OC17-plan - 版本历史

2017年4月20日 (四) 09:10 Cslt

2017-04-20T09:10:26Z

2017年4月20日 (四) 08:34 Cslt

2017-04-20T08:34:36Z

2017年4月20日 (四) 08:14 Cslt

2017-04-20T08:14:26Z

Cslt：以“ * Constraint on resource. The only constraint is that only the resources listed in the data profile can be used in the system development. * Constra...”为内容创建页面

2017-04-20T08:13:30Z

以“ * Constraint on resource. The only constraint is that only the resources listed in the data profile can be used in the system development. * Constra...”为内容创建页面

新页面

* Constraint on resource. The only constraint is that only the resources listed in the [[OC17-data|data profile]] can be used in the system development.

* Constraint on technology. We do not want to set much limitations on what techniques can be used by participants. Any technologies on front-end, acoustic model, language model, decoding are
applicable. For example, one may want to use some speech enhancement methods to improve quality of the signal, while others may want to train a high-order LM.

* Constraint on tools. Any tools can be used, however, we highly recommend tools publicly available. The tools (internal or external) should not use
any heavy models trained using extra data.
The only exception is the G2P conversion for the English words in OC17-EnWord. You can use some online services or third-party G2P tools
that have been trained using their own database, only that they are publicly available. We think this simulates the real scenario when
new English words are encountered and are required to be handled.

* Constraint on system. Although any open-source tools can be used to construct the system, participants are encouraged to use the Kaldi baseline
provided by the organizer and augment their own novel techniques, so that the community will get more insight what techniques really help.

←上一版本		2017年4月20日 (四) 09:10的版本
第30行：		第30行：
	==Evaluation metric==		==Evaluation metric==

−	* ~~Character~~ error rate ~~(CER~~)/WER	+	* The performance of the submission is evaluated in terms of WER(Word error rate). Each Chinese character is treated as a word.
		+	* The major metric is the over-all WER, which evaluates the entire transcription, including both English and Chinese parts.
		+	* The second metric is the English WER, which evaluates the English part.

@@ 第1行： / 第1行： @@
 ===Constraint on resource===
@@ 第18行： / 第26行： @@
 Constraint on system. Although any open-source tools can be used to construct the system, participants are encouraged to use the Kaldi baseline
 provided by the organizer and augment their own novel techniques, so that the community will get more insight what techniques really help.

@@ 第1行： / 第1行： @@
-* Constraint on technology. We do not want to set much limitations on what techniques can be used by participants. Any technologies on front-end, acoustic model, language model, decoding are
+===Constraint on resource===
 applicable. For example, one may want to use some speech enhancement methods to improve quality of the signal, while others may want to train a high-order LM.
-* Constraint on tools. Any tools can be used, however, we highly recommend tools publicly available. The tools (internal or external) should not use
+===Constraint on tools===
 any heavy models trained using extra data.
 The only exception is the G2P conversion for the English words in OC17-EnWord. You can use some online services or third-party G2P tools
@@ 第11行： / 第15行： @@
 new English words are encountered and are required to be handled.
-* Constraint on system. Although any open-source tools can be used to construct the system, participants are encouraged to use the Kaldi baseline
+===Constraint on system===
 provided by the organizer and augment their own novel techniques, so that the community will get more insight what techniques really help.