Results 261 to 270 of about 1,400,670 (295)
Some of the next articles are maybe not open access.
MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech
Annual Meeting of the Association for Computational LinguisticsZero-shot text-to-speech (TTS) has gained significant attention due to its powerful voice cloning capabilities, requiring only a few seconds of unseen speaker voice prompts. However, all previous work has been developed for cloud-based systems.
Shengpeng Ji +4 more
semanticscholar +1 more source
Pushing the Limits of Zero-shot End-to-End Speech Translation
Annual Meeting of the Association for Computational LinguisticsData scarcity and the modality gap between the speech and text modalities are two major obstacles of end-to-end Speech Translation (ST) systems, thus hindering their performance.
Yiannis (Ioannis) Tsiamas +3 more
semanticscholar +1 more source
MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector
Annual Meeting of the Association for Computational LinguisticsResearch in toxicity detection in natural language processing for the speech modality (audio-based) is quite limited, particularly for languages other than English.
M. Costa-jussà +8 more
semanticscholar +1 more source
Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon
Conference of the European Chapter of the Association for Computational LinguisticsImproving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we relax the reliance on texts in low-resource languages by using multilingual
Fajri Koto +4 more
semanticscholar +1 more source
Demonstration Augmentation for Zero-shot In-context Learning
Annual Meeting of the Association for Computational LinguisticsLarge Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates. However, many studies have highlighted
Yi Su +5 more
semanticscholar +1 more source
Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore
International Conference on Computational LinguisticsThe efficacy of detectors for texts generated by large language models (LLMs) substantially depends on the availability of large-scale training data. However, white-box zero-shot detectors, which require no such data, are limited by the accessibility of ...
Junchao Wu +6 more
semanticscholar +1 more source
Taxonomy-Guided Zero-Shot Recommendations with LLMs
International Conference on Computational LinguisticsWith the emergence of large language models (LLMs) and their ability to perform a variety of tasks, their application in recommender systems (RecSys) has shown promise.
Yueqing Liang +5 more
semanticscholar +1 more source
Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing
North American Chapter of the Association for Computational LinguisticsLarge Language Models (LLMs) have achieved state-of-the-art performance at zero-shot generation of abstractive summaries for given articles. However, little is known about the robustness of such a process of zero-shot summarization.
Hadi Askari +3 more
semanticscholar +1 more source
, 2016 Engineered platforms for topological superconductivity and Majorana zero modes
Nature Reviews Materials, 2021Karsten Flensberg +2 more
exaly