Ahmad Hashemi-Sakhtsari

Learn More
Speech recognition can potentially aid in producing transcripts of discussions, interviews, meetings, and other collaborative efforts. This report presents a concept demonstrator of an automatic transcription system that produces text and audio records using speaker dependent speech recognition. It is defined and discussed in terms of how it works, how(More)
This paper presents a sensor array position calibration algorithm for determining the positions of individual microphones in a linear array automatically from time-difference of arrival measurements obtained from a mobile sounding source. The algorithm uses a nonlinear least squares method to determine the interspacing of microphones that are located along(More)
A simple recursive tracking algorithm for moving sources is developed based on time difference of arrival (TDOA) measurements. The proposed algorithm uses location estimates obtained from a stationary source localization algorithm and smoothes them according to a general motion model for the source. The motion model allows for source acceleration. A unified(More)
This paper investigates the performance of three speaker-independent speech recognisers (SISRs) that support continuous speech and are currently available for speaker-independent recognition of English. These speech recognisers were tested using a subset of the Australian National Database Of Spoken Language (ANDOSL) for the recognition of digits, sentences(More)
This paper presents a three dimensional sensor and source position calibration algorithm for automatically determining the positions of individual microphones in a three dimensional space with at least one linear sub array of sensors. Time-difference of arrival measurements were obtained from a mobile sounding source. The algorithm uses a nonlinear least(More)
This paper introduces a Direction of Arrival (DOA) estimation technique for microphone arrays that has improved robustness in reverberant environments. The technique applies a separate beamformer at each frequency to estimate the DOA of the speech signal at that frequency. A histogram of the DOA estimates from all frequencies is then formed, which(More)
  • 1