Understanding unsegmented user utterances in real-time spoken dialogue systems

Nakano, Mikio; Miyazaki, Noboru; Hirasawa, Jun-ichi; Dohsaka, Kohji; Kawabata, Takeshi

doi:10.3115/1034678.1034715

Cited by 29 publications

(31 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nakano et al [6] proposed holding multiple dialogue states to deal with utterances that convey meaning over several speech intervals and with the inability to determine the understanding result at the end of each interval. Multiple dialogue states are used to represent the ambiguity of whether the user has completed his/her utterance as well as the ambiguity in intention recognition results arising from multiple applicable interpretation rules.…”

Section: Previous Workmentioning

confidence: 99%

“…In addition, since it is sometimes difficult to decide on a single dialogue state due to ambiguity in user utterances, an approach to keeping multiple dialogue states and resolving the ambiguity using succeeding user utterances has also been proposed [6], [7]. In this way, the correct dialogue state, which was not incidentally selected as the best interpretation in the previous turn, could survive until the next turn.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ranking Multiple Dialogue States by Corpus Statistics to Improve Discourse Understanding in Spoken Dialogue Systems

Higashinaka

Nakano

2009

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

Ryuichiro HIGASHINAKA†a) , Nonmember and Mikio NAKANO † †b) , Member SUMMARY This paper discusses the discourse understanding process in spoken dialogue systems. This process enables a system to understand user utterances from the context of a dialogue. Ambiguity in user utterances caused by multiple speech recognition hypotheses and parsing results sometimes makes it difficult for a system to decide on a single interpretation of a user intention. As a solution, the idea of retaining possible interpretations as multiple dialogue states and resolving the ambiguity using succeeding user utterances has been proposed. Although this approach has proven to improve discourse understanding accuracy, carefully created hand-crafted rules are necessary in order to accurately rank the dialogue states. This paper proposes automatically ranking multiple dialogue states using statistical information obtained from dialogue corpora. The experimental results in the train ticket reservation and weather information service domains show that the statistical information can significantly improve the ranking accuracy of dialogue states as well as the slot accuracy and the concept error rate of the top-ranked dialogue states.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Ranking Multiple Dialogue States by Corpus Statistics to Improve Discourse Understanding in Spoken Dialogue Systems

Higashinaka

Nakano

2009

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…33 Statuses have been predefined and were compared with the measured context values to determine the current status as relatively high/normal/low. 34 In study by Nakano et al and Hong et al, 35,36 context features were simplified by discarding ''unnecessary context.'' Both the threshold method and the discarding method filtered out some useful information hiding in the context values near the thresholds or in the discarded context.…”

Section: Robotic Elderly Caregivingmentioning

confidence: 99%

Fuzzy context-specific intention inference for robotic caregiving

Liu

Zhang

2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

To provide timely and appropriate assistance, robots must have the capability of proactively understanding a user's personal needs, the so-called human intention inference. In human-human interaction, humans have a natural and implicit way to infer others' intentions by selecting correlated context features and interpreting these features based on their life experience. However, robots do not have this capability and it is not realistic to build an explicit formula to associate human intentions with context. In this article, a novel fuzzy context-specific intention inference method is developed for human-like implicit human intention inference. With a fuzzy manner, context features are converted into discrete context statuses, which are similar to human subjective feelings. An intention-centered common sense database is developed consisting of correlated fuzzy context statuses, object affordances, and their relationship with human intentions. With this database, a Fuzzy Naïve Bayesian Network algorithm is adopted for implicit intention inference. Home scenario results validated the fuzzy context-specific intention inference methods reliability and lab scenario results validated the fuzzy context-specific intention inference methods effectiveness and robustness. This work is expected to develop intuitive and effective human-robot interaction, consequently enhancing the adoption of assistive technologies and improving the independence of the disabled and elderly in activities of daily living.

show abstract

“…Nakano et al proposed a method for incrementally understanding segmented utterances and responding in real time [22]. Bell et al proposed a method for handling fragmented utterances and controlling the system's behaviors [23].…”

Section: Related Workmentioning

confidence: 99%

Posteriori Restoration of Turn-Taking and ASR Results for Incorrectly Segmented Utterances

Komatani

Hotta

Sato

et al. 2015

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYAppropriate turn-taking is important in spoken dialogue systems as well as generating correct responses. Especially if the dialogue features quick responses, a user utterance is often incorrectly segmented due to short pauses within it by voice activity detection (VAD). Incorrectly segmented utterances cause problems both in the automatic speech recognition (ASR) results and turn-taking: i.e., an incorrect VAD result leads to ASR errors and causes the system to start responding though the user is still speaking. We develop a method that performs a posteriori restoration for incorrectly segmented utterances and implement it as a plug-in for the MMDAgent open-source software. A crucial part of the method is to classify whether the restoration is required or not. We cast it as a binary classification problem of detecting originally single utterances from pairs of utterance fragments. Various features are used representing timing, prosody, and ASR result information. Experiments show that the proposed method outperformed a baseline with manually-selected features by 4.8% and 3.9% in cross-domain evaluations with two domains. More detailed analysis revealed that the dominant and domain-independent features were utterance intervals and results from the Gaussian mixture model (GMM). key words: spoken dialogue system, VAD error, turn taking, a posteriori restoration

show abstract

Understanding unsegmented user utterances in real-time spoken dialogue systems

Cited by 29 publications

References 27 publications

Ranking Multiple Dialogue States by Corpus Statistics to Improve Discourse Understanding in Spoken Dialogue Systems

Ranking Multiple Dialogue States by Corpus Statistics to Improve Discourse Understanding in Spoken Dialogue Systems

Fuzzy context-specific intention inference for robotic caregiving

Posteriori Restoration of Turn-Taking and ASR Results for Incorrectly Segmented Utterances

Contact Info

Product

Resources

About