Verification of Speech Recognition Results Incorporating In-domain Confidence and Discourse Coherence Measures

Lane, Ian; Kawahara, Tatsuya

doi:10.1093/ietisy/e89-d.3.931

Cited by 4 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This result denotes that there is room to improve the accuracy of the first keyword list. Lane and Kawahara (2006) have proposed a method that incorporates not only “low‐level” information (e.g., linguistic likelihood) but also “high‐level” knowledge, i.e., discourse coherence measures. We are currently pursuing a method of estimation of speech intentions (Iwashita et al 2006).…”

Section: Discussionmentioning

confidence: 99%

Speech Understanding Based on Keyword Extraction and Relations Between Words

Shimada

Endo

Minewaki

2007

Computational Intelligence

View full text Add to dashboard Cite

In this paper, we propose a method for speech understanding using a corpus. First, the method extracts keywords from an N-best list of speech recognizer output. This process employs two measures: a confidence measure of speech recognizer output and an association probability between words. Next, the method uses dependencies between keywords in a corpus. Finally, it evaluates relations (tagged labels) of the dependencies. Our method obtained high accuracy as compared with a method with only the confidence measure of the speech understanding module. The results show the effectiveness of the proposed method.

show abstract

Section: Discussionmentioning

confidence: 99%

Speech Understanding Based on Keyword Extraction and Relations Between Words

Shimada

Endo

Minewaki

2007

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Lin et al (2001) gave preference to the domain selected in the previous turn by adding a certain score as an award when comparing the N-best candidates of the speech recognition for each domain. Lane and Kawahara (2005) also assigned a similar preference in the classification with Support Vector Machine (SVM). A system described in (O'Neill et al, 2004) does not change its domain until its sub-task is completed, which is a constraint similar to keeping dialogue in one domain.…”

Section: Extensible and Robust Domain Selectionmentioning

confidence: 99%

Multi-domain spoken dialogue system with extensibility and robustness against speech recognition errors

Komatani

Kanda

Nakano

et al. 2006

Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue - SigDIAL '06

View full text Add to dashboard Cite

We developed a multi-domain spoken dialogue system that can handle user requests across multiple domains. Such systems need to satisfy two requirements: extensibility and robustness against speech recognition errors. Extensibility is required to allow for the modification and addition of domains independent of other domains. Robustness against speech recognition errors is required because such errors are inevitable in speech recognition. However, the systems should still behave appropriately, even when their inputs are erroneous. Our system was constructed on an extensible architecture and is equipped with a robust and extensible domain selection method. Domain selection was based on three choices: (I) the previous domain, (II) the domain in which the speech recognition result can be accepted with the highest recognition score, and (III) other domains. With the third choice we newly introduced, our system can prevent dialogues from continuously being stuck in an erroneous domain. Our experimental results, obtained with 10 subjects, showed that our method reduced the domain selection errors by 18.3%, compared to a conventional method.

show abstract

“…For example, topic consistency is employed as a confidence measure for utterance verification [8], which is a measure of topic match between the input utterance and the application domain from the confidence vector of topic classificaCopyright c 2014 The Institute of Electronics, Information and Communication Engineers tion. Another example is topic adaptation for the language model of speech recognition [9], [10].…”

Section: Introductionmentioning

confidence: 99%

Confidence Measure Based on Context Consistency Using Word Occurrence Probability and Topic Adaptation for Spoken Term Detection

Zheng

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we propose a novel confidence measure to improve the performance of spoken term detection (STD). The proposed confidence measure is based on the context consistency between a hypothesized word and its context in a word lattice. The main contribution of this paper is to compute the context consistency by considering the uncertainty in the results of speech recognition and the effect of topic. To measure the uncertainty of the context, we employ the word occurrence probability, which is obtained through combining the overlapping hypotheses in a word posterior lattice. To handle the effect of topic, we propose a method of topic adaptation. The adaptation method firstly classifies the spoken document according to the topics and then computes the context consistency of the hypothesized word with the topic-specific measure of semantic similarity. Additionally, we apply the topic-specific measure of semantic similarity by two means, and they are performed respectively with the information of the top-1 topic and the mixture of all topics according to topic classification. The experiments conducted on the Hub-4NE Mandarin database show that both the occurrence probability of context word and the topic adaptation are effective for the confidence measure of STD. The proposed confidence measure performs better compared with the one ignoring the uncertainty of the context or the one using a non-topic method.

show abstract

Verification of Speech Recognition Results Incorporating In-domain Confidence and Discourse Coherence Measures

Cited by 4 publications

References 16 publications

Speech Understanding Based on Keyword Extraction and Relations Between Words

Speech Understanding Based on Keyword Extraction and Relations Between Words

Multi-domain spoken dialogue system with extensibility and robustness against speech recognition errors

Confidence Measure Based on Context Consistency Using Word Occurrence Probability and Topic Adaptation for Spoken Term Detection

Contact Info

Product

Resources

About