Filters








17 Hits in 7.6 sec

VoCo

Zeyu Jin, Gautham J. Mysore, Stephen Diverdi, Jingwan Lu, Adam Finkelstein
2017 ACM Transactions on Graphics  
Mysore, Stephen DiVerdi, Jingwan Lu, and Adam Finkelstein. 2017. VoCo: Text-based Insertion and Replacement in Audio Narration. ACM Trans. Graph. 36, 4, Article 96 (July 2017), 13 pages.  ...  Text-based editing provides a natural interface for modifying audio narrations.  ... 
doi:10.1145/3072959.3073702 fatcat:fofvc42v55hhlol4fqpmuyo3oi

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration [article]

Chuanxin Tang, Chong Luo, Zhiyuan Zhao, Dacheng Yin, Yucheng Zhao, Wenjun Zeng
2021 arXiv   pre-print
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript.  ...  In particular, we manage to perform accurate zero-shot duration prediction for the inserted text. The predicted duration is used to regulate both text embedding and speech embedding.  ...  In this paper, we shall address the zero-shot text-based speech insertion problem.  ... 
arXiv:2109.05426v1 fatcat:ytf4cantzjfc7k6bahpfufn3wu

A^3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing [article]

He Bai, Renjie Zheng, Junkun Chen, Xintong Li, Mingbo Ma, Liang Huang
2022 arXiv   pre-print
To address this problem, we propose our framework, Alignment-Aware Acoustic-Text Pretraining (A^3T), which reconstructs masked acoustic signals with text input and acoustic-text alignment during training  ...  In this way, the pretrained model can generate high quality reconstructed spectrogram, which can be applied to the speech editing and unseen speaker TTS directly.  ...  Voco: Text-based insertion and replacement in audio J. H., Johnson, M., Riesa, J., Conneau, A., and Zhang, Y. narration.  ... 
arXiv:2203.09690v2 fatcat:h44bnzrjerge7b33srgsb6txii

Scene-aware audio for 360° videos

Dingzeyu Li, Timothy R. Langlois, Changxi Zheng
2018 ACM Transactions on Graphics  
We present a method for adding scene-aware spatial audio to 360 videos in typical indoor scenes, using only a conventional mono-channel microphone and a speaker.  ...  In our validations, we show that our synthesized spatial audio matches closely with recordings using ambisonic microphones. Lastly, we demonstrate the strength of our method in several applications.  ...  ACKNOWLEDGMENTS We thank Chunxiao Cao for discussing and sharing his bidirectional sound simulation code, Carl Schissler for sharing the "infinite" audio  ... 
doi:10.1145/3197517.3201391 fatcat:oezgtrxtlfcqfaf4it3dvcsa64

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

Chuanxin Tang, Chong Luo, Zhiyuan Zhao, Dacheng Yin, Yucheng Zhao, Wenjun Zeng
2021 Interspeech 2021   unpublished
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript.  ...  In particular, we manage to perform accurate zero-shot duration prediction for the inserted text. The predicted duration is used to regulate both text embedding and speech embedding.  ...  In this paper, we shall address the zero-shot text-based speech insertion problem.  ... 
doi:10.21437/interspeech.2021-189 fatcat:hyzvtxy4eramtbwxycy5cmmjny

The Language of Filmic Audio Description: a Corpus-Based Analysis of Adjectives

Saveria Arma
2011
The corpus-based analysis has been conducted on a corpus of 69 English AD film scripts by means of corpus analysis tools (AntConc and CQP in particular) and has co [...]  ...  Though very recent, audio description has rapidly expanded worldwide and is widely used in English-speaking countries, where it is applied to most audiovisual fields and in particular to cinema, theatre  ...  It is written to be read and delivered aurally and is inserted into another text of which it replaces the video component.  ... 
doi:10.6092/unina/fedoa/8740 fatcat:5pyjj5rimvgxddqm56xj7tlpui

Oral Sessions

2011 International Journal of Paediatric Dentistry  
have a better information where to insert the needle.  ...  replacements.  ...  Sutures can be used safely in all patients. Conclusions: This guideline will help dentists treating patients with EB to provide safe and evidence based treatments.  ... 
doi:10.1111/j.1365-263x.2011.01137.x pmid:21672059 fatcat:yyiyms3t4nd2zh7czwusqjwb2a

Efficient Acoustic Simulation for Immersive Media and Digital Fabrication

Dingzeyu Li
2018
Second, for realistic audio editing in 360° videos, we proposed an inverse material optimization based on fast sound simulation and a hybrid ambisonic audio synthesis that exploits the directional isotropy  ...  in spatial audios.  ...  VoCo allows realistic textbased insertion and replacement of audio narration using a learning-based text to speech conversion which matches the rest of the narration.  ... 
doi:10.7916/d8jt1767 fatcat:bbzc4fflm5ga7ocj5l3a5nlkai

