Harald Singer

According to our database, Harald Singer authored at least 28 papers between 1990 and 2000.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2000

Cellular-phone based speech-to-speech translation system ATR-MATRIX.

Rainer Gruhn, Harald Singer, Hajime Tsukada, Masaki Naito, Atsushi Nishino, Atsushi Nakamura, Yoshinori Sagisaka, Satoshi Nakamura

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

1999

Multiple pronunciation dictionary using HMM-state confusion characteristics.

Yumi Wakita, Harald Singer, Yoshinori Sagisaka

Comput. Speech Lang., 1999

Improving n-gram modeling using distance-related unit association maximum entropy language modeling.

Shuwu Zhang, Harald Singer, Dekai Wu, Yoshinori Sagisaka

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Unified framework for acoustic topology modelling: ML-SSS and question-based decision trees.

Harald Singer, Atsushi Nakamura

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Japanese spontaneous speech database with wide regional and age distribution.

Tomoko Matsui, Masaki Naito, Harald Singer, Atsushi Nakamura, Yoshinori Sagisaka

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Speaker normalized spectral subband parameters for noise robust speech recognition.

Satoru Tsuge, Toshiaki Fukuda, Harald Singer

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1997

HMM topology design using maximum likelihood successive state splitting.

Mari Ostendorf, Harald Singer

Comput. Speech Lang., 1997

Speech recognition using HMM-state confusion characteristics.

Yumi Wakita, Harald Singer, Yoshinori Sagisaka

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Maximum likelihood successive state splitting algorithm for tied-mixture HMNET.

Alexandre Girardi, Harald Singer, Kiyohiro Shikano, Satoshi Nakamura

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Fast word-graph generation for spontaneous conversational speech translation.

Tohru Shimizu, Harald Singer, Yoshinori Sagisaka

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

Accent Phrase Segmentation by F₀ Clustering Using Superpositional Modelling.

Mitsuru Nakai, Harald Singer, Yoshinori Sagisaka, Hiroshi Shimodaira

Proceedings of the Computing Prosody, 1997

1996

Maximum likelihood successive state splitting.

Harald Singer, Mari Ostendorf

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

"Pause Units" and Analysis of Spontaneous Japanese Dialogues: Preliminary Studies.

Mark Seligman, Junko Hosaka, Harald Singer

Proceedings of the Dialogue Processing in Spoken Language Systems, 1996

1995

Speaker-Consistent Parsing for Speaker-Independent Continuous Speech Recognition.

Kouichi Yamaguchi, Harald Singer, Shoichi Matsunaga, Shigeki Sagayama

IEICE Trans. Inf. Syst., 1995

Effect of rasta-type processing for speech recognition with speaking-rate mismatches.

Harald Singer, Kuldip K. Paliwal, Tomohiko Beppu, Yoshinori Sagisaka

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

Continuous speech recognition using non-uniform unit based acoustic and language models.

Shoichi Matsunaga, Takeshi Matsumura, Harald Singer

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

Time-synchronous continuous speech recognizer driven by a context-free grammar.

Tohru Shimizu, Seikou Monzen, Harald Singer, Shoichi Matsunaga

Proceedings of the 1995 International Conference on Acoustics, 1995

Automatic prosodic segmentation by F₀ clustering using superpositional modeling.

Mitsuru Nakai, Harald Singer, Yoshinori Sagisaka, Hiroshi Shimodaira

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

Speech recognition without grammar or vocabulary constraints.

Harald Singer, Jun-ichi Takami

Proceedings of the 3rd International Conference on Spoken Language Processing, 1994

Non-uniform unit parsing for SSS-LR continuous speech recognition.

Harald Singer, Jun-ichi Takami, Shoichi Matsunaga

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

Pause As A Phrase Demarcator For Speech And Language Processing.

Junko Hosaka, Mark Seligman, Harald Singer

Proceedings of the 15th International Conference on Computational Linguistics, 1994

1993

Suprasegmental duration control with matrix parsing in continuous speech recognition.

Harald Singer, Shigeki Sagayama

Speech Commun., 1993

Feature extraction using a matrix coefficient filter for speech recognition.

Kazuki Katagishi, Harald Singer, Kiyoaki Aikawa, Shigeki Sagayama

Speech Commun., 1993

ATREUS: a speech recognition front-end for a speech translation system.

Shigeki Sagayama, Jun-ichi Takami, Akito Nagai, Harald Singer, Kouichi Yamaguchi, Kazumi Ohkura, Kenji Kita, Akira Kurematsu

Proceedings of the Third European Conference on Speech Communication and Technology, 1993

Matrix parser and its application to HMM-based speech recognition.

Harald Singer, Shigeki Sagayama

Proceedings of the IEEE International Conference on Acoustics, 1993

A dynamic cepstrum incorporating time-frequency masking and its application to continuous speech recognition.

Kiyoaki Aikawa, Harald Singer, Hideki Kawahara, Yoh'ichi Tohkura

Proceedings of the IEEE International Conference on Acoustics, 1993

1992

Pitch dependent phone modelling for HMM based speech recognition.

Harald Singer, Shigeki Sagayama

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

1990

Low bit quantization of the smoothed group delay spectrum for speech recognition.

Harald Singer, Taizo Umezaki, Fumitada Itakura

Proceedings of the 1990 International Conference on Acoustics, 1990