For deep learning based speech segregation to have translational significance as a noise-reduction tool, it must perform in a wide variety of acoustic environments. In the current study, performance was examined when target speech was subjected to interference from a single talker and room reverberation. Conditions were compared in which an algorithm was trained to remove both reverberation and interfering speech, or only interfering speech. A recurrent neural network incorporating bidirectional long short-term memory was trained to estimate the ideal ratio mask corresponding to target speech. Substantial intelligibility improvements were found for hearing-impaired (HI) and normalhearing (NH) listeners across a range of target-to-interferer ratios (TIRs). HI listeners performed better with reverberation removed, whereas NH listeners demonstrated no difference. Algorithm benefit averaged 56 percentage points for the HI listeners at the least-favorable TIR, allowing these listeners to perform numerically better than young NH listeners without processing. The current study highlights the difficulty associated with perceiving speech in reverberant-noisy environments, and it extends the range of environments in which deep learning based speech segregation can be effectively applied. This increasingly wide array of environments includes not only a variety of background noises and interfering speech, but also room reverberation.
Previous research has shown that English-speaking learners of Russian, even those with advanced proficiency, often have not acquired the contrast between palatalized and unpalatalized consonants, which is a central feature of the Russian consonant system. The present study examined whether training utilizing electropalatography (EPG) could help a group of Russian learners achieve more native-like productions of this contrast. Although not all subjects showed significant improvements, on average, the Russian learners showed an increase from pre- to post-training in the second formant frequency of vowels preceding palatalized consonants, thus enhancing their contrast between palatalized and unpalatalized consonants. To determine whether these acoustic differences were associated with increased identification accuracy, three native Russian speakers listened to all pre- and post-training productions. A modest increase in identification accuracy was observed. These results suggest that even short-term EPG training can be an effective intervention with adult L2 learners.
Recently, deep learning based speech segregation has been shown to improve human speech intelligibility in noisy environments. However, one important factor not yet considered is room reverberation, which characterizes typical daily environments. The combination of reverberation and background noise can severely degrade speech intelligibility for hearing-impaired (HI) listeners. In the current study, a deep learning based time-frequency masking algorithm was proposed to address both room reverberation and background noise. Specifically, a deep neural network was trained to estimate the ideal ratio mask, where anechoic-clean speech was considered as the desired signal. Intelligibility testing was conducted under reverberant-noisy conditions with reverberation time T 60 ¼ 0.6 s, plus speech-shaped noise or babble noise at various signal-to-noise ratios. The experiments demonstrated that substantial speech intelligibility improvements were obtained for HI listeners. The algorithm was also somewhat beneficial for normal-hearing (NH) listeners. In addition, sentence intelligibility scores for HI listeners with algorithm processing approached or matched those of young-adult NH listeners without processing. The current study represents a step toward deploying deep learning algorithms to help the speech understanding of HI listeners in everyday conditions. V
Recently, deep learning based speech segregation has been shown to improve human speech intelligibility in noisy environments. However, one important factor not yet considered is room reverberation, which characterizes typical daily environments. The combination of reverberation and background noise can severely degrade speech intelligibility for hearing-impaired (HI) listeners. In the current study, a deep learning based time-frequency masking algorithm was proposed to address both room reverberation and background noise. Specifically, a deep neural network was trained to estimate the ideal ratio mask, where anechoic-clean speech was considered as the desired signal. Intelligibility testing was conducted under reverberant-noisy conditions with reverberation time T60 = 0.6 s, plus speech-shaped noise or babble noise at various signal-to-noise ratios. The experiments demonstrated that substantial speech intelligibility improvements were obtained for HI listeners. The algorithm was also somewhat beneficial for normal-hearing (NH) listeners. In addition, sentence intelligibility scores for HI listeners with algorithm processing approached or matched those of young-adult NH listeners without processing. The current study represents a step toward deploying deep learning algorithms to help the speech understanding of HI listeners in everyday conditions. [Work supported by NIH.]
Many rodents use day length to time reproduction to occur when resources are abundant, but some species also use supplementary environmental cues. One supplementary cue is the plant-derived compound, 6-methoxy-2-benzoxazolinone (6-MBOA). Most rodents grow their gonads in response to 6-MBOA in their diets, but it is presently unknown whether they also use 6-MBOA to adjust other aspects of physiology, specifically their immune systems. 6-MBOA is structurally similar to melatonin, and seasonal changes in rodent immune activities are often mediated by melatonin. We therefore predicted that white-footed mice (Peromyscus leucopus), which breed seasonally and are reproductively sensitive to melatonin, would adjust their immune systems when fed 6-MBOA. 6-MBOA treated mice in long day lengths regressed their testes to a greater extent than mice fed a standard diet, or mice kept in short day lengths and fed 6-MBOA or a standard diet. One type of immune activity (delayed-type hypersensitivity) was not affected by 6-MBOA, however, although responses were greater in short versus long day mice. In sum, P. leucopus responded reproductively to 6-MBOA, although differently than other species; immune activity was unaffected. Other aspects of the immune system, especially in herbivorous rodents, may be affected by 6-MBOA and thus warrant further study.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.