Automatic Speech Recognition: Past, Present, and Future

In a method for forming a high aspect ratio structure using copper in an ultra high-speed device, the degree of copper burying is heightened. A high aspect ratio structure, such as a fine connecting hole, is formed in a layer insulating film on a silicon substrate. Then, after a CVD-TiN film is formed to have a thickness of 10 nm on the insulating film, a copper film having a thickness of 1 mug m is formed. In this case, the highly pure copper film is formed by controlling film-forming conditions so as to set oxygen and sulfur concentrations in the film equal to a fixed level or lower. Thus, during its burying in the connecting hole, the surface diffusibility and fluidity of the copper film heated by means of laser irradiation are facilitated.

[1]  Bing Xiang,et al.  Light supervision in acoustic model training , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  H. Van hamme,et al.  Robust speech recognition using cepstral domain missing data techniques and noisy masks , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Jeff A. Bilmes,et al.  Graphical models and automatic speech recognition , 2002 .

[4]  Jean-Luc Gauvain,et al.  Lightly supervised and unsupervised acoustic model training , 2002, Comput. Speech Lang..

[5]  Phil D. Green,et al.  Robust automatic speech recognition with missing and unreliable acoustic data , 2001, Speech Commun..

[6]  Maurizio Omologo,et al.  Speech Recognition with Microphone Arrays , 2001, Microphone Arrays.

[7]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[8]  Jean-Paul Haton,et al.  Neural networks for automatic speech recognition: a review , 1999 .

[9]  Joseph Picone,et al.  Support vector machines for speech recognition , 1998, ICSLP.

[10]  Frederick Jelinek,et al.  Statistical methods for speech recognition , 1997 .

[11]  Hervé Bourlard,et al.  A mew ASR approach based on independent processing and recombination of partial frequency bands , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[12]  Jean-Claude Junqua,et al.  Robustness in Automatic Speech Recognition , 1996 .

[13]  Jean-Claude Junqua,et al.  Robustness in Automatic Speech Recognition: Fundamentals and Applications , 1995 .

[14]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.