| tech,9-9-H90-1060,ak | the <term> target speaker </term> for <term> | adaptation | </term> , the <term> error rate </term> dropped | #21255 Using only 40 utterances from the target speaker foradaptation, the error rate dropped to 4.1% --- a 45% reduction in error compared to the SI result. | |
| other,10-5-H90-1060,ak | comparable to our best condition for this <term> | test suite | </term> , using 109 <term> training speakers | #21170 This performance is comparable to our best condition for thistest suite, using 109 training speakers. | |
| tech,6-4-H90-1060,ak | 12 <term> training speakers </term> for <term> | SI recognition | </term> , we achieved a 7.5 % <term> word error | #21135 With only 12 training speakers forSI recognition, we achieved a 7.5% word error rate on a standard grammar and test set from the DARPA Resource Management corpus. | |
| model,14-2-H90-1060,ak | speaker-independent ( SI ) training </term> of <term> | hidden Markov models ( HMM ) | </term> , which uses a large amount of <term> | #21062 First, we present a new paradigm for speaker-independent (SI) training ofhidden Markov models ( HMM ), which uses a large amount of speech from a few speakers instead of the traditional practice of using a little speech from many speakers. | |
| other,26-6-H90-1060,ak | amount of <term> speech </term> from the <term> | new ( target ) speaker | </term> . A <term> probabilistic spectral mapping | #21204 Second, we show a significant improvement for speaker adaptation (SA) using the new SI corpus and a small amount of speech from thenew ( target ) speaker. | |
| other,16-7-H90-1060,ak | reference ) speaker </term> and the <term> | target speaker | </term> . Each <term> reference model </term> | #21226 A probabilistic spectral mapping is estimated independently for each training (reference) speaker and thetarget speaker. | |
| tech,7-1-H90-1060,ak | paper reports on two contributions to <term> | large vocabulary continuous speech recognition | </term> . First , we present a new paradigm | #21042 This paper reports on two contributions tolarge vocabulary continuous speech recognition. | |
| other,44-2-H90-1060,ak | of using a little speech from many <term> | speakers | </term> . In addition , combination of the | #21092 First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount of speech from a few speakers instead of the traditional practice of using a little speech from manyspeakers. | |
| other,15-5-H90-1060,ak | <term> test suite </term> , using 109 <term> | training speakers | </term> . Second , we show a significant | #21175 This performance is comparable to our best condition for this test suite, using 109training speakers. | |
| lr-prod,26-4-H90-1060,ak | </term> and <term> test set </term> from the <term> | DARPA Resource Management corpus | </term> . This performance is comparable | #21155 With only 12 training speakers for SI recognition, we achieved a 7.5% word error rate on a standard grammar and test set from theDARPA Resource Management corpus. | |
| tech,33-3-H90-1060,ak | many <term> speakers </term> prior to <term> | training | </term> . With only 12 <term> training speakers | #21127 In addition, combination of the training speakers is done by averaging the statistics of independently trained models rather than the usual pooling of all the speech data from many speakers prior totraining. | |
| lr,16-6-H90-1060,ak | adaptation ( SA ) </term> using the new <term> | SI corpus | </term> and a small amount of <term> speech | #21194 Second, we show a significant improvement for speaker adaptation (SA) using the newSI corpus and a small amount of speech from the new (target) speaker. | |
| other,10-8-H90-1060,ak | is transformed to the space of the <term> | target speaker | </term> and combined by averaging . Using | #21239 Each reference model is transformed to the space of thetarget speaker and combined by averaging. | |
| lr,20-4-H90-1060,ak | word error rate </term> on a standard <term> | grammar | </term> and <term> test set </term> from the <term> | #21149 With only 12 training speakers for SI recognition, we achieved a 7.5% word error rate on a standardgrammar and test set from the DARPA Resource Management corpus. | |
| other,9-7-H90-1060,ak | is estimated independently for each <term> | training ( reference ) speaker | </term> and the <term> target speaker </term> | #21219 A probabilistic spectral mapping is estimated independently for eachtraining ( reference ) speaker and the target speaker. | |
| measure(ment),12-9-H90-1060,ak | </term> for <term> adaptation </term> , the <term> | error rate | </term> dropped to 4.1 % --- a 45 % reduction | #21258 Using only 40 utterances from the target speaker for adaptation, theerror rate dropped to 4.1% --- a 45% reduction in error compared to the SI result. | |
| other,6-9-H90-1060,ak | 40 <term> utterances </term> from the <term> | target speaker | </term> for <term> adaptation </term> , the <term> | #21252 Using only 40 utterances from thetarget speaker for adaptation, the error rate dropped to 4.1% --- a 45% reduction in error compared to the SI result. | |
| other,3-4-H90-1060,ak | <term> training </term> . With only 12 <term> | training speakers | </term> for <term> SI recognition </term> , we | #21132 With only 12training speakers for SI recognition, we achieved a 7.5% word error rate on a standard grammar and test set from the DARPA Resource Management corpus. | |
| lr,27-2-H90-1060,ak | </term> , which uses a large amount of <term> | speech | </term> from a few <term> speakers </term> instead | #21075 First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount ofspeech from a few speakers instead of the traditional practice of using a little speech from many speakers. | |
| lr,26-3-H90-1060,ak | usual <term> pooling </term> of all the <term> | speech data | </term> from many <term> speakers </term> prior | #21120 In addition, combination of the training speakers is done by averaging the statistics of independently trained models rather than the usual pooling of all thespeech data from many speakers prior to training. |
