Remote tracing and debugging of automatic speech recognition servers by speech reconstruction from cepstra and pitch information
申请公布号:US7783488(B2)
申请号:US20050311753
申请日期:2005.12.19
申请公布日期:2010.08.24
发明人:BEN-DAVID SHAY;MANDALIA BAIJU DHIRAJLAL;SIVAN ZOHAR;SORIN ALEXANDER
分类号:G06K9/00;G06F17/27;G10L15/00;G10L21/00
主分类号:G06K9/00
摘要:Methods and systems are provided for remote tuning and debugging of an automatic speech recognition system. Trace files are generated on-site from input speech by efficient, lossless compression of MFCC data, which is merged with compressed pitch and voicing information and stored as trace files. The trace files are transferred to a remote site where human-intelligible speech is reconstructed and analyzed. Based on the analysis, parameters of the automatic speech recognition system are remotely adjusted.