Title :
Recognising Speech in the Presence of a Competing Speaker using a `Speech Fragment Decoder´
Author :
Coy, Andre ; Barker, Jon
Author_Institution :
Dept. of Comput. Sci., Univ. of Sheffield, UK
fDate :
March 18-23, 2005
Keywords :
harmonic analysis; signal representation; source separation; speech recognition; ASR search; competing speaker; competing speech source; cross-gender mixtures; harmonic energy components; image processing techniques; matched-gender utterances; pitch information; single acoustic source fragments; spectral representation subset; spectro-temporal fragments; spectrogram inharmonic region segmentation; speech fragment decoder; speech model sequence; speech recognition; Acoustic noise; Acoustic testing; Automatic speech recognition; Decoding; Microphones; Signal processing; Speech coding; Speech enhancement; Speech recognition; Time frequency analysis;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415141
