Abstract
Immersive video applications impose unpractical bandwidth requirements for best-effort networks. With Multi-View(MV) streaming, these can be minimized by resorting to view prediction techniques. SmoothMV is a multi-view system that uses a non-intrusive head tracking mechanism to detect the viewer's interest and select appropriate views. By coupling Neural Networks (NNs) to anticipate the viewer's interest, a reduction of view-switching latency is likely to be obtained. The objective of this paper is twofold: 1) Present a solution for acquisition of gaze data from users when viewing MV content; 2) Describe a dataset, collected with a large-scale testbed, capable of being used to train NNs to predict the user's viewing interest. Tracking data from head movements was obtained from 45 participants using an Intel Realsense F200 camera, with 7 video playlists, each being viewed a minimum of 17 times. This dataset is publicly available to the research community and constitutes an important contribution to reducing the current scarcity of such data. Tools to obtain saliency/heat maps and generate complementary plots are also provided as an open-source software package.

Abstract
Quality of Experience (QoE) in multi-view streaming systems is known to be severely affected by the latency associated with view-switching procedures. Anticipating the navigation intentions of the viewer on the multi-view scene could provide the means to greatly reduce such latency. The research work presented in this article builds on this premise by proposing a new predictive view-selection mechanism. A VGG16-inspired Convolutional Neural Network (CNN) is used to identify the viewer's focus of attention and determine which views would be most suited to be presented in the brief term, i.e., the near-term viewing intentions. This way, those views can be locally buffered before they are actually needed. To this aim, two datasets were used to evaluate the prediction performance and impact on latency, in particular when compared to the solution implemented in the previous version of our multi-view streaming system. Results obtained with this work translate into a generalized improvement in perceived QoE. A significant reduction in latency during view-switching procedures was effectively achieved. Moreover, results also demonstrated that the prediction of the user's visual interest was achieved with a high level of accuracy. An experimental platform was also established on which future predictive models can be integrated and compared with previously implemented models.

Abstract
Purpose: The acoustic signal attributes of whispered speech potentially carry sufficiently distinct information to define vowel spaces and to disambiguate consonant place and voicing, but what these attributes are and the underlying production mechanisms are not fully known. The purpose of this study was to define segmental cues to place and voicing of vowels and sibilant fricatives and to develop an articulatory interpretation of acoustic data.Method: Seventeen speakers produced sustained sibilants and oral vowels, disyllabic words, sentences and read a phonetically balanced text. All the tasks were repeated in voiced and whispered speech, and the sound source and filter analysed using the following parameters: Fundamental frequency, spectral peak frequencies and levels, spectral slopes, sound pressure level and durations. Logistic linear mixed-effects models were developed to understand what acoustic signal attributes carry sufficiently distinct information to disambiguate /i, a/ and /s, ?/.Results: Vowels were produced with significantly different spectral slope, sound pressure level, first and second formant frequencies in voiced and whispered speech. The low frequencies spectral slope of voiced sibilants was significantly different between whispered and voiced speech. The odds of choosing /a/ instead of /i/ were esti-mated to be lower for whispered speech when compared to voiced speech. Fricatives' broad peak frequency was statistically significant when discriminating between /s/ and /?/.Conclusions: First formant frequency and relative duration of vowels are consistently used as height cues, and spectral slope and broad peak frequency are attributes associated with consonantal place of articulation. The rel-ative duration of same-place voiceless fricatives was higher than voiced fricatives both in voiced and whispered speech. The evidence presented in this paper can be used to restore voiced speech signals, and to inform reha-bilitation strategies that can safely explore the production mechanisms of whispering.CO 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).

Abstract
The estimation of the frequency of sinusoids has been the object of intense research for more than 40 years. Its importance in classical fields such as telecommunications, instrumentation, and medicine has been extended to numerous specific signal processing applications involving, for example, speech, audio, and music processing. In many cases, these applications run in real-time and, thus, require accurate, fast, and low-complexity algorithms. Taking the normalized Cramer-Rao lower bound as a reference, this paper evaluates the relative performance of nine non-iterative discrete Fourier transform-based individual sinusoid frequency estimators when the target sinusoid is affected by full-bandwidth quasi-harmonic interference, in addition to stationary noise. Three levels of the quasi-harmonic interference severity are considered: no harmonic interference, mild harmonic interference, and strong harmonic interference. Moreover, the harmonic interference is amplitude-modulated and frequency-modulated reflecting real-world conditions, e.g., in singing and musical chords. Results are presented for when the Signal-to-Noise Ratio varies between -10 dB and 70 dB, and they reveal that the relative performance of different frequency estimators depends on the SNR and on the selectivity and leakage of the window that is used, but also changes drastically as a function of the severity of the quasi-harmonic interference. In particular, when this interference is strong, the performance curves of the majority of the tested frequency estimators collapse to a few trends around and above 0.4% of the DFT bin width.

Abstract
The temporal distribution of acoustic cues in whispered speech was analyzed using the gating paradigm. Fifteen Portuguese participants listened to real disyllabic words produced by four Portuguese speakers. Lexical choices, confidence scores, isolation points (IPs), and recognition points (RPs) were analyzed. Mixed effects models predicted that the first syllable and 70% of the total duration of the second syllable were needed for lexical choices to be above chance level. Fricatives' place, not voicing, had a significant effect on the percentage of correctly identified words. IP and RP values of words with postalveolar voiced and voiceless fricatives were significantly different.

Abstract
Cricket sounds are usually regarded as pleasant and, thus, can be used as suitable test signals in psychoacoustic experiments assessing the human listening acuity to specific temporal and spectral features. In addition, the simple structure of cricket sounds makes them prone to reverse engineering such that they can be analyzed and re-synthesized with desired alterations in their defining parameters. This paper describes cricket sounds from a parametric point of view, characterizes their main temporal and spectral features, namely jitter, shimmer and frequency sweeps, and explains a re-synthesis process generating modified natural cricket sounds. These are subsequently used in listening tests helping to shed light on the sound identification and discrimination capabilities of humans that are important, for example, in voice recognition. © 2023 IEEE.