| H90-1006 | hand-labeled data . Results for | speaker-dependent training | on two speakers are summarized |
| H91-1009 | speaker-dependent training . The | speaker-dependent training | is described in detail in Section |
| H91-1009 | areas of signal processing and | speaker-dependent training | . The speaker-dependent training |
| H89-1011 | from the prototype speaker . The | speaker-dependent training | procedure in the BYBLOS system |
| H92-1031 | systems given the same amount of | speaker-dependent training | data . <title> RECENT TOPICS |
| H89-1006 | usually achieved using 20 minutes of | speaker-dependent training | . In this project we have combined |
| H89-1011 | initial model generated from the | speaker-dependent training | of a single prototype speaker |
| H89-1010 | same performance as 30-minute | speaker-dependent training | . 4 . Robust Smoothing for Much |
| H91-1080 | usually achieved with 20 minutes of | speaker-dependent training | or with speakerindependent training |
| H90-1079 | usually achieved with 20 minutes of | speaker-dependent training | or with speaker-independent training |
| H89-2058 | usually achieved with 20 minutes of | speaker-dependent training | or with speaker-independent training |
| H89-2037 | thus alleviating the need for | speaker-dependent training | . However , these speaker-independent |
| H89-2034 | compared to those produced by | speaker-dependent training | . Since the adaptation procedures |
| H89-1011 | continuous speech task domain , | speaker-dependent training | uses 30 minutes of speech ( 600 |
| H91-1009 | Using this automatic labeling , | speaker-dependent training | is performed for each of the |
| H91-1054 | speakers . How - ever , when 40 | speaker-dependent training | sentences are used to build the |
| H90-1065 | 7200-sentence resource management | speaker-dependent training | sentences . We show a further |
