Getting started with SUSAS: a speech under simulated and actual stress database. JHL Hansen, SE Bou-Ghazale, R Sarikaya, B Pellom Eurospeech 97 (4), 1743-46, 1997 | 440 | 1997 |
A comparative study of traditional and newly proposed features for recognition of speech under stress SE Bou-Ghazale, JHL Hansen IEEE Transactions on speech and audio processing 8 (4), 429-442, 2000 | 346 | 2000 |
System and method for an endpoint detection of speech for improved speech recognition in noisy environments SE Bou-Ghazale, AO Asadi, K Assaleh US Patent 8,175,876, 2012 | 171 | 2012 |
System and method for an endpoint detection of speech for improved speech recognition in noisy environment S Bou-Ghazale, A Asadi, K Assaleh US Patent App. 11/903,290, 2008 | 128 | 2008 |
Robust speech boundary detection system and method SE Bou-Ghazale, T Thormundsson, WB Wu US Patent 9,886,968, 2018 | 102 | 2018 |
A robust endpoint detection of speech for noisy environments with application to automatic speech recognition SE Bou-Ghazale, K Assaleh 2002 IEEE International Conference on Acoustics, Speech, and Signal …, 2002 | 89 | 2002 |
HMM-based stressed speech modeling with application to improved synthesis and recognition of isolated speech under stress SE Bou-Ghazale, JHL Hansen IEEE Transactions on Speech and Audio Processing 6 (3), 201-216, 1998 | 51 | 1998 |
Robust speech recognition training via duration and spectral-based stress token generation JHL Hansen, SE Bou-Ghazale IEEE Transactions on Speech and Audio Processing 3 (5), 415-421, 1995 | 43 | 1995 |
System and method for a endpoint detection of speech for improved speech recognition in noisy environments SE Bou-Ghazale, AO Asadi, K Assaleh US Patent 7,277,853, 2007 | 42 | 2007 |
Computationally efficient background noise suppressor for speech coding and speech recognition SE Bou-Ghazale US Patent 7,133,825, 2006 | 36 | 2006 |
Generating stressed speech from neutral speech using a modified CELP vocoder SE Bou-Ghazale, JHL Hansen Speech Communication 20 (1-2), 93-110, 1996 | 33 | 1996 |
Duration and spectral based stress token generation for HMM speech recognition under stress SE Bou-Ghazale, JHL Hansen Proceedings of ICASSP'94. IEEE International Conference on Acoustics, Speech …, 1994 | 32 | 1994 |
Stress perturbation of neutral speech for synthesis based on hidden Markov models LUKR WP IEEE Transactions on Speech & Audio Processing 6, 201-216, 1998 | 26 | 1998 |
Hands-free voice activation of personal communication devices SE Bou-Ghazale, AO Asadi 2000 IEEE International Conference on Acoustics, Speech, and Signal …, 2000 | 13 | 2000 |
Duration and spectral based stress token generation for keyword recognition using hidden Markov models JHL Hansen IEEE Trans. Speech Audio Process. 3 (5), 415-421, 1995 | 12 | 1995 |
Duration and spectral based stress token generation for keyword recognition using hidden Markov models SE Bou-Ghazale Duke University, 1993 | 11 | 1993 |
A novel training approach for improving speech recognition under adverse stressful conditions SE Bou-Ghazale, JHL Hansen Fifth European Conference on Speech Communication and Technology, 1997 | 10 | 1997 |
Speech feature modeling for robust stressed speech recognition SE Bou-Ghazale, JHL Hansen Fifth International Conference on Spoken Language Processing, 1998 | 9 | 1998 |
A source generator based modeling framework for synthesis of speech under stress SE Bou-Ghazale, JHL Hansen 1995 International Conference on Acoustics, Speech, and Signal Processing 1 …, 1995 | 9 | 1995 |
Improving recognition and synthesis of stressed speech via feature perturbation in a source generator framework SE Bou-Ghazale, JHL Harisen Proc. SUS 1995, 45-48, 1995 | 7 | 1995 |