Spoken Dialog Systems 2015


Resources:

  • opendial-toolkit.net .. java-based, domain-independent toolkit for developing spoken dialogue systems

References:

See also:

CLASSiC (Computational Learning in Adaptive Systems for Spoken Conversation) | LSTM (Long Short Term Memory) & Dialog Systems 2015POMDP (Partially Observable Markov Decision Process) & Dialog SystemsSLP (Spoken Language Programming)


Semantically conditioned lstm-based natural language generation for spoken dialogue systems TH Wen, M Gasic, N Mrksic, PH Su, D Vandyke… – arXiv preprint arXiv: …, 2015 – arxiv.org Abstract: Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised … Cited by 52 Related articles All 18 versions

Learning from real users: Rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems PH Su, D Vandyke, M Gasic, D Kim, N Mrksic… – arXiv preprint arXiv: …, 2015 – arxiv.org Abstract: To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the dialogue’s success by observing … Cited by 10 Related articles All 12 versions

HALEF: An Open-Source Standard-Compliant Telephony-Based Modular Spoken Dialog System: A Review and An Outlook D Suendermann-Oeft, V Ramanarayanan… – … Dialog Systems and …, 2015 – Springer Abstract We describe completed and ongoing research on HALEF, a telephony-based open- source spoken dialog system that can be used with different plug-and-play back-end modules. We present two examples of such a module, one which classifies whether the … Cited by 7 Related articles All 21 versions

Detecting Multiple Domains from User’s Utterance in Spoken Dialog System S Ryu, J Song, S Koo, S Kwon, GG Lee – … Language Dialog Systems and …, 2015 – Springer Abstract Multi-domain spoken dialog system should be able to detect more than one domain from a user’s utterance. However, it is difficult to train an accurate binary classifier of a domain based on only positive and unlabeled examples. This paper improves hierarchical … Cited by 5 Related articles All 5 versions

Learning OOV through semantic relatedness in spoken dialog systems M Sun, YN Chen, AI Rudnicky – Proc. The 16th Annual Conference of …, 2015 – cs.cmu.edu Abstract Ensuring language coverage in dialog systems can be a challenge, since the language in a domain may drift over time, creating a mismatch between the original training data and current input. This in turn degrades performance by increasing … Cited by 5 Related articles All 4 versions

Knowledge graph inference for spoken dialog systems Y Ma, PA Crook, R Sarikaya… – 2015 IEEE International …, 2015 – ieeexplore.ieee.org ABSTRACT We propose Inference Knowledge Graph, a novel approach of remapping existing, large scale, semantic knowledge graphs into Markov Random Fields in order to create user goal tracking models that could form part of a spoken dialog system. Since … Cited by 7 Related articles All 6 versions

Understanding user’s cross-domain intentions in spoken dialog systems M Sun, YN Chen, AI Rudnicky – … on Machine Learning for SLU and …, 2015 – researchgate.net Abstract Spoken language based intelligent assistants (IAs) have been developed for a number of domains but their functionality has mostly been confined to the scope of a given app. One reason is that it’s is difficult for IAs to infer a user’s intent without access to … Cited by 5 Related articles All 3 versions

Situated language understanding for a spoken dialog system within vehicles T Misu, A Raux, R Gupta, I Lane – Computer Speech & Language, 2015 – Elsevier Abstract In this paper, we address issues in situated language understanding in a moving car, which has the additional challenge of being a rapidly changing environment. More specifically, we propose methods for understanding user queries regarding specific target … Cited by 4 Related articles All 3 versions

Discriminative methods for statistical spoken dialogue systems MS Henderson – 2015 – repository.cam.ac.uk Dialogue promises a natural and effective method for users to interact with and obtain information from computer systems. Statistical spoken dialogue systems are able to disambiguate in the presence of errors by maintaining probability distributions over what … Cited by 4 Related articles All 3 versions

From rule-based to data-driven lexical entrainment models in spoken dialog systems J Lopes, M Eskenazi, I Trancoso – Computer Speech & Language, 2015 – Elsevier Abstract This paper presents uses a data-driven approach to improve Spoken Dialog System (SDS) performance by automatically finding the most appropriate terms to be used in system prompts. The literature shows that speakers use one another’s terms (entrain) … Cited by 4 Related articles All 5 versions

