中文
相关论文

相关论文: On the Fallacy of Global Token Perplexity in Spoke…

200 篇论文

Automatic methods and metrics that assess various quality criteria of automatically generated texts are important for developing NLG systems because they produce repeatable results and allow for a fast development cycle. We present here an…

计算与语言 · 计算机科学 2020-06-25 Erion Çano , Ondřej Bojar

Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in…

音频与语音处理 · 电气工程与系统科学 2026-02-12 Haibin Wu , Yuxuan Hu , Ruchao Fan , Xiaofei Wang , Kenichi Kumatani , Bo Ren , Jianwei Yu , Heng Lu , Lijuan Wang , Yao Qian , Jinyu Li

Instruction-based speech processing is becoming popular. Studies show that training with multiple tasks boosts performance, but collecting diverse, large-scale tasks and datasets is expensive. Thus, it is highly desirable to design a…

计算与语言 · 计算机科学 2024-08-27 Chien-yu Huang , Min-Han Shih , Ke-Han Lu , Chi-Yuan Hsiao , Hung-yi Lee

Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue et al., 2022). However, these works mainly focus on reporting…

计算与语言 · 计算机科学 2022-10-14 Jimin Sun , Patrick Fernandes , Xinyi Wang , Graham Neubig

Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d.\ test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such…

机器学习 · 计算机科学 2026-04-08 Shashaank Aiyer , Yishay Mansour , Shay Moran , Han Shao

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

计算与语言 · 计算机科学 2021-09-22 Giulio Zhou , Gerasimos Lampouras

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

音频与语音处理 · 电气工程与系统科学 2024-06-21 Vahid Noroozi , Zhehuai Chen , Somshubra Majumdar , Steve Huang , Jagadeesh Balam , Boris Ginsburg

Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners.…

计算与语言 · 计算机科学 2017-06-21 Chung-Cheng Chiu , Dieterich Lawson , Yuping Luo , George Tucker , Kevin Swersky , Ilya Sutskever , Navdeep Jaitly

Generative models, such as large language models and text-to-image diffusion models, produce relevant information when presented a query. Different models may produce different information when presented the same query. As the landscape of…

机器学习 · 计算机科学 2025-01-20 Aranyak Acharyya , Michael W. Trosset , Carey E. Priebe , Hayden S. Helm

Fine-tuning large language models (LLMs) typically relies on producing large sets of input-output pairs. Yet for a given question, there can be many valid outputs. In practice, these outputs are often derived by distilling knowledge from…

计算与语言 · 计算机科学 2025-08-28 Xuan Ren , Qi Chen , Lingqiao Liu

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how…

计算与语言 · 计算机科学 2020-11-13 Charles Welch , Jonathan K. Kummerfeld , Verónica Pérez-Rosas , Rada Mihalcea

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

计算与语言 · 计算机科学 2026-05-07 Mikhail L. Arbuzov , Sisong Bei , Ziwei Dong , Dmitri Kalaev , Alexey A. Shvets

Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds. We compare two ideas about the influence of the native language on speech perception: the Perceptual Assimilation…

计算与语言 · 计算机科学 2022-06-01 Juliette Millet , Ioana Chitoran , Ewan Dunbar

Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, fundamentally reshaping the landscape of natural language processing (NLP) research. However, recent evaluation frameworks often rely on the…

计算与语言 · 计算机科学 2024-07-10 Chenyang Lyu , Minghao Wu , Alham Fikri Aji

Recent advances in deep learning have significantly enhanced generative AI capabilities across text, images, and audio. However, automatically evaluating the quality of these generated outputs presents ongoing challenges. Although numerous…

计算与语言 · 计算机科学 2025-06-13 Tian Lan , Yang-Hao Zhou , Zi-Ao Ma , Fanshu Sun , Rui-Qing Sun , Junyu Luo , Rong-Cheng Tu , Heyan Huang , Chen Xu , Zhijing Wu , Xian-Ling Mao

Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity, of the generated language -- ideally tailored towards each…

计算与语言 · 计算机科学 2024-08-09 Justin Lovelace , Varsha Kishore , Yiwei Chen , Kilian Q. Weinberger

Recent advances in speech generation have enabled high-fidelity synthesis, yet systematic evaluation of models under long-context conditions remains largely underexplored. A comprehensive evaluation benchmark for long-form speech is…

音频与语音处理 · 电气工程与系统科学 2026-05-28 Changhao Pan , Rui Yang , Han Wang , Zhuan Zhou , Xuming He , Wenxiang Guo , Ziyue Jiang , Ruiqi Li , Yu Zhang , Chenyuhao Wen , Ke Lei , Xiang Yin , Jingyu Lu , Zhiyuan Zhu , Zhou Zhao

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

计算与语言 · 计算机科学 2019-08-30 Jindřich Libovický , Pranava Madhyastha

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech…

计算与语言 · 计算机科学 2026-02-02 Yuxuan Lou , Ziming Wu , Yaochen Wang , Yong Liu , Yingxuan Ren , Fuming Lai , Shaobing Lian , Jie Tang , Yang You

Advancements in spoken language processing have driven the development of spoken language models (SLMs), designed to achieve universal audio understanding by jointly learning text and audio representations for a wide range of tasks.…

计算与语言 · 计算机科学 2025-10-31 Pedro Corrêa , João Lima , Victor Moreno , Lucas Ueda , Paula Dornhofer Paro Costa
‹ 上一页 1 8 9 10 下一页 ›