Results 1 to 10 of about 69,547 (57)
PaperRobot: Incremental Draft Generation of Scientific Ideas
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating ...
Bansal, Mohit+6 more
core +1 more source
Intonation in neurogenic foreign accent syndrome [PDF]
Foreign accent syndrome (FAS) is a motor speech disorder in which changes to segmental as well as suprasegmental aspects lead to the perception of a foreign accent in speech. This paper focuses on one suprasegmental aspect, namely that of intonation.
Kuschmann, Anja+3 more
core +1 more source
Characterizing intonation deficit in motor speech disorders : an autosegmental-metrical analysis of spontaneous speech in hypokinetic dysarthria, ataxic dysarthria and foreign accent syndrome [PDF]
The autosegmental-metrical (AM) framework represents an established methodology for intonational analysis in unimpaired speaker populations but has found little application in describing intonation in motor speech disorders (MSDs).
Kuschmann, Anja, Lowit, Anja
core +1 more source
Proposal for Two Phonetic Characters [PDF]
This is a proposal to add two phonetic characters to the international character encoding standard Unicode.
Anderson, Deborah+3 more
core
Seven Dimensions of Portability for Language Documentation and Description
The process of documenting and describing the world's languages is undergoing radical transformation with the rapid uptake of new digital technologies for capture, storage, annotation and dissemination.
Bird, Steven, Simons, Gary
core +6 more sources
The emergence of prosody in linguistic theory [PDF]
Prosody is a unique character in the production of sounds. Human speech is particularly marked by prosody for various functions in the different aspects of linguistics (e.g. phonology, morphology, sociolinguistics).
Parawahera, Nimal P.
core
A lexical database tool for quantitative phonological research
A lexical database tool tailored for phonological research is described. Database fields include transcriptions, glosses and hyperlinks to speech files.
Bird, Steven
core +3 more sources
Comparison of Decoding Strategies for CTC Acoustic Models
Connectionist Temporal Classification has recently attracted a lot of interest as it offers an elegant approach to building acoustic models (AMs) for speech recognition.
Metze, Florian+6 more
core +1 more source
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018 [PDF]
This paper describes FBK's submission to the end-to-end English-German speech translation task at IWSLT 2018. Our system relies on a state-of-the-art model based on LSTMs and CNNs, where the CNNs are used to reduce the temporal dimension of the audio ...
Cattoni, Roldano+4 more
core +1 more source
Annotation graphs and annotation servers offer infrastructure to support the analysis of human language resources in the form of time-series data such as text, audio and video.
Bird, Steven, Cieri, Christopher
core +1 more source