Reward shaping with recurrent neural networks for speeding up on-line policy learning in spoken dialogue systems PH Su, D Vandyke, M Gasic, N Mrksic, TH Wen… – arXiv preprint arXiv: …, 2015 – arxiv.org Abstract: Statistical spoken dialogue systems have the attractive property of being able to be optimised from data via interactions with real users. However in the reinforcement learning paradigm the dialogue manager (agent) often requires significant time to explore the state … Cited by 2 Related articles All 18 versions

Policy committee for adaptation in multi-domain spoken dialogue systems M Gaši?, N Mrkši?, PH Su, D Vandyke, TH Wen… – 2015 – repository.cam.ac.uk Moving from limited-domain dialogue systems to open domain dialogue systems raises a number of challenges. One of them is the ability of the system to utilise small amounts of data from disparate domains to build a dialogue manager policy. Previous work has … Cited by 4 Related articles All 7 versions

Using knowledge on word-islands to improve the performance of spoken dialogue systems R López-Cózar – Knowledge-Based Systems, 2015 – Elsevier Abstract This paper proposes a technique to improve the performance of spoken dialogue systems that not only consider knowledge about the semantic frames used by systems to understand the spoken language but also employ knowledge about the words in the … Cited by 4 Related articles All 3 versions

Spoken language understanding in a nutrition dialogue system MB Korpusik – 2015 – dspace.mit.edu Existing approaches for the prevention and treatment of obesity are hampered by the lack of accurate, low-burden methods for self-assessment of food intake, especially for hard-to- reach, low-literate populations. For this reason, we propose a novel approach to diet … Cited by 3 Related articles All 3 versions

DietTalk: Diet and Health Assistant Based on Spoken Dialog System S Jung, S Ryu, S Han, GG Lee – … Dialog Systems and Intelligent Assistants, 2015 – Springer Abstract This paper presents DietTalk, a diet and health assistant based on a spoken dialog system. The purpose of DietTalk is to help people to control their weight by consulting with it using natural language. DietTalk stores personal status, provides food and exercise … Cited by 1 Related articles All 5 versions

Developing Spoken Dialogue Systems with the OpenDial toolkit P Lison, C Kennington – SEMDIAL 2015 goDIAL, 2015 – flov.gu.se Abstract We present OpenDial1, an open-source toolkit for building and evaluating dialogue systems. The toolkit is centered on a dialogue state expressed as a Bayesian network and acting as a shared memory for the system modules. The domain models are specified via … Cited by 1 Related articles All 8 versions

Detecting repetitions in spoken dialogue systems using phonetic distances J Lopes, G Salvi, G Skantze, A Abad… – … Annual Conference of …, 2015 – inesc-id.pt Abstract Repetitions in Spoken Dialogue Systems can be a symptom of problematic communication. Such repetitions are often due to speech recognition errors, which in turn makes it harder to use the output of the speech recognizer to detect repetitions. In this … Cited by 1 Related articles All 7 versions

Automatic detection of miscommunication in spoken dialogue systems R Meena, JLG Skantze… – … Discourse and Dialogue, 2015 – anthology.aclweb.org Abstract In this paper, we present a data-driven approach for detecting instances of miscommunication in dialogue system interactions. A range of generic features that are both automatically extractable and manually annotated were used to train two models for … Cited by 3 Related articles All 15 versions

Deep Contextual Language Understanding in Spoken Dialogue Systems C Liu, P Xu, R Sarikaya – Sixteenth Annual Conference of …, 2015 – research.microsoft.com Abstract We describe a unified multi-turn multi-task spoken language understanding (SLU) solution capable of handling multiple context sensitive classification (intent determination) and sequence labeling (slot filling) tasks simultaneously. The proposed architecture is … Cited by 2 Related articles All 4 versions

