experiments across different model families and scales, including Gemma 2 IT 2B, Llama 3 8B Instruct, and three additional models, agree with our findings. To the best of our knowledge, this is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning, offering valuable insights for developing more robust fine-tuning strategies.

PDF Details

TMLR Journal 2025 Journal Article

On The Landscape of Spoken Language Models: A Comprehensive Survey

Siddhant Arora
Kai-Wei Chang
Chung-Ming Chien
Yifan Peng
Haibin Wu
Yossi Adi
Emmanuel Dupoux
Hung-yi Lee

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar to the progression toward universal language models that has taken place in the field of (text) natural language processing. SLMs include both "pure" language models of speech---models of the distribution of tokenized speech sequences---and models that combine speech encoders with text language models, often including both spoken and written input or output. Work in this area is very diverse, with a range of terminology and evaluation settings. This paper aims to contribute an improved understanding of SLMs via a unifying literature survey of recent work in the context of the evolution of the field. Our survey categorizes the work in this area by model architecture, training, and evaluation choices, and describes some key challenges and directions for future work.

PDF Details

NeurIPS Conference 2024 Conference Paper

Meta-Diffu$B$: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration

Yun-Yen Chuang
Hung-Min Hsu
Kevin Lin
Chen-Sheng Gu
Ling Z. Li
Ray-I Chang
Hung-yi Lee

The diffusion model, a new generative modeling paradigm, has achieved significant success in generating images, audio, video, and text. It has been adapted for sequence-to-sequence text generation (Seq2Seq) through DiffuSeq, termed the S2S-Diffusion model. Existing S2S-Diffusion models predominantly rely on fixed or hand-crafted rules to schedule noise during the diffusion and denoising processes. However, these models are limited by non-contextualized noise, which fails to fully consider the characteristics of Seq2Seq tasks. In this paper, we propose the Meta-Diffu$B$ framework—a novel scheduler-exploiter S2S-Diffusion paradigm designed to overcome the limitations of existing S2S-Diffusion models. We employ Meta-Exploration to train an additional scheduler model dedicated to scheduling contextualized noise for each sentence. Our exploiter model, an S2S-Diffusion model, leverages the noise scheduled by our scheduler model for updating and generation. Meta-Diffu$B$ achieves state-of-the-art performance compared to previous S2S-Diffusion models and fine-tuned pre-trained language models (PLMs) across four Seq2Seq benchmark datasets. We further investigate and visualize the impact of Meta-Diffu$B$'s noise scheduling on the generation of sentences with varying difficulties. Additionally, our scheduler model can function as a "plug-and-play" model to enhance DiffuSeq without the need for fine-tuning during the inference stage.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR

Liang-Hsuan Tseng
En-Pei Hu
Cheng-Han Chiang
Yuan Tseng
Hung-yi Lee
Lin-shan Lee
Shao-Hua Sun

Unsupervised automatic speech recognition (ASR) aims to learn the mapping between the speech signal and its corresponding textual transcription without the supervision of paired speech-text data. A word/phoneme in the speech signal is represented by a segment of speech signal with variable length and unknown boundary, and this segmental structure makes learning the mapping between speech and text challenging, especially without paired data. In this paper, we propose REBORN, Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR. REBORN alternates between (1) training a segmentation model that predicts the boundaries of the segmental structures in speech signals and (2) training the phoneme prediction model, whose input is a segmental structure segmented by the segmentation model, to predict a phoneme transcription. Since supervised data for training the segmentation model is not available, we use reinforcement learning to train the segmentation model to favor segmentations that yield phoneme sequence predictions with a lower perplexity. We conduct extensive experiments and find that under the same setting, REBORN outperforms all prior unsupervised ASR models on LibriSpeech, TIMIT, and five non-English languages in Multilingual LibriSpeech. We comprehensively analyze why the boundaries learned by REBORN improve the unsupervised ASR performance.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

StreamBench: Towards Benchmarking Continuous Improvement of Language Agents

Cheng-Kuang Wu
Zhi R. Tam
Chieh-Yen Lin
Yun-Nung Chen
Hung-yi Lee

Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However, existing benchmarks primarily evaluate their innate capabilities and do not assess their ability to improve over time. To address this gap, we introduce StreamBench, a pioneering benchmark designed to evaluate the continuous improvement of LLM agents over an input-feedback sequence. StreamBench simulates an online learning environment where LLMs receive a continuous flow of feedback stream and iteratively enhance their performance. In addition, we propose several simple yet effective baselines for improving LLMs on StreamBench, and provide a comprehensive analysis to identify critical components that contribute to successful streaming strategies. Our work serves as a stepping stone towards developing effective online learning strategies for LLMs, paving the way for more adaptive AI systems in streaming scenarios.

PDF Details DOI

ICML Conference 2023 Conference Paper

Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs

Guan-Ting Liu
En-Pei Hu
Pu-Jen Cheng
Hung-yi Lee
Shao-Hua Sun

Aiming to produce reinforcement learning (RL) policies that are human-interpretable and can generalize better to novel scenarios, Trivedi et al. (2021) present a method (LEAPS) that first learns a program embedding space to continuously parameterize diverse programs from a pre-generated program dataset, and then searches for a task-solving program in the learned program embedding space when given a task. Despite the encouraging results, the program policies that LEAPS can produce are limited by the distribution of the program dataset. Furthermore, during searching, LEAPS evaluates each candidate program solely based on its return, failing to precisely reward correct parts of programs and penalize incorrect parts. To address these issues, we propose to learn a meta-policy that composes a series of programs sampled from the learned program embedding space. By learning to compose programs, our proposed hierarchical programmatic reinforcement learning (HPRL) framework can produce program policies that describe out-of-distributionally complex behaviors and directly assign credits to programs that induce desired behaviors. The experimental results in the Karel domain show that our proposed framework outperforms baselines. The ablation studies confirm the limitations of LEAPS and justify our design choices.

