What Speech Tells Us About Discourse: The Role of Prosodic and Discourse Features in Speech Act Classification

Hoque, Mohammed Ehsan; Sorower, Mohammad S.; Yeasin, Mohammed; Louwerse, Max M.

doi:10.1109/ijcnn.2007.4371438

Cited by 9 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this appears to be only a slight improvement, the di erence was highly signi cant (p <0.001), as veri ed by a Sign test. A more recent experiment by Hoque et al (2007) also found that, whilst dialogue act classi cation based on prosody alone does not result in very high accuracy, prosodic features could be used to improve scores of a classi er based on discourse features, reaching an accuracy of 65.6% for a total of 13 speech act categories. Shriberg et al use a decision tree, in which more salient features are likely to be placed higher up than less salient features.…”

Section: Dialogue Acts and Prosody: Related Workmentioning

confidence: 99%

Towards the generation of dialogue acts in socio-affective ECAs: a corpus-based prosodic analysis

Bawden

Clavel

Landragin

2015

Lang Resources & Evaluation

View full text Add to dashboard Cite

International audienceWe present a corpus-based prosodic analysis with the aim of uncovering the relationship between dialogue acts, personality and prosody in view to providing guidelines for the ECA Greta's text-to-speech system. The corpus used is the SEMAINE corpus, featuring four different personalities, further annotated for dialogue acts and prosodic features. In order to show the importance of the choice of dialogue act taxonomy, two different taxonomies were used, the first corresponding to Searle's taxonomy of speech acts and the second, inspired by Bunt's DIT++, including a division of directive acts into finer categories. Our results show that finer-grained distinctions are important when choosing a taxonomy. We also show with some preliminary results that the prosodic correlates of dialogue acts are not always as cited in the literature and prove more complex and variable. By studying the realisation of different directive acts, we also observe differences in the communicative strategies of the ECA depending on personality, in view to providing input to a speech system

show abstract

Section: Dialogue Acts and Prosody: Related Workmentioning

confidence: 99%

Towards the generation of dialogue acts in socio-affective ECAs: a corpus-based prosodic analysis

Bawden

Clavel

Landragin

2015

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…We expanded upon the previous research by Vigliano et al (2016) by conducting a more detailed examination of convergence in duration, F0 mean, and F0 max syllable-wise. We based our analysis on duration and F0 as (1) they were the parameters manipulated using the prosodic transplantation technique; (2) they are also among the prosodic features commonly employed for automatic speech act classification, as outlined in prior research in English (Hoque et al 2007). Moreover, we took F0 mean and F0 max as indicators of F0 in the endeavor to capture the alterations in F0 associated with pitch accents and the shape of the final sentence contour.…”

Section: The Present Studymentioning

confidence: 99%

After Self-Imitation Prosodic Training L2 Learners Converge Prosodically to the Native Speakers

Pellegrino

2024

Languages

View full text Add to dashboard Cite

Little attention is paid to prosody in second language (L2) instruction, but computer-assisted pronunciation training (CAPT) offers learners solutions to improve the perception and production of L2 suprasegmentals. In this study, we extend with acoustic analysis a previous research showing the effectiveness of self-imitation training on prosodic improvements of Japanese learners of Italian. In light of the increased degree of correct match between intended and perceived pragmatic functions (e.g., speech acts), in this study, we aimed at quantifying the degree of prosodic convergence towards L1 Italian speakers used as a model for self-imitation training. To measure convergence, we calculated the difference in duration, F0 mean, and F0 max syllable-wise between L1 utterances and the corresponding L2 utterances produced before and after training. The results showed that after self-imitation training, L2 learners converged to the L1 speakers. The extent of the effect, however, varied based on the speech act, the acoustic measure, and the distance between L1 and L2 speakers before the training. The findings from perceptual and acoustic investigations, taken together, show the potential of self-imitation prosodic training as a valuable tool to help L2 learners communicate more effectively.

show abstract

“…In the HCRC corpus, each utterance is annotated in terms of a dialog act (DA) as shown in the Table 1 (Examples taken from [16]). The corpus contains 27084 utterances generated during 128 conversations.…”

Section: Map Task Corpusmentioning

confidence: 99%

Robust Classification of Dialog Acts from the Transcription of Utterances

Raftopoulos

Papadakis

Ntalianis

et al. 2007

International Conference on Semantic Computing (ICSC 2007)

Self Cite

View full text Add to dashboard Cite

This paper presents a robust classification of dialog acts from text utterances. Two different types, namely, bag-of-words and syntactic relationship among words, were used to extract the discourse level features from the transcript of utterances. Subsequently a number of feature mining methods have been used to identify the most relevant features and their roles in classifying dialog acts. The selected features are used to learn the underlying models of dialog acts using a number of existing machine learning algorithms from the WEKA toolbox. Empirical analyses using the HCRC Map Task Corpus dialog data was conducted to evaluate the performance of the proposed approach.

show abstract

What Speech Tells Us About Discourse: The Role of Prosodic and Discourse Features in Speech Act Classification

Cited by 9 publications

References 4 publications

Towards the generation of dialogue acts in socio-affective ECAs: a corpus-based prosodic analysis

Towards the generation of dialogue acts in socio-affective ECAs: a corpus-based prosodic analysis

After Self-Imitation Prosodic Training L2 Learners Converge Prosodically to the Native Speakers

Robust Classification of Dialog Acts from the Transcription of Utterances

Contact Info

Product

Resources

About