LIVIVO - Search results -

Search results

Result 1 - 10 of total 80391

Search options

Article ; Online: Learning to Generate Tips from Song Reviews.

Zang, Jingya / Gao, Cuiyun / Chen, Yupan / Xu, Ruifeng / Zhou, Lanjun / Wang, Xuan

Neural networks : the official journal of the International Neural Network Society

2023 Volume 161, Page(s) 746–756

Abstract: ... that users can make quicker and more informed decisions when presented with meaningful song reviews ... descriptions about songs. Tips are produced from song reviews and should express non-trivial insights ... framework named GenTMS for automatically generating tips from song reviews. The dataset involves 8,003 ...

Abstract	Reviews of songs play an important role in online music service platforms. Prior research shows that users can make quicker and more informed decisions when presented with meaningful song reviews. However, reviews of songs are generally long in length and most of them are non-informative for users. It is difficult for users to efficiently grasp meaningful messages for making decisions. To solve this problem, one practical strategy is to provide tips, i.e., short, concise, empathetic, and self-contained descriptions about songs. Tips are produced from song reviews and should express non-trivial insights about the songs. To the best of our knowledge, no prior studies have explored the tip generation task in music domain. In this paper, we create a dataset named MTips for the task and propose a learning-to-generate framework named GenTMS for automatically generating tips from song reviews. The dataset involves 8,003 Chinese tips/non-tips from 128 songs which are distributed in five different song genres. Experimental results show that GenTMS achieves top-10 precision at 85.56%, outperforming the baseline models by at least 3.34%. Besides, to simulate the practical usage of our proposed framework, we also experiment with previously-unseen songs, during which GenTMS also achieves the best performance with top-10 precision at 78.89% on average. The results demonstrate the effectiveness of the proposed framework in tip generation of the music domain.
MeSH term(s)	Learning ; Music ; Problem Solving ; Decision Making
Language	English
Publishing date	2023-02-17
Publishing country	United States
Document type	Journal Article
ZDB-ID	740542-x
ISSN	1879-2782 ; 0893-6080
ISSN (online)	1879-2782
ISSN	0893-6080
DOI	10.1016/j.neunet.2023.01.049
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2365: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Details ▾
- See ZB MED holdings
- Order with fees

Book ; Online: The Song Describer Dataset

Manco, Ilaria / Weck, Benno / Doh, SeungHeon / Won, Minz / Zhang, Yixiao / Bogdanov, Dmitry / Wu, Yusong / Chen, Ke / Tovstogan, Philip / Benetos, Emmanouil / Quinton, Elio / Fazekas, György / Nam, Juhan

a Corpus of Audio Captions for Music-and-Language Evaluation

2023

Abstract: We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio ...

Abstract	We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models. The dataset consists of 1.1k human-written natural language descriptions of 706 music recordings, all publicly accessible and released under Creative Common licenses. To showcase the use of our dataset, we benchmark popular models on three key music-and-language tasks (music captioning, text-to-music generation and music-language retrieval). Our experiments highlight the importance of cross-dataset evaluation and offer insights into how researchers can use SDD to gain a broader understanding of model performance. Comment: Accepted to NeurIPS 2023 Workshop on Machine Learning for Audio
Keywords	Computer Science - Sound ; Computer Science - Artificial Intelligence ; Computer Science - Computation and Language ; Electrical Engineering and Systems Science - Audio and Speech Processing
Subject code	780
Publishing date	2023-11-16
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Siren's Song in the AI Ocean

Zhang, Yue / Li, Yafu / Cui, Leyang / Cai, Deng / Liu, Lemao / Fu, Tingchen / Huang, Xinting / Zhao, Enbo / Zhang, Yu / Chen, Yulong / Wang, Longyue / Luu, Anh Tuan / Bi, Wei / Shi, Freda / Shi, Shuming

A Survey on Hallucination in Large Language Models

2023

Abstract: While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the ... ...

Abstract	While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research. Comment: work in progress; 32 pages
Keywords	Computer Science - Computation and Language ; Computer Science - Artificial Intelligence ; Computer Science - Computers and Society ; Computer Science - Machine Learning
Subject code	501
Publishing date	2023-09-03
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: A Proactive and Dual Prevention Mechanism against Illegal Song Covers empowered by Singing Voice Conversion

Chen, Guangke / Zhang, Yedi / Song, Fu / Wang, Ting / Du, Xiaoning / Liu, Yang

2024

Abstract: Singing voice conversion (SVC) automates song covers by converting one singer's singing voice ... proactive approach to mitigate unauthorized SVC-based illegal song covers. SongBsAb introduces human ... research direction for mitigating illegal automated song covers. ...

