Journal Publications:

1.   Muhammad Ghulam, Takaharu Sato, Takashi Fukuda, and Tsuneo Nitta, “Confidence scoring for accurate HMM-based speech recognition by using monophone-level normalization based on subspace method,” IEICE Trans. Inf. & Syst., vol. E86-D, no.3, pp.430-437, March 2003. [PDF]

2.   Muhammad Ghulam, Takashi Fukuda, Kouichi Katsurada, Junsei Horikawa, and Tsuneo Nitta, "PS-ZCPA based features extraction with auditory masking, modulation enhancement and noise reduction for robust ASR," IEICE Trans. Inf. & Syst., vol. E89-D, no.3, pp.1015-1023, March 2006. [PDF]

3.   Muhammad Ghulam, Junsei Horikawa, Kouichi Katsurada, and Tsuneo Nitta, “A pitch-synchronous peak-amplitude (PS-PA) based feature extraction method for noise robust ASR,” IEICE Trans. Inf. & Syst., vol. E89-D, no.11, pp. 2766-2774, November 2006. [PDF]

4.    Mohammad Nurul Huda, Muhammad Ghulam, Takashi Fukuda, Kouichi Katsurada, and Tsuneo Nitta,Canonicalization of Feature Parameters for Robust Speech Recognition Based on Distinctive Phonetic Feature (DPF) Vectors,IEICE Trans. Inf. & Syst., in press, 2007. [PDF]

   (IEICE: The Institute of Electronics, Information & Communication Engineers, Japan)

 

 International Conference Papers:

1.    Takaharu Sato, Muhammad Ghulam, Takashi Fukuda, and Tsuneo Nitta, “Confidence scoring for accurate HMM-based word recognition by using SM-based monophone score normalization,” Proc IEEE ICASSP’02, pp. I-217-220, Orlando, 2002. [PDF]

2.     Muhammad Ghulam, Takashi Fukuda, Takaharu Sato, and Tsuneo Nitta, “Improving performance of an HMM-based ASR system by using monophone-level normalized confidence measure,” Proc. ICSLP’02, vol.4, pp.2453-2456, Denver, Colorado, 2002. [PDF]

3.    Muhammad Ghulam, Takashi Fukuda, and Tsuneo Nitta, “Voice quality normalization in an utterance for robust ASR,” Proc. Eurospeech’03, vol. III, pp. 2173-2176, Geneva, 2003. [PDF] 

4.     Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa, and Tsuneo Nitta, “A noise-robust feature-extraction method based on pitch-synchronous ZCPA for ASR,” Proc. INTERSPEECH-ICSLP’04, vol.I, pp.133-136, Korea, 2004. [PDF] 

5.   Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa, and Tsuneo Nitta, “Pitch-synchronous ZCPA (PS-ZCPA)-based feature extraction with auditory masking,” Proc. IEEE ICASSP’05, pp. I-517-520, Philadelphia, 2005. [PDF]

6.    Takashi Fukuda, Muhammad Ghulam, and Tsuneo Nitta, "Designing multiple distinctive phonetic feature extractors for canonicalization by using clustering technique," Proc. INTERSPEECH'05, pp. 3141-3144, Lisbon, 2005. [PDF]

7.   Muhammad Ghulam, Junsei Horikawa and Tsuneo Nitta, "A pitch-synchronous peak-amplitude based feature extraction method for robust ASR," Proc. IEEE ICASSP'06, pp. I-505-508, Toulouse, France, May 2006. [PDF]

8.    Muhammad Ghulam, Junsei Horikawa and Tsuneo Nitta, “Comparative study on contributions of pitch-synchronization and peak-amplitude towards robustness issue of ASR,” Proc. INTERSPEECH’06, pp. 373-376, Pittsburgh, September 2006. [PDF]

9.    Huda Mohammad Nurul, Muhammad Ghulam, Kouichi Katsurada, Yurie Iribe and Tsuneo Nitta, “Distinctive Phonetic feature (DPF) based phone segmentation using 2-stage multilayer neural networks,” RISP International Workshop on Nonlinear Circuits and Signal Processing (NCSP'07), pp. 325-328, Shanghai, China, March 2007. [PDF]

