Harald Singer

29 papers A 1B 1Misc 7Journal 5Unranked 14
YearRankTypeTitle / Venue / Authors
2000 A conf
Cellular-phone based speech-to-speech translation system ATR-MATRIX.
INTERSPEECH
Rainer Gruhn, Harald Singer, Hajime Tsukada, Masaki Naito, Atsushi Nishino, Atsushi Nakamura, Yoshinori Sagisaka, Satoshi Nakamura
1999 — conf
Improving n-gram modeling using distance-related unit association maximum entropy language modeling.
EUROSPEECH
Shuwu Zhang, Harald Singer, Dekai Wu, Yoshinori Sagisaka
1999 — conf
Japanese spontaneous speech database with wide regional and age distribution.
EUROSPEECH
Tomoko Matsui, Masaki Naito, Harald Singer, Atsushi Nakamura, Yoshinori Sagisaka
1999 J jnl
Multiple pronunciation dictionary using HMM-state confusion characteristics.
Comput. Speech Lang.
Yumi Wakita, Harald Singer, Yoshinori Sagisaka
1999 Misc conf
Speaker normalized spectral subband parameters for noise robust speech recognition.
ICASSP
Satoru Tsuge, Toshiaki Fukuda, Harald Singer
1999 — conf
Unified framework for acoustic topology modelling: ML-SSS and question-based decision trees.
EUROSPEECH
Harald Singer, Atsushi Nakamura
1997 — ch.
Accent Phrase Segmentation by F
Computing Prosody
Mitsuru Nakai, Harald Singer, Yoshinori Sagisaka, Hiroshi Shimodaira
1997 Misc conf
Fast word-graph generation for spontaneous conversational speech translation.
ICASSP
Tohru Shimizu, Harald Singer, Yoshinori Sagisaka
1997 J jnl
HMM topology design using maximum likelihood successive state splitting.
Comput. Speech Lang.
Mari Ostendorf, Harald Singer
1997 — conf
Maximum likelihood successive state splitting algorithm for tied-mixture HMNET.
EUROSPEECH
Alexandre Girardi, Harald Singer, Kiyohiro Shikano, Satoshi Nakamura
1997 — conf
Speech recognition using HMM-state confusion characteristics.
EUROSPEECH
Yumi Wakita, Harald Singer, Yoshinori Sagisaka
1996 — conf
"Pause Units" and Analysis of Spontaneous Japanese Dialogues: Preliminary Studies.
ECAI Workshop on Dialogue Processing in Spoken Language Systems
Mark Seligman, Junko Hosaka, Harald Singer
1996 Misc conf
Maximum likelihood successive state splitting.
ICASSP
Harald Singer, Mari Ostendorf
1995 Misc conf
Automatic prosodic segmentation by F
ICASSP
Mitsuru Nakai, Harald Singer, Yoshinori Sagisaka, Hiroshi Shimodaira
1995 — conf
Continuous speech recognition using non-uniform unit based acoustic and language models.
EUROSPEECH
Shoichi Matsunaga, Takeshi Matsumura, Harald Singer
1995 — conf
Effect of rasta-type processing for speech recognition with speaking-rate mismatches.
EUROSPEECH
Harald Singer, Kuldip K. Paliwal, Tomohiko Beppu, Yoshinori Sagisaka
1995 J jnl
Speaker-Consistent Parsing for Speaker-Independent Continuous Speech Recognition.
IEICE Trans. Inf. Syst.
Kouichi Yamaguchi, Harald Singer, Shoichi Matsunaga, Shigeki Sagayama
1995 Misc conf
Time-synchronous continuous speech recognizer driven by a context-free grammar.
ICASSP
Tohru Shimizu, Seikou Monzen, Harald Singer, Shoichi Matsunaga
1994 — conf
Non-uniform unit parsing for SSS-LR continuous speech recognition.
ICASSP (2)
Harald Singer, Jun-ichi Takami, Shoichi Matsunaga
1994 B conf
Pause As A Phrase Demarcator For Speech And Language Processing.
COLING
Junko Hosaka, Mark Seligman, Harald Singer
1994 — conf
Speaker-consistent parsing for speaker-independent continuous speech recognition.
ICSLP
Kouichi Yamaguchi, Harald Singer, Shoichi Matsunaga, Shigeki Sagayama
1994 — conf
Speech recognition without grammar or vocabulary constraints.
ICSLP
Harald Singer, Jun-ichi Takami
1993 — conf
A dynamic cepstrum incorporating time-frequency masking and its application to continuous speech recognition.
ICASSP (2)
Kiyoaki Aikawa, Harald Singer, Hideki Kawahara, Yoh'ichi Tohkura
1993 — conf
ATREUS: a speech recognition front-end for a speech translation system.
EUROSPEECH
Shigeki Sagayama, Jun-ichi Takami, Akito Nagai, Harald Singer, Kouichi Yamaguchi, Kazumi Ohkura, Kenji Kita, Akira Kurematsu
1993 J jnl
Feature extraction using a matrix coefficient filter for speech recognition.
Speech Commun.
Kazuki Katagishi, Harald Singer, Kiyoaki Aikawa, Shigeki Sagayama
1993 — conf
Matrix parser and its application to HMM-based speech recognition.
ICASSP (2)
Harald Singer, Shigeki Sagayama
1993 J jnl
Suprasegmental duration control with matrix parsing in continuous speech recognition.
Speech Commun.
Harald Singer, Shigeki Sagayama
1992 Misc conf
Pitch dependent phone modelling for HMM based speech recognition.
ICASSP
Harald Singer, Shigeki Sagayama
1990 Misc conf
Low bit quantization of the smoothed group delay spectrum for speech recognition.
ICASSP
Harald Singer, Taizo Umezaki, Fumitada Itakura