Results 1 - 10
of
17
A Scalable Architecture For Web Deployment of Spoken Dialogue Systems
"... We describe a scalable architecture, particularly well-suited to cloud-based computing, which can be used for Web-deployment of spoken dialogue systems. In common with similar platforms, like WAMI and the Nuance Mobile Developer Platform, we use a client/server approach in which speech recognition i ..."
Abstract
-
Cited by 7 (7 self)
- Add to MetaCart
(Show Context)
We describe a scalable architecture, particularly well-suited to cloud-based computing, which can be used for Web-deployment of spoken dialogue systems. In common with similar platforms, like WAMI and the Nuance Mobile Developer Platform, we use a client/server approach in which speech recognition is carried out on the server side; our architecture, however, differs from these systems in offering considerably more elaborate server-side functionality, based on large-scale grammar-based language processing and generic dialogue management. We describe two substantial applications, built using our framework, which we argue would have been hard to construct in WAMI or NMDP. Finally, we present a series of evaluations carried out using CALL-SLT, a speech translation game, where we contrast performance in Web and desktop versions. Task Error Rate in the Web version is only slightly inferior that in the desktop one, and the average additional latency is under half a second. The software is generally available for research purposes.
For a Fistful of Dollars: Using Crowd-Sourcing to Evaluate a Spoken Language CALL Application
- in Proc. SLaTE
, 2011
"... We present an evaluation of a Web-deployed spoken lan-guage CALL system, carried out using crowd-sourcing meth-ods. The system, “Survival Japanese”, is a crash course in tourist Japanese implemented within the platform CALL-SLT. The evaluation was carried out over one week using the Ama-zon Mechanic ..."
Abstract
-
Cited by 5 (3 self)
- Add to MetaCart
(Show Context)
We present an evaluation of a Web-deployed spoken lan-guage CALL system, carried out using crowd-sourcing meth-ods. The system, “Survival Japanese”, is a crash course in tourist Japanese implemented within the platform CALL-SLT. The evaluation was carried out over one week using the Ama-zon Mechanical Turk. Although we found a high proportion of attempted scammers, there was a core of 23 subjects who used the system in a responsible manner. The evidence that these subjects learned from their 111 sessions and 9092 spoken in-teractions was significant at P =0.001. Our conclusion is that crowd-sourcing is a potentially valid method for evaluating spo-ken CALL systems. Index Terms: CALL, crowd-sourcing, speech recognition, evaluation, Japanese
2012. Evaluating appropriateness of system responses in a spoken call game
- In Proceedings of LREC 2012
"... We describe an experiment carried out using a French version of CALL-SLT, a web-enabled CALL game in which students at each turn are prompted to give a semi-free spoken response which the system then either accepts or rejects. The central question we investigate is whether the response is appropriat ..."
Abstract
-
Cited by 5 (5 self)
- Add to MetaCart
(Show Context)
We describe an experiment carried out using a French version of CALL-SLT, a web-enabled CALL game in which students at each turn are prompted to give a semi-free spoken response which the system then either accepts or rejects. The central question we investigate is whether the response is appropriate; we do this by extracting pairs of utterances where both members of the pair are responses by the same student to the same prompt, and where one response is accepted and one rejected. When the two spoken responses are presented in random order, native speakers show a reasonable degree of agreement in judging that the accepted utterance is better than the rejected one. We discuss the significance of the results and also present a small study supporting the claim that native speakers are nearly always recognised by the system, while non-native speakers are rejected a significant proportion of the time.
Using a serious game to collect a child learner speech corpus
- in Proceedings of LREC 2014
, 2014
"... We present an English-L2 child learner speech corpus, produced by Swiss German-L1 students in their third year of learning English, which is currently in the process of being collected. The collection method uses a web-enabled multimodal language game implemented using the CALL-SLT platform, in whic ..."
Abstract
-
Cited by 5 (5 self)
- Add to MetaCart
(Show Context)
We present an English-L2 child learner speech corpus, produced by Swiss German-L1 students in their third year of learning English, which is currently in the process of being collected. The collection method uses a web-enabled multimodal language game implemented using the CALL-SLT platform, in which subjects hold prompted conversations with an animated agent. Prompts consist of a short animated Engligh-language video clip together with a German-language piece of text indicating the semantic content of the requested response. Grammar-based speech understanding is used to decide whether responses are accepted or rejected, and dialogue flow is controlled using a simple XML-based scripting language; the scripts are written to allow multiple dialogue paths, the choice being made randomly. The system is gamified using a score-and-badge framework with four levels of badges. We describe the application, the data collection and annotation procedures, and the initial tranche of data. The full corpus, when complete, should contain at least 5 000 annotated utterances.
Methodological Issues in Evaluating a Spoken CALL Game: Can Crowdsourcing Help Us Perform Controlled Experiments?
"... We summarise a series of experiments we have carried out over the last three years on CALL-SLT, a speech-enabled web-based CALL game for learning and im-proving fluency in domain language, focussing on the methodological aspects. In particular, we argue that our previous evaluations have been system ..."