Modeling user response timings in spoken dialog systems S Witt – International Journal of Speech Technology, 2015 – Springer Abstract This article is concerned with optimizing human-machine turn-taking. In particular, the article covers an in-depth analysis of the timings when users respond to system query in spoken dialog systems. The goal of this work is to obtain a broad understanding of such … Cited by 1 Related articles All 3 versions

A Persian spoken dialogue system using POMDPs H Mahmoudi… – Artificial Intelligence and …, 2015 – ieeexplore.ieee.org Persian spoken dialogue system. The framework is based on the Partially Observable Markov Decision Process (POMDP). A Bayesian network is used to represent the states of the POMDP model. It is shown that Bayesian approaches can improve the spoken … Related articles

Evaluation of NLG in an end-to-end Spoken dialogue system-is it worth it? H Hastie, H Cuayáhuitl, N Dethlefs, S Keizer, X Liu – researchgate.net Abstract In the past 10 years, only around 15% of published conference papers include some kind of extrinsic evaluation of an NLG component in an end-to-end system. These types of evaluations are costly to set-up and run, so is it worth it? Is there anything to be … Related articles All 2 versions

Extension with intelligent agents for the spoken dialogue system for smartphones T Uchiya, R Nakano, D Yamamoto… – 2015 IEEE 4th …, 2015 – ieeexplore.ieee.org Abstract—MMDAgent has been proposed as a voice dialogue system capable of voice interaction in real time with 3D character. In order to improve the convenience by enlarging the operating environment, the” Smart Meichan” has been proposed transplanted with … Related articles

Data for Policy Committee for adaptation in multi-domain spoken dialogue systems M Gasic – 2015 – repository.cam.ac.uk This dataset correspond to the results presented in ASRU15 paper POLICY COMMITTEE FOR ADAPTATION IN MULTI-DOMAIN SPOKEN DIALOGUE SYSTEMS and relates to Fig. 2 Two contrasts were presented INDOM and MBCM. INDOM_L6_ [1, 2, 3] is the data …

A spoken dialog system with redundant response to prevent user misunderstanding M Yamaoka, S Hara, M Abe – 2015 Asia-Pacific Signal and …, 2015 – ieeexplore.ieee.org Abstract—We propose a spoken dialog strategy for car navigation systems to facilitate safe driving. To drive safely, drivers need to concentrate on their driving; however, their concentration may be disrupted due to disagreement with their spoken dialog system. … Related articles All 4 versions

Multi-agent learning in multi-domain spoken dialogue systems M Gašic, N Mrkšic, LR Barahona, PH Su, D Vandyke… – pdfs.semanticscholar.org Abstract The use of a committee of dialogue policies has been shown to be particularly beneficial for adaptation in multi-domain dialogue systems. In this model, each domain is represented by a committee member and the committee collaboratively decides which … Related articles All 3 versions

On Appropriateness and Estimation of the Emotion of Synthesized Response Speech in a Spoken Dialogue System T Kase, T Nose, A Ito – International Conference on Human-Computer …, 2015 – Springer Abstract Paralinguistic features such as emotion of an utterance is as important as its linguistic content for generating better response utterances in spoken dialog systems. In this research, we carried out an experiment to reveal the effect of emotional speech synthesis … Related articles

Recognition of Paralinguistic Information in Spoken Dialogue Systems for Elderly People H Pérez-Espinosa, J Martínez-Miranda – Mexican International Conference …, 2015 – Springer Abstract Different strategies are currently studied and applied with the objective to facilitate the acceptability and effective use of Ambient Assisted Living (AAL) applications. One of these strategies is the development of speech-based interfaces to facilitate the … Related articles

Data for Multi-agent learning in multi-domain spoken dialogue systems M Gasic – 2015 – repository.cam.ac.uk This dataset correspond to the results presented in NIPS 2015 Workshop on Spoken Language Understanding and Interaction, paper MULTI-AGENT LEARNING IN MULTI- DOMAIN SPOKEN DIALOGUE SYSTEMS and relates to Fig. 1 Two contrasts were …

An Incremental Turn-Taking Model with Active System Barge-in for Spoken Dialog Systems T Zhao, AW Black, M Eskenazi – … Group on Discourse and Dialogue, 2015 – aclweb.org Abstract This paper deals with an incremental turntaking model that provides a novel solution for end-of-turn detection. It includes a flexible framework that enables active system barge-in. In order to accomplish this, a systematic procedure of teaching a dialog system … Cited by 2 Related articles All 9 versions