10.  Huda Mohammad Nurul, Muhammad Ghulam, Junsei Horikawa, and Tsuneo Nitta, Distinctive Phonetic Feature (DPF) Based Phone Segmentation using Hybrid Neural Networks, Proc. INTERSPEECH07, Antwerp, Belgium, August 2007. [PDF]

 

Technical Reports and Seminars (as first author only, in Japan):

1.   Muhammad Ghulam, Takaharu Sato, Takashi Fukuda and Tsuneo Nitta, "Confidence scoring for accurate HMM-based speech recogntion by using monophone-level normalization based on subspace method," Proc. IEICE, SP2002-41, pp.31-36, Sendai, June 2002.  

2.    Muhammad Ghulam and Tsuneo Nitta, "HMM-SM based speaker-independent connected digit recognition by using normalized confidence measure," Proc. Summer meeting of ASJ, pp.61-62, Akita, September 2002. 

3.     Muhammad Ghulam, Takashi Fukuda and Tsuneo Nitta, "Normalizing the acoustic qualities of monophones in an utterance," Proc. IEICE, SP2002-122, pp.7-12, Tokyo, December 2002.

4.    Muhammad Ghulam, Junsei Horikawa and Tsuneo Nitta, "Auditory-motivated front-end processing for robust ASR," Proc. Summer meeting of ASJ, pp.3-4, Nagoya, September 2003.

5.    Muhammad Ghulam, Junsei Horikawa and Tsuneo Nitta, "A pitch-synchronous auditory feature extraction for robust ASR," Proc. Spring meeting of ASJ, pp.149-150, Kanagawa, March 2004.

6.    Muhammad Ghulam, Junsei Horikawa and Tsuneo Nitta, "A pitch-synchronous ZCPA-based feature extraction method for robust ASR," Proc. Technical Report of IEICE, pp.13-18, Yamagata, May 2004.

7.    Muhammad Ghulam, Junsei Horikawa and Tsuneo Nitta, "The pitch-synchronous     ZCPA (PS-ZCPA)-based feature extraction with auditory masking effect," Proc. summer meeting of ASJ, pp.65-66, Okinawa, September 2004.

8.   Muhammad Ghulam, Takashi Fukuda, Junsei Horikawa and Tsuneo Nitta, "Embedding auditory masking into the pitch-synchronous ZCPA (PS-ZCPA)-based feature extractor," Proc. Technical Report of IEICE, SP2004-80, pp.53-58, Toyohashi, November 2004.

9.    Muhammad Ghulam, Junsei Horikawa, and Tsuneo Nitta, "Effect of modulation enhancement and noise reduction on PS-ZCPA based feature extraction method," Proc. Autumn meeting of ASJ, pp.81-82, Sendai, September 2005.

10.    Muhammad Ghulam, Junsei Horikawa, and Tsuneo Nitta, "A pitch-synchronous peak-amplitude (PS-PA) based feature extraction method for noise-robust ASR," Proc. Autumn meeting of ASJ, pp.79-80, Sendai, September 2005.

11.   Muhammad Ghulam, Junsei Horikawa, and Tsuneo Nitta, "A pitch-synchronous peak-amplitude (PS-PA) based feature extraction method with noise-reduction, modulation enhancement and masking for robust ASR," Proc. Technical Report of IEICE, NLC2005-85, SP2005-118, pp.63-64, Tokyo, December 2005.

12.   Muhammad Ghulam, Junsei Horikawa, and Tsuneo Nitta, "Which is dominant: pitch-synchronization (PS) or peak-amplitude (PA) for robust ASR," Proc. Spring meeting of ASJ, pp.93-94, Tokyo, March 2006.

13.  Muhammad Ghulam, Junsei Horikawa, and Tsuneo Nitta, "Study on contributions of pitch-synchronization and peak-amplitudes on robust ASR," Proc. Technical Report of ISPJ, 2006-SLP-62, pp. 37-42, July 2006.