Details

AAAI Conference 2022 Conference Paper

On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets

Cheng-Han Chiang
Hung-yi Lee

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what specific traits in the pre-training data, other than the semantics, make a pre-trained LM superior to their counterparts trained from scratch on downstream tasks. We propose to use artificially constructed datasets as the pre-training data to exclude the effect of semantics, and further control what characteristics the pre-training corpora have. By fine-tuning the pre-trained models on GLUE benchmark, we can learn how beneficial it is to transfer the knowledge from the model trained on the dataset possessing that specific trait. We define and discuss three different characteristics in the artificial dataset: 1) matching the token’s uni-gram or bi-gram distribution between pre-training and downstream fine-tuning, 2) the presence of the explicit dependencies among the tokens in a sequence, 3) the length of the implicit dependencies among the tokens in a sequence. Our experiments show that the explicit dependencies in the sequences of the pre-training data are critical to the downstream performance. Our results also reveal that models achieve better downstream performance when pre-trained on a dataset with a longer range of implicit dependencies. Based on our analysis, we find that models pretrained with artificial datasets are prone to learn spurious correlation in downstream tasks. Our work reveals that even if the LMs are not pre-trained on natural language, they still gain transferability on certain human language downstream tasks once the LMs learn to model the token dependencies in the sequences. This result helps us understand the exceptional transferability of pre-trained LMs.

PDF Details

AAAI Conference 2021 Short Paper

Multi-modal User Intent Classification Under the Scenario of Smart Factory (Student Abstract)

Yu-Ching Chiu
Bo-Hao Chang
Tzu-Yu Chen
Cheng-Fu Yang
Nanyi Bi
Richard Tzong-Han Tsai
Hung-yi Lee
Jane Yung-jen Hsu

Question-answering systems are becoming increasingly popular in Natural Language Processing, especially when applied in smart factory settings. A common practice in designing those systems is through intent classification. However, in a multiple-stage task commonly seen in those settings, relying solely on intent classification may lead to erroneous answers, as questions rising from different work stages may share the same intent but have different contexts and therefore require different answers. To address this problem, we designed an interactive dialogue system that utilizes contextual information to assist intent classification in a multiple-stage task. Specifically, our system incorporates user’s utterances with real-time video feed to better situate users’ questions and analyze their intent.

PDF Details

ICLR Conference 2020 Conference Paper

LAMOL: LAnguage MOdeling for Lifelong Language Learning

Fan-Keng Sun
Cheng-Hao Ho
Hung-yi Lee

Most research on lifelong learning applies to images or games, but not language. We present LAMOL, a simple yet effective method for lifelong language learning (LLL) based on language modeling. LAMOL replays pseudo-samples of previous tasks while requiring no extra memory or model capacity. Specifically, LAMOL is a language model that simultaneously learns to solve the tasks and generate training samples. When the model is trained for a new task, it generates pseudo-samples of previous tasks for training alongside data for the new task. The results show that LAMOL prevents catastrophic forgetting without any sign of intransigence and can perform five very different language tasks sequentially with only one model. Overall, LAMOL outperforms previous methods by a considerable margin and is only 2-3% worse than multitasking, which is usually considered the LLL upper bound. The source code is available at https://github.com/jojotenya/LAMOL.

Details

AAAI Conference 2020 Conference Paper

Order-Free Learning Alleviating Exposure Bias in Multi-Label Classification

Che-Ping Tsai
Hung-yi Lee

Multi-label classiﬁcation (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However, training a RNN decoder requires a predeﬁned order of labels, which is not directly available in the MLC speciﬁcation. Besides, RNN thus trained tends to overﬁt the label combinations in the training set and have difﬁculty generating unseen label sequences. In this paper, we propose a new framework for MLC which does not rely on a predeﬁned label order and thus alleviates exposure bias. The experimental results on three multi-label classiﬁcation benchmark datasets show that our method outperforms competitive baselines by a large margin. We also ﬁnd the proposed approach has a higher probability of generating label combinations not seen during training than the baseline models. The result shows that the proposed approach has better generalization capability.

PDF Details

NeurIPS Conference 2020 Conference Paper

TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation

Chun-Hsing Lin
Siang-Ruei Wu
Hung-yi Lee
Yun-Nung Chen

Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems. This is mainly due to the non-differentiable nature of the discrete space sampling and thus these methods have to treat the discriminator as a black box and ignore the gradient information. To improve the sample efficiency and reduce the variance of REINFORCE, we propose a novel approach, TaylorGAN, which augments the gradient estimation by off-policy update and the first-order Taylor expansion. This approach enables us to train NLG models from scratch with smaller batch size --- without maximum likelihood pre-training, and outperforms existing GAN-based methods on multiple metrics of quality and diversity.

PDF Details