Search

This article contributes to a more adequate modelling of emotions encoded in speech, by addressing four fallacies prevalent in traditional affective computing: First, studies concentrate on few emotions and disregard all other ones ('closed world'). Second, studies use clean (lab) data or real-life ones but do not compare clean and noisy data in a comparable setting ('clean world'). Third, machine learning approaches need large amounts of data; however, their performance has not yet been assessed by systematically comparing different approaches and different sizes of databases ('small world'). Fourth, although human annotations of emotion constitute the basis for automatic classification, human perception and machine classification have not yet been compared on a strict basis ('one world'). Finally, we deal with the intrinsic ambiguities of emotions by interpreting the confusions between categories ('fuzzy world'). We use acted nonsense speech from the GEMEP corpus, emotional 'distractors' as categories not entailed in the test set, real-life noises that mask the clear recordings, and different sizes of the training set for machine learning. We show that machine learning based on state-of-the-art feature representations (wav2vec2) is able to mirror the main emotional categories ('pillars') present in perceptual emotional constellations even in degradated acoustic conditions., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Parada-Cabaleiro et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Machine Learning (ML) algorithms within a human-computer framework are the leading force in speech emotion recognition (SER). However, few studies explore cross-corpora aspects of SER; this work aims to explore the feasibility and characteristics of a cross-linguistic, cross-gender SER. Three ML classifiers (SVM, Naïve Bayes and MLP) are applied to acoustic features, obtained through a procedure based on Kononenko's discretization and correlation-based feature selection. The system encompasses five emotions (disgust, fear, happiness, anger and sadness), using the Emofilm database, comprised of short clips of English movies and the respective Italian and Spanish dubbed versions, for a total of 1115 annotated utterances. The results see MLP as the most effective classifier, with accuracies higher than 90% for single-language approaches, while the cross-language classifier still yields accuracies higher than 80%. The results show cross-gender tasks to be more difficult than those involving two languages, suggesting greater differences between emotions expressed by male versus female subjects than between different languages. Four feature domains, namely, RASTA, F0, MFCC and spectral energy, are algorithmically assessed as the most effective, refining existing literature and approaches based on standard sets. To our knowledge, this is one of the first studies encompassing cross-gender and cross-linguistic assessments on SER.

Introduction: The Autonomous Sensory Meridian Response (ASMR) is a combination of sensory phenomena involving electrostatic-like tingling sensations, which emerge in response to certain stimuli. Despite the overwhelming popularity of ASMR in the socialmedia, no open source databases on ASMR related stimuli are yet available, which makes this phenomenon mostly inaccessible to the research community; thus, almost completely unexplored. In this regard, we present the ASMR Whispered-Speech (ASMR-WS) database. Methods: ASWR-WS is a novel database on whispered speech, specifically tailored to promote the development of ASMR-like unvoiced Language Identification (unvoiced-LID) systems. The ASMR-WS database encompasses 38 videos-for a total duration of 10 h and 36 min-and includes seven target languages (Chinese, English, French, Italian, Japanese, Korean, and Spanish). Along with the database, we present baseline results for unvoiced-LID on the ASMR-WS database. Results: Our best results on the seven-class problem, based on segments of 2s length, and on a CNN classifier and MFCC acoustic features, achieved 85.74% of unweighted average recall and 90.83% of accuracy. Discussion: For future work, we would like to focus more deeply on the duration of speech samples, as we see varied results with the combinations applied herein. To enable further research in this area, the ASMR-WS database, as well as the partitioning considered in the presented baseline, is made accessible to the research community. [ABSTRACT FROM AUTHOR]

The unprecedented growth of noise pollution over the last decades has raised an always increasing need for developing efficient audio enhancement technologies. Yet, the variety of difficulties related to processing audio sources in-the-wild, such as handling unseen noises or suppressing specific interferences, makes audio enhancement a still open challenge. In this regard, we present N-HANS (the Neuro-Holistic Audio-eNhancement System), a Python toolkit for in-the-wild audio enhancement that includes functionalities for audio denoising, source separation, and —for the first time in such a toolkit—selective noise suppression. The N-HANS architecture is specially developed to automatically adapt to different environmental backgrounds and speakers. This is achieved by the use of two identical neural networks comprised of stacks of residual blocks, each conditioned on additional speech- and noise-based recordings through auxiliary sub-networks. Along to a Python API, a command line interface is provided to researchers and developers, both of them carefully documented. Experimental results indicate that N-HANS achieves great performance w. r. t. existing methods, preserving also the audio quality at a high level; thus, ensuring a reliable usage in real-life application, e. g., for in-the-wild speech processing, which encourages the development of speech-based intelligent technology. [ABSTRACT FROM AUTHOR]

We present DEMoS (Database of Elicited Mood in Speech), a new, large database with Italian emotional speech: 68 speakers, some 9 k speech samples. As Italian is under-represented in speech emotion research, for a comparison with the state-of-the-art, we model the 'big 6 emotions' and guilt. Besides making available this database for research, our contribution is three-fold: First, we employ a variety of mood induction procedures, whose combinations are especially tailored for specific emotions. Second, we use combinations of selection procedures such as an alexithymia test and self- and external assessment, obtaining 1,5 k (proto-) typical samples; these were used in a perception test (86 native Italian subjects, categorical identification and dimensional rating). Third, machine learning techniques—based on standardised brute-forced openSMILE ComParE features and support vector machine classifiers—were applied to assess how emotional typicality and sample size might impact machine learning efficiency. Our results are three-fold as well: First, we show that appropriate induction techniques ensure the collection of valid samples, whereas the type of self-assessment employed turned out not to be a meaningful measurement. Second, emotional typicality—which shows up in an acoustic analysis of prosodic main features—in contrast to sample size is not an essential feature for successfully training machine learning models. Third, the perceptual findings demonstrate that the confusion patterns mostly relate to cultural rules and to ambiguous emotions. [ABSTRACT FROM AUTHOR]