Speech, Prosody, and Machines: Nine Challenges for Prosody Research

Rosenberg, Andrew

doi:10.21437/speechprosody.2018-159

Cited by 5 publications

(6 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, building a dataset with large available labeled samples is costly, time-consuming, and laborious work in the automatic personality perception field, which restricts various methods. Therefore, previous studies have used handcrafted features for the DNN input [44].…”

Section: Feature Extractionmentioning

confidence: 99%

Hyper-Parameter Optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception

Zaferani

Teshnehlab

Khodadadian

et al. 2022

Sensors

View full text Add to dashboard Cite

In this work, a method for automatic hyper-parameter tuning of the stacked asymmetric auto-encoder is proposed. In previous work, the deep learning ability to extract personality perception from speech was shown, but hyper-parameter tuning was attained by trial-and-error, which is time-consuming and requires machine learning knowledge. Therefore, obtaining hyper-parameter values is challenging and places limits on deep learning usage. To address this challenge, researchers have applied optimization methods. Although there were successes, the search space is very large due to the large number of deep learning hyper-parameters, which increases the probability of getting stuck in local optima. Researchers have also focused on improving global optimization methods. In this regard, we suggest a novel global optimization method based on the cultural algorithm, multi-island and the concept of parallelism to search this large space smartly. At first, we evaluated our method on three well-known optimization benchmarks and compared the results with recently published papers. Results indicate that the convergence of the proposed method speeds up due to the ability to escape from local optima, and the precision of the results improves dramatically. Afterward, we applied our method to optimize five hyper-parameters of an asymmetric auto-encoder for automatic personality perception. Since inappropriate hyper-parameters lead the network to over-fitting and under-fitting, we used a novel cost function to prevent over-fitting and under-fitting. As observed, the unweighted average recall (accuracy) was improved by 6.52% (9.54%) compared to our previous work and had remarkable outcomes compared to other published personality perception works.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Hyper-Parameter Optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception

Zaferani

Teshnehlab

Khodadadian

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…One remaining challenge with speech-based personality perception is the limitation in the dataset, which has been discussed frequently in academic conferences for a decade [42]. Some reasons behind these limitations are: 1) most of them are not public, 2) some of them are not prosodically annotated, 3) labeling is an expensive process, 4) training annotators is a difficult trend, and 5) at least one psychologist must be employed to supervise the annotating process.…”

Section: Datasetmentioning

confidence: 99%

“…Because the prosodic content of speech must be preserved during transformations. So, those transformations must be examined to ensure if the speaker personality differences maintained [42].…”

Section: B Data Augmentationmentioning

confidence: 99%

Automatic Personality Traits Perception Using Asymmetric Auto-Encoder

Zaferani¹,

Teshnehlab²,

Vali³

2021

IEEE Access

View full text Add to dashboard Cite

On account of an increase in the human-computer interface applications, the study of automatic personality perception has become more and more prevalent than speech signal processing in recent years. These studies have shown that personality traits derived from psychology theories mainly affect acoustic features. However, some obstacles remain in the automatic personality perception classification, and the most important one is to extract the features related to each personality trait. Previous studies have shown that the personality effect differs from one acoustic feature to the others. Additionally, there are many features one can extract from speech signals. Curse of dimensionality in features also makes the classification difficult. This paper aimed to introduce and examine a novel and efficient automatic feature extraction method to classify the well-known big five personality traits. In this regard, three data augmentation methods for increasing data samples were examined. Afterwards, 6,373 statistical features were extracted from the nonverbal features of the SSPNet Speaker Personality Corpus. Finally, an innovative stacked asymmetric auto-encoder was utilized to extract useful features automatically to improve classification results. Compared with the conventional stacked auto-encoder and convolutional neural network, the proposed method exhibited an average improvement of 12.40%(10.14%) and 14.36%(1.42%) in terms of the unweighted average recall (accuracy), respectively. In comparison with other published works, classification results also revealed a notable average enhancement (11.78%) for unweighted average recall for all five traits and an average improvement of 5.1% for accuracy in two out of five personality traits.

show abstract

“…Segmentation can also put less demands on working memory which later benefits the reanalysis process. Syntactic parsing is closely related to prosodic phrasing in the way that readers' ability to phrase words while applying some prosodic contour or intonation to the sentence, even in silent reading (Breen, 2014;Fodor, 2002;Frazier & Gibson, 2015), develops along with the automaticity of syntactic parsing. Reading aloud for beginner and intermediate learners to prime the correct segmentation from prosody can help learners see the pattern easier and develop their own parsing ability.…”

Section: Putting Things Together: Implications For L2 Reading Pedagogymentioning

confidence: 99%

Reassessing second language reading comprehension: Insights from the psycholinguistics notion of sentence processing

Zudianto

Ashadi

2021

View full text Add to dashboard Cite

Theories and practices in second language reading pedagogy often overlook the sentence processing description from the psycholinguistics perspective. Second language reading comprehension is easily associated with vocabulary learning or discourse strategy. Yet, such activities can lead to an unnatural way of reading such as translating vocabularies or pointing out information as required. Meanwhile the authentic way of reading should encourage a natural stream of ideas to be interpreted from sentence to sentence. As suggested by the sentence processing notion from the psycholinguistics point of view, syntax appears to be the key to effective and authentic reading as opposed to the general belief of semantic or discourse information being the primary concern. This article argues that understanding the architecture of sentence processing, with syntactic parsing at the core of the underlying mechanism, can offer insights into the second language reading pedagogy. The concepts of syntactic parsing, reanalysis, and sentence processing models are described to give the idea of how sentence processing works. Additionally, a critical review on the differences between L1 and L2 sentence processing is presented considering the recent debate on individual differences as significant indicators of nativelike L2 sentence processing. Lastly, implications for the L2 reading pedagogy and potential implementation in instructional setting are discussed.

show abstract

Speech, Prosody, and Machines: Nine Challenges for Prosody Research

Cited by 5 publications

References 52 publications

Hyper-Parameter Optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception

Hyper-Parameter Optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception

Automatic Personality Traits Perception Using Asymmetric Auto-Encoder

Reassessing second language reading comprehension: Insights from the psycholinguistics notion of sentence processing

Contact Info

Product

Resources

About