Kiyohiro Shikano
Speech & Audio · 1989–2010
A researcher in the Science corpus: 5 papers; trusts 3 researchers and is trusted by 52 researchers here, as inferred from the citation graph.
Subfields
- Speech & Audio — 9 citations into it; #302 of 1,076 by trust here, #210 by citations
- Natural Language Processing — 6 citations into it; #1,528 of 5,688 by trust here, #1,250 by citations
Whom Kiyohiro Shikano trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
Who trusts Kiyohiro Shikano overall
- Li Deng
- Heiga Zen
- C. D. Santos
- Ronan Collobert
- Shaojie Bai
- Wayne Xiong
- Zhizheng Wu
- Jinyu Li
- Graham W. Taylor
- Berrak Sisman
Papers from Kiyohiro Shikano's perspective
Ordered by how strongly the researchers Kiyohiro Shikano trusts endorse each paper. Same corpus, a different order for every researcher.
- The HTK book
- Continuous speech recognition by statistical methods
- Spectral voice conversion for text-to-speech synthesis
- Statistical language modeling using the CMU-cambridge toolkit
- The acoustic-modeling problem in automatic speech recognition
- An introduction to computing with neural nets
- Adaptive Filter Theory
- Adaptive Statistical Language Modeling; A Maximum Entropy Approach
- A Maximum Likelihood Approach to Continuous Speech Recognition
- An Empirical Study of Smoothing Techniques for Language Modeling
Their papers
- Low-delay voice conversion based on maximum likelihood estimation of spectral parameter trajectory (2008) — 1,064 citations
- PAPER Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction Improvements of the One-to-Many Eigenvoice Conversion System (2010) — 5 citations
- GMM-based voice conversion applied to emotional speech synthesis (2003) — 101 citations
- Julius - an open source real-time large vocabulary recognition engine (2001) — 660 citations
- Phoneme recognition using time-delay neural networks (1989)