On the use of the digital moving image in retooling the australian political cartooning tradition to a new media context [article]

Lucien Leon, University, The Australian National, University, The Australian National
2017
The observation that the political cartoon has, throughout its history, adapted and evolved in response to various socio-political and technological changes invites the question of how the art form might  ...  In exploring the creative possibilities afforded by new media technologies and analysing where these outcomes intersect with the conventions and functions of political cartoons, the study specifically  ...  Occasionally the artist may insert illustration or text elements.  ... 
doi:10.25911/5d74e2d6a72d8 fatcat:mkjr4uwpp5esnej4fidqb4t6fe

19. Amores 1.13: Oh how I hate to get up in the morning [chapter]

William Turpin
2016 Ovid, Amores (Book 1)  
the α family, but the later date of S (11th cent.) means that its text has "degenerated" and resembles in some particulars the text of β manuscripts.  ...  It is finally revealed that the narrator and the puella are lovers, and it is clear that the narrator has been more than simply a casual eavesdropper.  ...  This editi on of the fi rst book of the collecti on contains the complete Lati n text of Book 1, along with commentary, notes, full vocabulary and embedded audio fi les of the original text read aloud.  ... 
doi:10.11647/obp.0067.18 fatcat:xifml7ufizaznnwiojhmr27ysu

Voicing subjectivity: Artistic Research in the realization of new Vocal Music

Jessica Aszodi, University, My, Vanessa Tomlinson
2018
Voicing Subjectivity argues for vocal subjectivity as a site for exploration and experiment in practice-based, artistic research.  ...  The subjectivities involved in the realization of musical works are now being unpacked and traditional notions of objectivity and concrete meaning as conveyed by musical texts, have eroded.  ...  I am well-practiced in singing text (like in operatic or song repertoire), or singing a piece on one vowel (as in the manner of a conventional vocalise), and in articulating a specific set of non-language-based  ... 
doi:10.25904/1912/1617 fatcat:lc33g7bjmjdg7knpvimnhlyy64

Digital Text and Physical Experience: French Digital Literatures Between Work and Text

Susan Joan Cronin, Apollo-University Of Cambridge Repository, Apollo-University Of Cambridge Repository, Martin Crowley
2019
Digital Text and Physical Experience: French Digital Literatures Between Work and Text Susan Joan Cronin This thesis takes into consideration the presence of computers and electronic equipment in French  ...  It proceeds in the second chapter to explore the materialities and physical factors that have informed the evolution of ideas related to the composition and reading of digital texts, so as to illuminate  ...  phase of static text generation, after which animated and kinetic texts began to replace this initial paradigm.  ... 
doi:10.17863/cam.36390 fatcat:g2lpr5m5o5gqrnlkcswsrtwie4

Sonic Diaspora: Exploring Migration Through Interdisciplinary Soundscape Composition

Carter Joseph Weleminsky
2021
In addition to conducting explorations of contemporary socio-cultural experience, this thesis challenges the domination of written texts within current forms of human inquiry.  ...  This study slowly meandered along a practice-based path, plugging into metaphors from the composer's everyday life, making excursions into issues of empathy, audience and accessibility.  ...  Sounds and music inserted between the spoken texts were collages, which in some way related to the texts and created a certain space. This aided the 'mental digestion' of the spoken words.  ... 
doi:10.25602/gold.00030336 fatcat:7rfrowhyujffxp433k6cbsk2vu

The historical relationship of musical form and the moving image in the current context of the digitisation of media

JOHN DAVEY
2018
The thesis investigates several historical aspects of the relationship of musical form and the moving image, in order to trace their influence in the current context of the general digitisation of media  ...  Music is traditionally a means of expressing multiple elements at once, and relates strongly to the development of modern non-linear forms in which information is presented in the form of a mosaic rather  ...  (He would prefer an 'image-based' rather than a 'text-based' cinema.)  ... 
doi:10.26180/5b9f105e8173b fatcat:kadpkxa4dngqdd6kc3wsmpju2y

Partial Displacement: En/decoding Spectral Thinking in Tristan Murail's Mémoire/Érosion, and Two Compositions for String Quartet

Shih-Wei Lo
2021
First, passive in nature and magnified by the incorporations of the percussion as well as the strings' scratch tones, the reduced presence of pitch in R[o/u]LE(s) signals an attempt to navigate and investigate  ...  can be viewed as an expression of reflecting on issues of intimacy, accessibility, and cultural implications that contemporary music elicits in relation to a valued sector of my personal sphere.  ...  in the recorded text.  ... 
doi:10.7916/d8-gma8-gy71 fatcat:ptv2ksqcufex5b5ylhkkkeeyya
« Previous Showing results 1 — 15 out of 17 results