Combining Evidence from Auditory, Instantaneous Frequency and Random Forest for Anti-Noise Speech Recognition

Due to the shortcomings of acoustic feature parameters in speech signals, and the limitations of existing acoustic features in characterizing the integrity of the speech information, This paper proposes a method for speech recognition combining cochlear feature and random forest. Environmental noise can pose a threat to the stable operation of current speech recognition systems. It is therefore essential to develop robust systems that are able to identify speech under low signal-to-noise ratio. In this paper, we propose a method of speech recognition combining spectral subtraction, auditory and energy features extraction. This method first extract novel auditory features based on cochlear filter cepstral coefficients (CFCC) and instantaneous frequency (IF), i.e., CFCCIF. Spectral subtraction is then introduced into the front end of feature extraction, and the extracted feature is called enhanced auditory features (EAF). An energy feature Teager energy operator (TEO) is also extracted, the combination of them is known as a fusion feature. Linear discriminate analysis (LDA) is then applied to feature selection and optimization of the fusion feature. Finally, random forest (RF) is used as the classifier in a non-specific persons, isolated words, and small-vocabulary speech recognition system. On the Korean isolated words database, the proposed features (i.e., EAF) after fusion with Teager energy features have shown strong robustness in the nosiy situation. Our experiments show that the optimization feature achieved in a speech recognition task display a high recognition rate and excellent anti-noise performance.

Hollywood Forever: Exploring The Digital African Diaspora In Poetry

<div>Abstract from First Paragraph:</div><div><br></div><div>This essay exclusively examines Holiday’s ebook Hollywood Forever. The e-book is non-traditional and includes a variety of media and performative elements that might otherwise be experienced in art exhibits or installations. The e-book is uniquely crafted to display a blend of visual and auditory features like posters, news reports, and podcasts. Moreover, the multimedia production adds layers of meaning, complexity, and emotion to the text. Holiday’s inclusion of historical materials from American Black culture is a recreation of the Black diaspora archives. Through the unity of old and new media, Holiday weaves together a complex narrative that combines past historical oppression, racial injustice, and intergenerational trauma to recontextualized contemporary social issues. The e-book embodies afropresentism, the combination of digital archival materials, to empower the Black voice. By reshaping history to create space for Black identities, digital texts can participate in the making of their own social and archival construction. The process of rememory uses archival material to reconstruct the narrative of a previously marginalized group. Holiday’s text uses rememory to investigate cultural biases and rearticulate the reader’s approach to racial injustices. </div>

Hollywood Forever: Exploring The Digital African Diaspora In Poetry

<div>Abstract from First Paragraph:</div><div><br></div><div>This essay exclusively examines Holiday’s ebook Hollywood Forever. The e-book is non-traditional and includes a variety of media and performative elements that might otherwise be experienced in art exhibits or installations. The e-book is uniquely crafted to display a blend of visual and auditory features like posters, news reports, and podcasts. Moreover, the multimedia production adds layers of meaning, complexity, and emotion to the text. Holiday’s inclusion of historical materials from American Black culture is a recreation of the Black diaspora archives. Through the unity of old and new media, Holiday weaves together a complex narrative that combines past historical oppression, racial injustice, and intergenerational trauma to recontextualized contemporary social issues. The e-book embodies afropresentism, the combination of digital archival materials, to empower the Black voice. By reshaping history to create space for Black identities, digital texts can participate in the making of their own social and archival construction. The process of rememory uses archival material to reconstruct the narrative of a previously marginalized group. Holiday’s text uses rememory to investigate cultural biases and rearticulate the reader’s approach to racial injustices. </div>

Neural responses to shot changes by cut in cinematographic editing: An EEG (ERD/ERS) study

In order to analyze and detect neural activations and inhibitions in film spectators to shot changes by cut in films, we developed a methodology based on comparisons of recorded EEG signals and analyzed the event-related desynchronization/synchronization (ERD/ERS). The aim of the research is isolating these neuronal responses from other visual and auditory features that covary with film editing. This system of comparing pairs of signals using permutation tests, the Spearman correlation, and slope analysis is implemented in an automated way through sliding windows, analyzing all the registered electrodes signals at all the frequency bands defined. Through this methodology, we are able to locate, identify, and quantify the variations in neuronal rhythms in specific cortical areas and frequency ranges with temporal precision. Our results detected that after a cut there is a synchronization in theta rhythms during the first 188 ms with left lateralization, and also a desynchronization between 250 ms and 750 ms in the delta frequency band. The cortical area where most of these neuronal responses are detected in both cases is the parietal area.

Higher-Order Cognition Does Not Affect Multisensory Distractor Processing

Multisensory processing is required for the perception of the majority of everyday objects and events. In the case of irrelevant stimuli, the multisensory processing of features is widely assumed to be modulated by attention. In the present study, we investigated whether the processing of audiovisual distractors is also modulated by higher-order cognition. Participants fixated a visual distractor viewed via a centrally-placed mirror and responded to a laterally-presented audiovisual target. Critically, a distractor tone was presented from the same location as the mirror, while the visual distractor feature was presented at an occluded location, visible only indirectly via mirror reflection. Consequently, it appeared as though the visual and auditory features were presented from the same location though, in fact, they actually originated from different locations. Nevertheless, the results still revealed that the visual and auditory distractor features were processed together just as in the control condition, in which the audiovisual distractor features were both actually presented from fixation. Taken together, these results suggest that the processing of irrelevant multisensory information is not influenced by higher-order cognition.