Abstract	Singing voice conversion (SVC) automates song covers by converting one singer's singing voice into another target singer's singing voice with the original lyrics and melody. However, it raises serious concerns about copyright and civil right infringements to multiple entities. This work proposes SongBsAb, the first proactive approach to mitigate unauthorized SVC-based illegal song covers. SongBsAb introduces human-imperceptible perturbations to singing voices before releasing them, so that when they are used, the generation process of SVC will be interfered, resulting in unexpected singing voices. SongBsAb features a dual prevention effect by causing both (singer) identity disruption and lyric disruption, namely, the SVC-covered singing voice neither imitates the target singer nor preserves the original lyrics. To improve the imperceptibility of perturbations, we refine a psychoacoustic model-based loss with the backing track as an additional masker, a unique accompanying element for singing voices compared to ordinary speech voices. To enhance the transferability, we propose to utilize a frame-level interaction reduction-based loss. We demonstrate the prevention effectiveness, utility, and robustness of SongBsAb on three SVC models and two datasets using both objective and human study-based subjective metrics. Our work fosters an emerging research direction for mitigating illegal automated song covers.
Keywords	Computer Science - Sound ; Computer Science - Artificial Intelligence ; Computer Science - Cryptography and Security ; Computer Science - Machine Learning ; Computer Science - Multimedia ; Electrical Engineering and Systems Science - Audio and Speech Processing
Subject code	303 ; 780
Publishing date	2024-01-30
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Generating Tips from Song Reviews

Zang, Jingya / Gao, Cuiyun / Chen, Yupan / Xu, Ruifeng / Zhou, Lanjun / Wang, Xuan

A New Dataset and Framework

2022

Abstract: ... that users can make quicker and more informed decisions when presented with meaningful song reviews ... descriptions about songs. Tips are produced from song reviews and should express non-trivial insights ... for automatically generating tips from song reviews. The dataset involves 8,003 Chinese tips/non-tips from 128 songs ...

Abstract	Reviews of songs play an important role in online music service platforms. Prior research shows that users can make quicker and more informed decisions when presented with meaningful song reviews. However, reviews of music songs are generally long in length and most of them are non-informative for users. It is difficult for users to efficiently grasp meaningful messages for making decisions. To solve this problem, one practical strategy is to provide tips, i.e., short, concise, empathetic, and self-contained descriptions about songs. Tips are produced from song reviews and should express non-trivial insights about the songs. To the best of our knowledge, no prior studies have explored the tip generation task in music domain. In this paper, we create a dataset named MTips for the task and propose a framework named GENTMS for automatically generating tips from song reviews. The dataset involves 8,003 Chinese tips/non-tips from 128 songs which are distributed in five different song genres. Experimental results show that GENTMS achieves top-10 precision at 85.56%, outperforming the baseline models by at least 3.34%. Besides, to simulate the practical usage of our proposed framework, we also experiment with previously-unseen songs, during which GENTMS also achieves the best performance with top-10 precision at 78.89% on average. The results demonstrate the effectiveness of the proposed framework in tip generation of the music domain.
Keywords	Computer Science - Information Retrieval ; Computer Science - Computation and Language
Subject code	780
Publishing date	2022-05-14
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: A Game of Infection - Song of Respiratory Viruses and Interferons.

Wang, Guo Qiang / Gu, Yinuo / Wang, Chao / Wang, Fang / Hsu, Alan Chen-Yu

Frontiers in cellular and infection microbiology

2022 Volume 12, Page(s) 937460

Abstract: Humanity has experienced four major pandemics since the twentieth century, with the 1918 Spanish flu, the 2002 severe acute respiratory syndrome (SARS), the 2009 swine flu, and the 2019 coronavirus disease (COVID)-19 pandemics having the most important ... ...

