English
Related papers

Related papers: SpeechAlign: Aligning Speech Generation to Human P…

200 papers

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

Computation and Language · Computer Science 2025-10-14 Shuai Zhao , Yunqiu Xu , Linchao Zhu , Yi Yang

Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known as sycophancy. We investigate the prevalence of sycophancy in…

Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, stories generated by LLMs still diverge from human-authored…

Computation and Language · Computer Science 2026-05-07 Haotian Xia , Hao Peng , Yunjia Qi , Xiaozhi Wang , Bin Xu , Lei Hou , Juanzi Li

With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For practical applicability, a TTS model should generate high-quality speech with only a few audio…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Dongchan Min , Dong Bok Lee , Eunho Yang , Sung Ju Hwang

Current speech evaluation suffers from two critical limitations: the need and difficulty of designing specialized systems targeting individual audio characteristics, and poor correlation between automatic evaluation methods and human…

Large language models (LLMs) that are tuned with instructions have demonstrated remarkable capabilities in various tasks and languages. However, their ability to generalize to underrepresented languages is limited due to the scarcity of…

Computation and Language · Computer Science 2023-10-25 Samuel Cahyawijaya , Holy Lovenia , Tiezheng Yu , Willy Chung , Pascale Fung

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from…

Computation and Language · Computer Science 2025-06-06 Zhaoxuan Tan , Zheng Li , Tianyi Liu , Haodong Wang , Hyokun Yun , Ming Zeng , Pei Chen , Zhihan Zhang , Yifan Gao , Ruijie Wang , Priyanka Nigam , Bing Yin , Meng Jiang

State of the art speech enhancement (SE) models achieve strong performance on neurotypical speech, but their effectiveness is substantially reduced for pathological speech. In this paper, we investigate strategies to address this gap for…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-24 Mingchi Hou , Ante Jukic , Ina Kodrasi

Training code-switched language models is difficult due to lack of data and complexity in the grammatical structure. Linguistic constraint theories have been used for decades to generate artificial code-switching sentences to cope with this…

Computation and Language · Computer Science 2019-09-19 Genta Indra Winata , Andrea Madotto , Chien-Sheng Wu , Pascale Fung

Recent advances in generative AI for music have achieved remarkable fidelity and stylistic diversity, yet these systems often fail to align with nuanced human preferences due to the specific loss functions they use. This paper advocates for…

Sound · Computer Science 2025-11-20 Dorien Herremans , Abhinaba Roy

Personalized dialogue generation aims to leverage persona profiles and dialogue history to generate persona-relevant and consistent responses. Mainstream models typically rely on token-level language model training with persona dialogue…

Computation and Language · Computer Science 2025-11-14 Guanrong Li , Xinyu Liu , Zhen Wu , Xinyu Dai

We study speech language models that incorporate semantic initialization and planning losses to achieve robust and consistent generation. Our approach initializes speech tokens with self-supervised features, applies a light alignment loss,…

Computation and Language · Computer Science 2025-10-01 Morteza Rohanian , Michael Krauthammer

From the earliest years of our lives, humans use language to express our beliefs and desires. Being able to talk to artificial agents about our preferences would thus fulfill a central goal of value alignment. Yet today, we lack…

Artificial Intelligence · Computer Science 2022-10-12 Theodore R Sumers , Robert D Hawkins , Mark K Ho , Thomas L Griffiths , Dylan Hadfield-Menell

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Computation and Language · Computer Science 2023-10-10 Chung-Ming Chien , Mingjiamei Zhang , Ju-Chieh Chou , Karen Livescu

In the quest to advance human-centric natural language generation (NLG) systems, ensuring alignment between NLG models and human preferences is crucial. For this alignment, current popular methods leverage a reinforcement learning (RL)…

Computation and Language · Computer Science 2024-01-17 Jiashuo Wang , Haozhao Wang , Shichao Sun , Wenjie Li

Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior…

Computation and Language · Computer Science 2026-05-28 Chan-Jan Hsu , Liang-Hsuan Tseng , Yi-Cheng Lin , Yen-Chun Kuo , Ju-Chieh Chou , Kai-Wei Chang , Hung-yi Lee , Carlos Busso

This paper presents SaSLaW, a spontaneous dialogue speech corpus containing synchronous recordings of what speakers speak, listen to, and watch. Humans consider the diverse environmental factors and then control the features of their…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-14 Osamu Take , Shinnosuke Takamichi , Kentaro Seki , Yoshiaki Bando , Hiroshi Saruwatari

A key requirement in developing Generative Language Models (GLMs) is to have their values aligned with human values. Preference-based alignment is a widely used paradigm for this purpose, in which preferences over generation pairs are first…

Computation and Language · Computer Science 2024-04-16 Yang Gao , Dana Alon , Donald Metzler

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-29 Jarod Duret , Yannick Estève , Titouan Parcollet

Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in…

Computation and Language · Computer Science 2024-07-17 Ganqu Cui , Lifan Yuan , Ning Ding , Guanming Yao , Bingxiang He , Wei Zhu , Yuan Ni , Guotong Xie , Ruobing Xie , Yankai Lin , Zhiyuan Liu , Maosong Sun
‹ Prev 1 3 4 5 6 7 10 Next ›