Speech Recognition for Education - Revision history

Ryan: correction

2022-06-10T10:09:09Z

correction

← Older revision		Revision as of 06:09, 10 June 2022
Line 1:		Line 1:
	Wang et al. (2018) [https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses pdf]		Wang et al. (2018) [https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses pdf]
	*Automated scoring model for evaluating English spoken responses		*Automated scoring model for evaluating English spoken responses
	*SpeechRater gave a significantly lower score than human raters for German		*SpeechRater gave a significantly lower score than human raters for German students
	*SpeechRater ~~scored in favor of Chinese group~~, with H1-rater scores higher than mean		*SpeechRater gave higher scores to students from China than human raters, with H1-rater scores higher than mean

Seiyon at 00:42, 18 May 2022

2022-05-18T00:42:05Z

← Older revision		Revision as of 20:42, 17 May 2022
Line 1:		Line 1:
	Wang et al. (2018) [[https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses pdf]]		Wang et al. (2018) [https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses pdf]
	*Automated scoring model for evaluating English spoken responses		*Automated scoring model for evaluating English spoken responses
	*SpeechRater gave a significantly lower score than human raters for German		*SpeechRater gave a significantly lower score than human raters for German
Line 5:		Line 5:


	Loukina & Buzick (2017) [[https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/ets2.12170 pdf]]		Loukina & Buzick (2017) [https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/ets2.12170 pdf]
	*a model (the SpeechRater) automatically scoring open-ended spoken responses for speakers with documented or suspected speech impairments		*a model (the SpeechRater) automatically scoring open-ended spoken responses for speakers with documented or suspected speech impairments
	*SpeechRater was less accurate for test takers who were deferred for signs of speech impairment (ρ<sup>2</sup> = .57) than test takers who were given accommodations for documented disabilities (ρ<sup>2</sup> = .73)		*SpeechRater was less accurate for test takers who were deferred for signs of speech impairment (ρ<sup>2</sup> = .57) than test takers who were given accommodations for documented disabilities (ρ<sup>2</sup> = .73)


	Loukina et al. (2019) [[https://aclanthology.org/W19-4401.pdf pdf]]		Loukina et al. (2019) [https://aclanthology.org/W19-4401.pdf pdf]
	*Models providing automated speech scores on English language proficiency assessment		*Models providing automated speech scores on English language proficiency assessment
	*L1-specific model trained on the speaker’s native language was the least fair, especially for Chinese, Japanese, and Korean speakers, but not for German speakers		*L1-specific model trained on the speaker’s native language was the least fair, especially for Chinese, Japanese, and Korean speakers, but not for German speakers
	*All models (Baseline, Fair feature subset, L1-specific) performed ~~disadvantageously~~ for Japanese speakers		*All models (Baseline, Fair feature subset, L1-specific) performed worse for Japanese speakers

Seiyon at 20:31, 28 March 2022

2022-03-28T20:31:54Z

← Older revision		Revision as of 16:31, 28 March 2022
Line 8:		Line 8:
	*a model (the SpeechRater) automatically scoring open-ended spoken responses for speakers with documented or suspected speech impairments		*a model (the SpeechRater) automatically scoring open-ended spoken responses for speakers with documented or suspected speech impairments
	*SpeechRater was less accurate for test takers who were deferred for signs of speech impairment (ρ<sup>2</sup> = .57) than test takers who were given accommodations for documented disabilities (ρ<sup>2</sup> = .73)		*SpeechRater was less accurate for test takers who were deferred for signs of speech impairment (ρ<sup>2</sup> = .57) than test takers who were given accommodations for documented disabilities (ρ<sup>2</sup> = .73)


			Loukina et al. (2019) [[https://aclanthology.org/W19-4401.pdf pdf]]
			*Models providing automated speech scores on English language proficiency assessment
			*L1-specific model trained on the speaker’s native language was the least fair, especially for Chinese, Japanese, and Korean speakers, but not for German speakers
			*All models (Baseline, Fair feature subset, L1-specific) performed disadvantageously for Japanese speakers

Seiyon at 18:10, 15 February 2022

2022-02-15T18:10:55Z

← Older revision		Revision as of 14:10, 15 February 2022
Line 3:		Line 3:
	*SpeechRater gave a significantly lower score than human raters for German		*SpeechRater gave a significantly lower score than human raters for German
	*SpeechRater scored in favor of Chinese group, with H1-rater scores higher than mean		*SpeechRater scored in favor of Chinese group, with H1-rater scores higher than mean


			Loukina & Buzick (2017) [[https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/ets2.12170 pdf]]
			*a model (the SpeechRater) automatically scoring open-ended spoken responses for speakers with documented or suspected speech impairments
			*SpeechRater was less accurate for test takers who were deferred for signs of speech impairment (ρ<sup>2</sup> = .57) than test takers who were given accommodations for documented disabilities (ρ<sup>2</sup> = .73)

Seiyon at 03:27, 26 January 2022

2022-01-26T03:27:32Z

← Older revision	Revision as of 23:27, 25 January 2022
Line 1:	Line 1:
		Wang et al. (2018) [[https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses pdf]]
		*Automated scoring model for evaluating English spoken responses
		*SpeechRater gave a significantly lower score than human raters for German
		*SpeechRater scored in favor of Chinese group, with H1-rater scores higher than mean

Seiyon: Blanked the page

2022-01-24T09:36:17Z

Blanked the page

← Older revision		Revision as of 05:36, 24 January 2022
Line 1:		Line 1:
	~~Wang et al. (2018) [[https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses page]]~~
	* Automated scoring model for evaluating English spoken responses
	*SpeechRater gave a significantly lower score than human raters for German
	*SpeechRater scored in favor of Chinese group, with H1-rater scores higher than mean

Seiyon at 09:33, 24 January 2022

2022-01-24T09:33:54Z

← Older revision		Revision as of 05:33, 24 January 2022
Line 1:		Line 1:
	Wang et al. (2018) [[https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses ~~pdf~~]]		Wang et al. (2018) [[https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses page]]
	* ~~SpeechRater system~~ for evaluating ~~communicative competence in~~ English		* Automated scoring model for evaluating English spoken responses
	*~~performance particularly low~~ for ~~native speakers of~~ German ~~and Telugu~~		*SpeechRater gave a significantly lower score than human raters for German
	*~~systematically bias upwards for~~ Chinese ~~students and downwards for German students~~		*SpeechRater scored in favor of Chinese group, with H1-rater scores higher than mean

Seiyon at 06:31, 24 January 2022

2022-01-24T06:31:54Z

← Older revision		Revision as of 02:31, 24 January 2022
Line 1:		Line 1:
	~~Bridgeman, Trapani, and Attali~~ (~~2012~~) [pdf]		Wang et al. (2018) [[https://www.researchgate.net/publication/336009443_Monitoring_the_performance_of_human_and_automated_scores_for_spoken_responses pdf]]
			* SpeechRater system for evaluating communicative competence in English
	* ~~A later version of E-Rater~~ system for ~~automatic grading of GSE essay~~		*performance particularly low for native speakers of German and Telugu
	* ~~Model gave lower scores to~~ speakers of ~~Arabic~~ and ~~Hindi~~		*systematically bias upwards for Chinese students and downwards for German students

Seiyon: Added Entry

2022-01-24T06:12:00Z

Added Entry

New page

Bridgeman, Trapani, and Attali (2012) [pdf]

* A later version of E-Rater system for automatic grading of GSE essay
* Model gave lower scores to speakers of Arabic and Hindi