Effects of Game on User Engagement with Spoken Dialogue System H Kobayashi, K Tanio, M Sassano – … Group on Discourse and Dialogue, 2015 – aclweb.org Abstract In this study, we examine the effects of using a game for encouraging the use of a spoken dialogue system. As a case study, we developed a word-chain game, called Shiritori in Japanese, and released the game as a module in a Japanese Android/iOS app, Onsei- … Cited by 1 Related articles All 10 versions

Evaluation of Machine-Led Error Recovery Strategies for Domain Switches in a Spoken Dialog System S Reichel, U Ehrlich, A Berton, M Weber – … Language Dialog Systems and …, 2015 – Springer Abstract Spoken dialog systems which include multiple domains or many applications set high requirements for natural language understanding. As the functionality in such systems increases, recognition errors and ambiguous interpretations are likely to occur. However, … Related articles All 6 versions

Requirements and Challenges of In-Vehicle Spoken Dialog Systems Specification from an Industrial Viewpoint P Braunger, H Hofmann, S Werner… – … Computer Systems with … – scxmlworkshop.de ABSTRACT The development process of in-vehicle spoken dialog systems (SDS) is characterized by intensive cooperation of different parties. Voice user interface designers specify the system requirements which are then implemented by integration experts. … Related articles All 6 versions

Combining Several User Models to Improve and Adapt the Dialog Management Process in Spoken Dialog Systems D Griol, JM Molina, A Sanchis, Z Callejas – International Workshop on …, 2015 – Springer Abstract Spoken dialog systems have demonstrated a high potential for more flexible, usable and natural human-computer interaction. These improvements are highly dependent on the users’ adaptation and dialog management processes, which respectively integrates … Related articles

Mobile spoken dialogue system using parser dependencies and ontology MS Yakoub, SA Selouani, R Nkambou – International Journal of Speech …, 2015 – Springer Abstract In this paper, we propose a mobile spoken dialogue system with a new spoken dialogue understanding architecture (SLU). This new SLU module combines an ontology and a dependency graph to do semantic analysis. The turn analysis algorithm integrated … Related articles All 3 versions

Easily Bootstrappable Statistical Spoken Dialogue System K Valev – 2015 – isl.anthropomatik.kit.edu Abstract Conventional, rule-based, dialogue managers require many expensive iterations of manual design and re-design in order to produce good strategies. In addition, such hand- coded strategies are not reusable from task to task, are not scalable, and require a … Related articles

Spoken Dialogue System For Product Recommendation Using Hierarchical POMDP Y Yamada, TTY Ariki – me.cs.scitec.kobe-u.ac.jp ABSTRACT We present a spoken dialogue system developed for product recommendation, which uses partially observable Markov decision processes (POMDPs) hierarchically (H- POMDPs). Aiming at the efficient dialogue system, user utterance log is utilized and the … Related articles

Policy committee for adaptation in multi-domain spoken dialogue systems M Ga, N Mrk, PH Su, D Vandyke… – … IEEE Workshop on …, 2015 – ieeexplore.ieee.org ABSTRACT Moving from limited-domain dialogue systems to open domain dialogue systems raises a number of challenges. One of them is the ability of the system to utilise small amounts of data from disparate domains to build a dialogue manager policy. … Cited by 2 Related articles All 3 versions

Research data supporting “Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems” TH Wen, M Gasic, N Mrksic, PH Su, D Vandyke… – 2015 – repository.cam.ac.uk This dataset is in JSON format and contains log files of interactions between a turn-taking spoken dialogue system and Amazon Mechanical turkers, collected from our previous live trials. It includes two application domains: San Francisco restaurants and hotels, each of …

Crowd-sourcing + spoken dialogue system development R Manuvinakurike – manuvinakurike.com [1] Ramesh Manuvinakurike and David DeVault. 2015.“Pair Me Up: A Web Framework for Crowd-Sourced Spoken Dialogue Collection.” In International Workshop on Spoken Dialogue Systems (IWSDS)[2] Maike Paetzel, Ramesh Manuvinakurike, and David … Related articles

