A new paradigm for speaker-independent training and speaker adaptation
HLT '90 Proceedings of the workshop on Speech and Natural Language
Improved acoustic modeling for continuous speech recognition
HLT '90 Proceedings of the workshop on Speech and Natural Language
Improved hidden Markov modeling for speaker-independent continuous speech recognition
HLT '90 Proceedings of the workshop on Speech and Natural Language
The Lincoln tied-mixture HMM continuous speech recognizer
HLT '90 Proceedings of the workshop on Speech and Natural Language
Training set issues in SRI's DECIPHER speech recognition system
HLT '90 Proceedings of the workshop on Speech and Natural Language
Experiments with tree-structured MMI encoders on the RM task
HLT '90 Proceedings of the workshop on Speech and Natural Language
Minimizing speaker variation effects for speaker-independent speech recognition
HLT '91 Proceedings of the workshop on Speech and Natural Language
Spontaneous speech effects in large vocabulary speech recognition applications
HLT '91 Proceedings of the workshop on Speech and Natural Language
IEEE Transactions on Audio, Speech, and Language Processing
Speaker normalization for speech recognition
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Supervised and unsupervised clustering of the speaker space for connectionist speech recognition
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
| Hi-index | 0.00 |
The June 1990 DARPA Resource Management Benchmark Test makes use of the first of several test sets provided with the Extended Resource Management Speaker-Dependent Corpus (RM2) [1]. The corpus was designed as a speaker-dependent extension to the Resource Management (RM1) Corpus [2], consisting of (only) four speakers, but with a large number (2400) of sentence utterances for each of these speakers for system training purposes. The corpus was produced on CDROM by NIST in April 1990, and distributed to DARPA contractors. Results have been reported to NIST for both speaker-dependent and speaker-independent systems, and the results of NIST scoring and preliminary analysis of these data are included in this paper. In addition to the June 1990 (RM2) test set results, some sites also reported the results of tests of new algorithms on test sets that have been used in previous results ("test-retest" results), or for new (first-time) use of previous test sets, or for new systems in development. Those results are also tabulated.