1 |
Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Age-related rhythmic variations: The role of syllable intensity variability ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Characterizing speech rhythm using spectral coherence between jaw displacement and speech temporal envelope
|
|
|
|
In: He, Lei; Zhang, Yu (2020). Characterizing speech rhythm using spectral coherence between jaw displacement and speech temporal envelope. Loquens, 7(2):e074. (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Speaker individuality in the durational characteristics of voiced intervals: the case of chinese bi-dialectal speakers ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Joint event extraction based on hierarchical event schemas from framenet
|
|
|
|
Abstract:
Event extraction is useful for many practical applications, such as news summarization and information retrieval. However, the popular automatic context extraction (ACE) event extraction program only defines very limited and coarse event schemas, which may not be suitable for practical applications. FrameNet is a linguistic corpus that defines complete semantic frames and frame-to-frame relations. As frames in FrameNet share highly similar structures with event schemas in ACE and many frames actually express events, we propose to redefine the event schemas based on FrameNet. Specifically, we extract frames expressing event information from FrameNet and leverage the frame-to-frame relations to build a hierarchy of event schemas that are more fine-grained and have much wider coverage than ACE. Based on the new event schemas, we propose a joint event extraction approach that leverages the hierarchical structure of event schemas and frame-to-frame relations in FrameNet. The extensive experiments have verified the advantages of our hierarchical event schemas and the effectiveness of our event extraction model. We further apply the results of our event extraction model on news summarization. The results show that the summarization approach based on our event extraction model achieves significant better performance than several state-of-the-art summarization approaches, which also demonstrates that the hierarchical event schemas and event extraction model are promising to be used in the practical applications.
|
|
URL: https://publications.aston.ac.uk/id/eprint/38848/ https://doi.org/10.1109/ACCESS.2019.2900124 https://publications.aston.ac.uk/id/eprint/38848/1/08643786.pdf
|
|
BASE
|
|
Hide details
|
|
9 |
Speaker individuality in the durational characteristics of voiced intervals : the case of Chinese bi-dialectal speakers
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Speaker individuality in the durational characteristics of voiced intervals: the case of chinese bi-dialectal speakers
|
|
|
|
In: Zhang, Yu; He, Lei; Dellwo, Volker (2019). Speaker individuality in the durational characteristics of voiced intervals: the case of chinese bi-dialectal speakers. In: International Congress of Phonetic Sciences, Melbourne/Australia, 5 August 2019 - 9 August 2019, 3075-3079. (2019)
|
|
BASE
|
|
Show details
|
|
11 |
Development of speech rhythm in first language: The role of syllable intensity variability ...
|
|
He, Lei. - : Acoustical Society of America, 2018
|
|
BASE
|
|
Show details
|
|
12 |
Development of speech rhythm in first language: The role of syllable intensity variability
|
|
He, Lei. - : Acoustical Soc Amer Amer Inst Physics, 2018
|
|
BASE
|
|
Show details
|
|
13 |
Computation of L2 speech rhythm based on duration and fundamental frequency
|
|
|
|
In: Pellegrino, Elisa; He, Lei; Dellwo, Volker (2017). Computation of L2 speech rhythm based on duration and fundamental frequency. In: Trouvain, Jürgen; Steiner, Ingmar; Mobius, Bernd. Elektronische Sprachsignalverarbeitung 2017. Dresden: TUDpress, 246-253. (2017)
|
|
BASE
|
|
Show details
|
|
14 |
Amplitude envelope kinematics of speech signal: parameter extraction and applications
|
|
|
|
In: He, Lei; Dellwo, Volker (2017). Amplitude envelope kinematics of speech signal: parameter extraction and applications. In: Trouvain, Jürgen; Steiner, Ingmar; Möbius, Bernd. Elektronische Sprachsignalverarbeitung 2017. Dresden: TUDpress, 1-8. (2017)
|
|
BASE
|
|
Show details
|
|
15 |
Perception of vocal tract tension: exploring possible prosodic correlates
|
|
|
|
In: San Segundo, Eugenia; Schwab, Sandra; Dellwo, Volker; He, Lei; Mompeán, José (2017). Perception of vocal tract tension: exploring possible prosodic correlates. In: VII Congreso Internacional de Fonética Experimental, Madrid, 22 November 2017 - 24 November 2017. (2017)
|
|
BASE
|
|
Show details
|
|
16 |
Speaker Idiosyncratic Intensity Variability in the Speech Signal
|
|
|
|
In: He, Lei. Speaker Idiosyncratic Intensity Variability in the Speech Signal. 2017, University of Zurich, Faculty of Arts. (2017)
|
|
BASE
|
|
Show details
|
|
17 |
Abstractive news summarization based on event semantic link network
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Exploring differential topic models for comparative summarization of scientific papers
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Speaker idiosyncratic variability of intensity across syllables ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Linguistic Variation in Contact: the Use of erhua and rusheng in the Xianggang Community in China
|
|
|
|
In: Theses - ALL (2014)
|
|
BASE
|
|
Show details
|
|
|
|