Crowdsourcing Environment to Create Voice Interaction Scenario of Spoken Dialogue System Y Matsushita, T Uchiya, R Nishimuray… – … Information Systems …, 2015 – ieeexplore.ieee.org Abstract—This university has published the” MMDAgent” voice interaction system toolkit as open source software. Voice Interaction Agent, produced using MMDAgent, is active in various scenarios and provides voice interaction capability. Voice interaction agents … Related articles All 2 versions

Automated recognition of paralinguistic signals in spoken dialogue systems: ways of improvement M Sidorov, A Schmitt… – Journal of Siberian …, 2015 – search.proquest.com Abstract The ability of artificial systems to recognize paralinguistic signals, such as emotions, depression, or openness, is useful in various applications. However, the performance of such recognizers is not yet perfect. In this study we consider several directions which can … Related articles All 10 versions

On the Granularity of Dialog Strategies: Insights from Large-scale Analyses of Two Commercial Travel Information Spoken Dialog Systems Z Jiao, Z Wang, G Wang, H Tian, H Wu, H Wang – 2015 – researchgate.net Abstract This paper empirically analyzes large amounts of real user dialogs collected from two deployments of spoken dialog systems (SDS) in a travel information mobile app widely used in China. The data studied here consist of 288K dialogs from a flight booking SDS … Related articles

Guardian: A Crowd-Powered Spoken Dialog System for Web APIs THK Huang, WS Lasecki, JP Bigham – Third AAAI Conference on Human …, 2015 – aaai.org Abstract Natural language dialog is an important and intuitive way for people to access information and services. However, current dialog systems are limited in scope, brittle to the richness of natural language, and expensive to produce. This paper introduces Guardian, … Cited by 1 Related articles All 7 versions

User Adaptive Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems K Komatani, N Hotta, S Sato… – … Discourse and Dialogue, 2015 – anthology.aclweb.org Abstract Ideally, the users of spoken dialogue systems should be able to speak at their own tempo. The systems thus need to correctly interpret utterances from various users, even when these utterances contain disfluency. In response to this issue, we propose an … Cited by 1 Related articles All 10 versions

Evaluation of Crowdsourced User Input Data for Spoken Dialog Systems M Schmidt, M Müller, M Wagner, S Stüker… – … and Dialogue, 2015 – aclweb.org Abstract Using the Internet for the collection of data is quite common these days. This process is called crowdsourcing and enables the collection of large amounts of data at reasonable costs. While being an inexpensive method, this data typically is of lower … All 10 versions

Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems YN Chen – target, 2015 – cs.cmu.edu Abstract Spoken language interfaces are being incorporated into various devices (smart- phones, smart TVs, in-car navigating system, etc). The role of spoken language understanding is of great significance to a successful spoken dialogue system: in order to … Related articles All 10 versions

A proposal for improving spoken dialog systems using context information fusion I Chairi, D Griol, J García… – Information Fusion (Fusion …, 2015 – ieeexplore.ieee.org Abstract-Context information fusion allow developing systems that provides large quantities of information obtained from network sensors with heterogeneous characteristics, that needs to be efficiently processed. During the last years, this field has become increasingly … Related articles

Learning for Spoken Dialog Systems with Discriminative Graphical Models Y Ma – 2015 – etd.ohiolink.edu ABSTRACT A statistical spoken dialog system must keep track of what the user wants at any point during a dialog. The system has the ability to disambiguate in the presence of errors by maintaining probability distributions over possible dialog states. This thesis demonstrates … Related articles All 3 versions

Advanced Research for Modeling of Spontaneous Spoken Dialogue Understanding System Using Prosody A ICHIKAWA, A IMIYA, Y HORIUCHI – sap.ist.i.kyoto-u.ac.jp Modern technologies for computer-human interface are unbalance and excessively depend on some part of media, for examples the” mouse” and” windows”. These technologies are rather di cult to use for advanced age people and people with disabilities. It is essential for … Related articles All 3 versions