Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Statistical parametric speech synthesis
2009793 citationsHeiga Zen, Alan W. Black et al.profile →
Statistical parametric speech synthesis using deep neural networks
This map shows the geographic impact of Heiga Zen's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Heiga Zen with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Heiga Zen more than expected).
This network shows the impact of papers produced by Heiga Zen. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Heiga Zen. The network helps show where Heiga Zen may publish in the future.
Co-authorship network of co-authors of Heiga Zen
This figure shows the co-authorship network connecting the top 25 collaborators of Heiga Zen.
A scholar is included among the top collaborators of Heiga Zen based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Heiga Zen. Heiga Zen is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Maia, Ranniery, Heiga Zen, & Mark Gales. (2010). Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters. Cambridge University Engineering Department Publications Database. 88–93.12 indexed citations
9.
Zen, Heiga, Norbert Braunschweiler, Sabine Buchholz, et al.. (2010). HMM-based polyglot speech synthesis by speaker and language adaptive training.. SSW. 186–191.4 indexed citations
10.
Zen, Heiga, Keiichiro Oura, Takashi Nose, et al.. (2009). Recent development of the HMM-based speech synthesis system (HTS). Hokkaido University Collection of Scholarly and Academic Papers (Hokkaido University). 121–130.24 indexed citations
Maia, Ranniery, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, & Keiichi Tokuda. (2007). An Excitation Model for HMM-Based Speech Synthesis Based on Residual Modeling. NAIST Digital Library (Nara Institute of Science and Technology). 131–136.52 indexed citations
13.
Zen, Heiga, Takashi Nose, Junichi Yamagishi, et al.. (2007). The HMM-based speech synthesis system (HTS) version 2.0.. SSW. 294–299.259 indexed citations
14.
Zen, Heiga, Tomoki Toda, Masaru Nakamura, & Keiichi Tokuda. (2007). Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005(Speech and Herring). IEICE Transactions on Information and Systems. 90(1). 325–333.6 indexed citations
15.
Zen, Heiga, et al.. (2007). A Hidden Semi-Markov Model-Based Speech Synthesis System(Speech and Hearing). IEICE Transactions on Information and Systems. 90(5). 825–834.9 indexed citations
16.
Zen, Heiga, et al.. (2005). Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies). IEICE Transactions on Information and Systems. 88(3). 425–431.1 indexed citations
17.
Lima, Amaro A. de, et al.. (2005). Applying Sparse KPCA for Feature Extraction in Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies). IEICE Transactions on Information and Systems. 88(3). 401–409.2 indexed citations
18.
Zen, Heiga, Keiichi Tokuda, & Tadashi Kitamura. (2004). An introduction of trajectory model into HMM-based speech synthesis.. SSW. 191–196.36 indexed citations
19.
Tokuda, Keiichi, Heiga Zen, & Tadashi Kitamura. (2004). Reformulating the HMM as a Trajectory Model. Scientific Programming. 104(538). 43–48.15 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.