Abstract	Humanity has experienced four major pandemics since the twentieth century, with the 1918 Spanish flu, the 2002 severe acute respiratory syndrome (SARS), the 2009 swine flu, and the 2019 coronavirus disease (COVID)-19 pandemics having the most important impact in human health. The 1918 Spanish flu caused unprecedented catastrophes in the recorded human history, with an estimated death toll between 50 - 100 million. While the 2002 SARS and 2009 swine flu pandemics caused approximately 780 and 280,000 deaths, respectively, the current COVID-19 pandemic has resulted in > 6 million deaths globally at the time of writing. COVID-19, instigated by the SARS - coronavirus-2 (SARS-CoV-2), causes unprecedented challenges in all facets of our lives, and never before brought scientists of all fields together to focus on this singular topic. While for the past 50 years research have been heavily focused on viruses themselves, we now understand that the host immune responses are just as important in determining the pathogenesis and outcomes of infection. Research in innate immune mechanisms is crucial in understanding all aspects of host antiviral programmes and the mechanisms underpinning virus-host interactions, which can be translated to the development of effective therapeutic avenues. This review summarizes what is known and what remains to be explored in the innate immune responses to influenza viruses and SARS-CoVs, and virus-host interactions in driving disease pathogenesis. This hopefully will encourage discussions and research on the unanswered questions, new paradigms, and antiviral strategies against these emerging infectious pathogens before the next pandemic occurs.
MeSH term(s)	Antiviral Agents/therapeutic use ; COVID-19 ; History, 20th Century ; Humans ; Influenza Pandemic, 1918-1919 ; Influenza, Human/drug therapy ; Interferons ; Pandemics ; SARS-CoV-2 ; Viruses
Chemical Substances	Antiviral Agents ; Interferons (9008-11-1)
Language	English
Publishing date	2022-06-29
Publishing country	Switzerland
Document type	Historical Article ; Journal Article ; Review
ZDB-ID	2619676-1
ISSN	2235-2988 ; 2235-2988
ISSN (online)	2235-2988
ISSN	2235-2988
DOI	10.3389/fcimb.2022.937460
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Book ; Online: Automatic Song Translation for Tonal Languages

Guo, Fenfei / Zhang, Chen / Zhang, Zhirui / He, Qixin / Zhang, Kejun / Xie, Jun / Boyd-Graber, Jordan

2022

Abstract: This paper develops automatic song translation (AST) for tonal languages and addresses the unique ... challenge of aligning words' tones with melody of a song in addition to conveying the original meaning ... design metrics for these criteria. We develop a new benchmark for English--Mandarin song translation and ...

Abstract	This paper develops automatic song translation (AST) for tonal languages and addresses the unique challenge of aligning words' tones with melody of a song in addition to conveying the original meaning. We propose three criteria for effective AST -- preserving meaning, singability and intelligibility -- and design metrics for these criteria. We develop a new benchmark for English--Mandarin song translation and develop an unsupervised AST system, Guided AliGnment for Automatic Song Translation (GagaST), which combines pre-training with three decoding constraints. Both automatic and human evaluations show GagaST successfully balances semantics and singability. Comment: Accepted at Findings of ACL 2022, 15 pages, 4 Tables and 10 Figures
Keywords	Computer Science - Computation and Language ; Computer Science - Artificial Intelligence ; Computer Science - Sound ; Electrical Engineering and Systems Science - Audio and Speech Processing
Publishing date	2022-03-24
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Temporal effects of an original myopia song on school children's myopia and awareness: a 3-year prospective study.

Tong, Liyang / Chen, Jun / Liu, Liqi / Kang, Min / Liao, Xulin / Ying, Ping / Ling, Qian / Zou, Jie / Wei, Hong / Wang, Yixin / Shao, Yi

Clinical & experimental optometry

2023 , Page(s) 1–7

Abstract: ... myopia song in raising school children's awareness of healthier eye use behaviour and on myopia ... in the myopia song group had a significantly shorter AL and less myopic refractive change ... than those in the control group (: Conclusions: An original myopia song performed twice daily in primary schools appeared ...

Abstract	Clinical relevance: Raising children's myopia prevention awareness and behaviour tends to exhibits a protective effect against myopia among schoolchildren. Background: To investigate the effect of an original myopia song in raising school children's awareness of healthier eye use behaviour and on myopia prevention. Methods: In this prospective randomised control study, two groups of students from one primary schools in Jiangxi, China, were enrolled and monitored from grade 3 to grade 6 (2016-2019). The primary outcome was the change in axial length (AL) after the intervention. Secondary outcomes included changes in spherical equivalent refraction (SER), near work and outdoor time, corrected near and distant visual acuity, visual discomfort score (VDS) and accommodative lag. Results: Four hundred students (193 females, 48.25%) aged 9.3 (range 8-10) years with emmetropia to moderate myopia were enrolled. Children in the myopia song group had a significantly shorter AL and less myopic refractive change than those in the control group ( Conclusions: An original myopia song performed twice daily in primary schools appeared to have a modest effect on myopia control among school-aged children by changing their lifestyles in the long term.
Language	English
Publishing date	2023-11-21
Publishing country	United States
Document type	Journal Article
ZDB-ID	639275-1
ISSN	1444-0938 ; 0816-4622
ISSN (online)	1444-0938
ISSN	0816-4622
DOI	10.1080/08164622.2023.2251975
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.B 3168: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Norepinephrine in the avian auditory cortex enhances developmental song learning.

