DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 38

1
Fine-grained style control in Transformer-based Text-to-speech Synthesis ...
Chen, Li-Wei; Rudnicky, Alexander. - : arXiv, 2021
Abstract: In this paper, we present a novel architecture to realize fine-grained style control on the transformer-based text-to-speech synthesis (TransformerTTS). Specifically, we model the speaking style by extracting a time sequence of local style tokens (LST) from the reference speech. The existing content encoder in TransformerTTS is then replaced by our designed cross-attention blocks for fusion and alignment between content and style. As the fusion is performed along with the skip connection, our cross-attention block provides a good inductive bias to gradually infuse the phoneme representation with a given style. Additionally, we prevent the style embedding from encoding linguistic content by randomly truncating LST during training and using wav2vec 2.0 features. Experiments show that with fine-grained style control, our system performs better in terms of naturalness, intelligibility, and style transferability. Our code and samples are publicly available. ... : Accepted in ICASSP 2022 ...
Keyword: Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG; Sound cs.SD
URL: https://dx.doi.org/10.48550/arxiv.2110.06306
https://arxiv.org/abs/2110.06306
BASE
Hide details
2
Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection ...
BASE
Show details
3
Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021 ...
BASE
Show details
4
Internationalizing Speech Technology through Language Independent Lexical Acquisition ...
BASE
Show details
5
Internationalizing Speech Technology through Language Independent Lexical Acquisition ...
BASE
Show details
6
Building a Vocabulary Self-Learning Speech Recognition System ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2014
BASE
Show details
7
Building a Vocabulary Self-Learning Speech Recognition System ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2014
BASE
Show details
8
Finding Recurrent Out-of-Vocabulary Words ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2013
BASE
Show details
9
Finding Recurrent Out-of-Vocabulary Words ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2013
BASE
Show details
10
Learning better lexical properties for recurrent OOV words ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2013
BASE
Show details
11
Learning better lexical properties for recurrent OOV words ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2013
BASE
Show details
12
OOV Word Detection using Hybrid Models with Mixed Types of Fragments ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2012
BASE
Show details
13
OOV Word Detection using Hybrid Models with Mixed Types of Fragments ...
Qin, Long; Rudnicky, Alexander. - : Carnegie Mellon University, 2012
BASE
Show details
14
Modeling Lexical Stress in Read and Spontaneous Speech ...
Polifroni, Joseph H; Rudnicky, Alexander. - : Carnegie Mellon University, 2011
BASE
Show details
15
Modeling Lexical Stress in Read and Spontaneous Speech ...
Polifroni, Joseph H; Rudnicky, Alexander. - : Carnegie Mellon University, 2011
BASE
Show details
16
The "RavenClaw" dialog management framework: architecture and systems
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 23 (2009) 3, 332-361
BLLDB
OLC Linguistik
Show details
17
The Lexical Access Component of the CMU Continuous Speech Recognition System ...
Rudnicky, Alexander; Baurneister, Lynn K; DeGraaf, Kevin H. - : Carnegie Mellon University, 2008
BASE
Show details
18
The Lexical Access Component of the CMU Continuous Speech Recognition System ...
Rudnicky, Alexander; Baurneister, Lynn K; DeGraaf, Kevin H. - : Carnegie Mellon University, 2008
BASE
Show details
19
Language-Independent Lexical Acquisition ...
Damiba, Bertrand A; Rudnicky, Alexander. - : Carnegie Mellon University, 2005
BASE
Show details
20
Language-Independent Lexical Acquisition ...
Damiba, Bertrand A; Rudnicky, Alexander. - : Carnegie Mellon University, 2005
BASE
Show details

Page: 1 2

Catalogues
0
0
3
0
0
0
0
Bibliographies
6
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
30
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern