Short-time speaker verification with different speaking style utterances

In recent years, great progress has been made in the technical aspects of automatic speaker verification (ASV). However, the promotion of ASV technology is still a very challenging issue, because most technologies are still very sensitive to new, unknown and spoofing conditions. Most previous studies focused on extracting target speaker information from natural speech. This paper aims to design a new ASV corpus with multi-speaking styles and investigate the ASV robustness to these different speaking styles. We first release this corpus in the Zenodo website for public research, in which each speaker has several text-dependent and text-independent singing, humming and normal reading speech utterances. Then, we investigate the speaker discrimination of each speaking style in the feature space. Furthermore, the intra and inter-speaker variabilities in each different speaking style and cross-speaking styles are investigated in both text-dependent and text-independent ASV tasks. Conventional Gaussian Mixture Model (GMM), and the state-of-the-art x-vector are used to build ASV systems. Experimental results show that the voiceprint information in humming and singing speech are more distinguishable than that in normal reading speech for conventional ASV systems. Furthermore, we find that combing the three speaking styles can significantly improve the x-vector based ASV system, even when only limited gains are obtained by conventional GMM-based systems.

Surprised by Percival: Arthurian Transtextuality and the Reader in George MacDonald’s Phantastes

The Arthurian aspects of George MacDonald’s Phantastes (1858) have been overlooked in Arthurian studies and downplayed in MacDonald scholarship. To fill this gap, the first section of this article examines the opening paratexts of the first edition (title, subtitles, epigraphs) tracing their Arthurian echoes and allusions. The second section focuses on a key architext, Sir Percival’s quest for the Holy Grail, suggesting that Anodos rather than the unnamed knight is the character most informed by Percival. Simultaneously, the article draws on reader response theory and Derrida’s poststructuralism to argue that Phantastes is a highly self-reflexive, metafictional work intended to disrupt normal reading and writing practices in order to initiate the reader into a more open, transformative mode of reading.

Decomposing predictability: Semantic feature overlap between words and the dynamics of reading for meaning

The present study uses a computational approach to examine the role of semantic constraints in normal reading. This methodology avoids confounds inherent in conventional measures of predictability, allowing for theoretically deeper accounts of semantic processing. We start from a definition of associations between words based on the significant log likelihood that two words co-occur frequently together in the sentences of a large text corpus. Direct associations between stimulus words were controlled, and semantic feature overlap between prime and target words was manipulated by their common associates. The stimuli consisted of sentences of the form pronoun, verb, article, adjective and noun, followed by a series of closed class words, e. g. "She rides the grey elephant on one of her many exploratory voyages". The results showed that verb- noun overlap reduces single and first fixation durations of the target noun and adjective-noun overlap reduces go-past durations. A dynamic spreading of activation account suggests that associates of the prime words take some time to become activated: The verb can act on the target noun's early eye-movement measures presented three words later, while the adjective is presented immediately prior to the target, which induces sentence re-examination after a difficult adjective- noun semantic integration.

The role of working memory in sentence processing in normal reading population. A review of related literature.

This essay aims to describe the factors that influence sentence processing with emphasis given on garden path sentences. The latter grammatical phenomenon has been proved more problematic in people with low working memory span. Predictions of the working memory model of Baddeley and Hich and the theory of language comprehension of Just and Carpenter were used to explain sentence processing within text context.

Addressing Text-Dependent Speaker Verification Using Singing Speech

The automatic speaker verification (ASV) has achieved significant progress in recent years. However, it is still very challenging to generalize the ASV technologies to new, unknown and spoofing conditions. Most previous studies focused on extracting the speaker information from natural speech. This paper attempts to address the speaker verification from another perspective. The speaker identity information was exploited from singing speech. We first designed and released a new corpus for speaker verification based on singing and normal reading speech. Then, the speaker discrimination was compared and analyzed between natural and singing speech in different feature spaces. Furthermore, the conventional Gaussian mixture model, the dynamic time warping and the state-of-the-art deep neural network were investigated. They were used to build text-dependent ASV systems with different training-test conditions. Experimental results show that the voiceprint information in the singing speech was more distinguishable than the one in the normal speech. More than relative 20% reduction of equal error rate was obtained on both the gender-dependent and independent 1 s-1 s evaluation tasks.

Word meaning in word identification during reading: Co-occurrence-based semantic neighborhood density effects

ABSTRACTIdentifying individual words is an essential part of the reading process that should occur first so that understanding the structural relations between words and comprehending the sentence as a whole may take place. Therefore, lexical processing (or word identification) has received much attention in the literature, with many researchers exploring the effects of different aspects of word representation (orthographic, phonological, and semantic information of words) in word identification. While the influence of many orthographic and phonological factors in normal reading are well researched and understood (Rayner, 1998, 2009), the effect of semantic characteristics of a word in its identification has received relatively less attention. A complete account of lexical processing during normal reading requires understanding the role of word meaning in lexical processing. Currently, little is understood about whether and how the meaning of an individual word is extracted during early stages of word identification. This article primarily focuses on how word meaning contributes to the process of word identification.

The preferred viewing location in top-to-bottom sentence reading

The preferred viewing location (PVL) is a robust finding in research on reading that when fixating on a word during normal sentence reading, readers tend to land slightly to the left of the center of the word. This is in contrast to the optimal viewing location in single word recognition, which falls at the center of the word. This study outlines the history of the PVL in eye tracking since Rayner’s 1979 original study, documenting the origins of the conflicting theoretical explanations. In addition, a new study is reported examining whether the PVL can be attributed solely to oculomotor error or a processing advantage by using an experimental manipulation that separates tracking direction (left-to-right reading) and landing position (left-to-right within a word). Sentences were presented to participants from the top to the bottom of a computer screen with one word per line while eye movements were recorded. In this presentation format, readers continued to land to the left of center, suggesting that the PVL in normal reading is not solely due to oculomotor error.