Chen, Yining / Sakata, Jon T

Journal of neurophysiology

2021 Volume 125, Issue 6, Page(s) 2397–2407

Abstract: ... a critical period in development, and the first crucial step in song learning is memorizing the sound of an adult ... conspecific's (tutor's) song. Here, we analyzed the extent to which NE modulates the auditory learning ... of a tutor's song and the fidelity of song imitation. Specifically, we paired infusions of NE or vehicle ...

Abstract	Sensory learning during critical periods in development has lasting effects on behavior. Neuromodulators like dopamine and norepinephrine (NE) have been implicated in various forms of sensory learning, but little is known about their contribution to sensory learning during critical periods. Songbirds like the zebra finch communicate with each other using vocal signals (e.g., songs) that are learned during a critical period in development, and the first crucial step in song learning is memorizing the sound of an adult conspecific's (tutor's) song. Here, we analyzed the extent to which NE modulates the auditory learning of a tutor's song and the fidelity of song imitation. Specifically, we paired infusions of NE or vehicle into the caudomedial nidopallium (NCM) with brief epochs of song tutoring. We analyzed the effect of NE in juvenile zebra finches that had or had not previously been exposed to song. Regardless of previous exposure to song, juveniles that received NE infusions into NCM during song tutoring produced songs that were more acoustically similar to the tutor song and that incorporated more elements of the tutor song than juveniles with control infusions. These data support the notion that NE can regulate the formation of sensory memories that shape the development of vocal behaviors that are used throughout an organism's life.
MeSH term(s)	Animals ; Auditory Cortex/drug effects ; Auditory Cortex/physiology ; Finches ; Learning/physiology ; Male ; Neurotransmitter Agents/administration & dosage ; Neurotransmitter Agents/pharmacology ; Norepinephrine/administration & dosage ; Norepinephrine/pharmacology ; Norepinephrine/physiology ; Vocalization, Animal/physiology
Chemical Substances	Neurotransmitter Agents ; Norepinephrine (X4W3ENH1CV)
Language	English
Publishing date	2021-05-12
Publishing country	United States
Document type	Journal Article ; Research Support, Non-U.S. Gov't
ZDB-ID	80161-6
ISSN	1522-1598 ; 0022-3077
ISSN (online)	1522-1598
ISSN	0022-3077
DOI	10.1152/jn.00612.2020
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Uc I Zs.224: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Song variation of a native songbird in a modified habitat by invasive plant.

Chen, Pan / Chen, Taiyu / Liu, Bin / Zhang, Manyu / Lu, Changhu

Integrative zoology

2021 Volume 17, Issue 1, Page(s) 93–104

Abstract: ... sometimes can dramatically alter native habitats, but the song variation of native songbirds migrating ... passerines have begun to use invaded habitats to breed. In this study, we compared the song type prevalence ... and the song characteristics of male plain prinia Prinia inornata to identify differences in vocal ...

Abstract	Habitat structure has been considered as an important factor affecting the acoustic evolution of birds, and bird songs are increasingly affected by artificial environmental variation. Invasive plants sometimes can dramatically alter native habitats, but the song variation of native songbirds migrating into invaded habitats has received little attention. The invasion of smooth cordgrass Spartina alterniflora in the coastal wetlands of eastern China has drastically altered the vegetation structure and some small passerines have begun to use invaded habitats to breed. In this study, we compared the song type prevalence and the song characteristics of male plain prinia Prinia inornata to identify differences in vocal behavior between native and invaded habitats. We also tested for differences in vocal behavior in relation to singing perch and wind speed variation between different habitats. The results indicated that males of plain prinia in invaded habitats sang shorter songs than those in native habitats and had a lower song diversity. The homogeneous vegetation structure and higher wind speed in invaded habitats likely leads to males changing the traditional perched singing style. The song variation may be related to the founder effect, the alteration of vegetation structure and microclimate in invaded habitats. This finding highlights the need for better understanding the behavioral evolution of native species in the process of adapting to the invaded habitat. In the future, experimental manipulation is needed to ascertain how the invasive plant drove these vocal behavior changes of native songbirds.
MeSH term(s)	Animals ; China ; Introduced Species ; Poaceae ; Songbirds ; Vocalization, Animal ; Wetlands
Language	English
Publishing date	2021-07-16
Publishing country	Australia
Document type	Journal Article
ZDB-ID	2570656-1
ISSN	1749-4877 ; 1749-4869
ISSN (online)	1749-4877
ISSN	1749-4869
DOI	10.1111/1749-4877.12573
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

Order via subito

Details ▾
- Full text online
- Order with fees

To top

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Order via subito