Abstract
-
Cited by 4 (4 self)
- Add to MetaCart
(Show Context)
We summarise a series of experiments we have carried out over the last three years on CALL-SLT, a speech-enabled web-based CALL game for learning and im-proving fluency in domain language, focussing on the methodological aspects. In particular, we argue that our previous evaluations have been systematically flawed due to the lack of a control group. We present a detailed de-scription of our most recent evaluation, where 130 sub-jects, recruited using crowdsourcing methods, followed a short course in basic French over a period of one week, with 24 subjects completing the course. About a third of the subjects (half of the ones that finished) were as-signed to a control group who used a version of the sys-tem with speech recognition feedback disabled; subjects in both groups demonstrated significant improvements in language skills over the duration of the experiment, but the improvements were significantly larger for the non-control subjects. We argue in conclusion that this type of experiment opens up interesting new ways to attack the difficult problem of performing controlled experiments with CALL applications. Index Terms: CALL, speech recognition, evaluation, methodology, crowdsourcing
A TEXTBOOK-BASED SERIOUS GAME FOR PRACTISING SPOKEN LANGUAGE
"... We describe a web-enabled serious game intended to help German-speaking beginner students of English improve their generative and auditory competence. The tool is built on top of the existing CALL-SLT platform, the architecture of which is briefly described. It offers a short course of 8 interactive ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
(Show Context)
We describe a web-enabled serious game intended to help German-speaking beginner students of English improve their generative and auditory competence. The tool is built on top of the existing CALL-SLT platform, the architecture of which is briefly described. It offers a short course of 8 interactive lessons using a combined vocabulary of about 450 words, and was developed in collaboration with a secondary school teacher, with the content taken from a commonly used textbook. Lessons are structured as a short dialogue between the student and the machine, where the student is encouraged to use simple language in practical contexts like booking a hotel room, buying clothes, or ordering a meal in a restaurant. A lesson connects together groups of component examples. At each turn, the system starts by playing a short video file in English, and simultaneously displays a piece of text in German indicating to the student how they should reply. The students give a spoken response in English; if they are uncertain how to respond, they can first ask for a help example. After the student answers, the system performs speech recognition, machine translation and matching, and either accepts or rejects. There are multiple paths through the dialogue, controlled by a lesson structure defined in an XML file supplied by the course designer. The overall system is gamified to increase student motivation, using common game elements such as badges. We conclude with a brief description of an informal pre-study carried out on several children aged between 9 and 13. The older children liked the system and found it easy to use, while the younger ones struggled.
Formative Feedback in an Interactive Spoken CALL System
"... By definition spoken dialogue CALL systems should be easy to use and understand. However, interaction in this context is often far from unhindered. In this paper we introduce a formative feedback mechanism in our CALL system, which can monitor interaction, report errors and provide advice and sugges ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
(Show Context)
By definition spoken dialogue CALL systems should be easy to use and understand. However, interaction in this context is often far from unhindered. In this paper we introduce a formative feedback mechanism in our CALL system, which can monitor interaction, report errors and provide advice and suggestions to users. The distinctive feature of this mechanism is the ability to combine information from different sources and decide on the most pertinent feedback, which can also be adapted in terms of phrasing, style and language. We conducted experiments at three secondary schools in German-speaking Switzerland and the obtained results suggest that our feedback mechanism helps students during interaction and contributes as a motivating factor.
A Web-Deployed Swedish Spoken CALL System Based on a Large Shared English/Swedish Feature Grammar
"... We describe a Swedish version of CALL-SLT, a web-deployed CALL system that allows beginner/intermediate students to practise generative spoken language skills. Speech recognition is grammar-based, with language models derived, using the Regulus platform, from substantial domain-independent feature g ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(Show Context)
We describe a Swedish version of CALL-SLT, a web-deployed CALL system that allows beginner/intermediate students to practise generative spoken language skills. Speech recognition is grammar-based, with language models derived, using the Regulus platform, from substantial domain-independent feature grammars. The paper focusses on the Swedish grammar resources, which were developed by generalising the existing English feature grammar into a shared grammar for English and Swedish. It turns out that this can be done very economically: all but a handful of rules and features are shared, and English grammar essentially ends up being treated as a reduced form of Swedish. We conclude by presenting a simple evaluation which compares the Swedish and French versions of CALL-SLT. 1
An Agent Based Competitive Translation Game for Second Language Learning
- in Proc. SLaTE
, 2011
"... This paper describes a competitive language translation game aimed at improving students vocabulary and writing skills. An automated agent is employed as an opponent in order to improve the user’s motivation and maintain the user focused. The agent’s actions are based on statistical machine translat ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
This paper describes a competitive language translation game aimed at improving students vocabulary and writing skills. An automated agent is employed as an opponent in order to improve the user’s motivation and maintain the user focused. The agent’s actions are based on statistical machine translation outputs. An evaluation that was performed with 20 Portuguese learners of Mandarin suggested that users were more focused and motivated when playing against the agent than playing alone. Furthermore, the majority of students felt that the sys-tem helped them learn Mandarin and would like to use it in the future. The system has a web-based implementation and is eas-ily accessible by language learners. Index Terms: computer assisted language learning, machine translation, automated agent, educational games
CALL-SLT: A Spoken CALL System based on grammar and speech recognition
, 2014
"... based on grammar and speech recognition ..."
(Show Context)
