ライフサイエンスコーパス: speech recognition

1 for bench-marking such devices is automatic speech recognition.

2 r unmask speech, thus hindering or improving speech recognition.

3 kthroughs in natural language processing and speech recognition.

4 e-warping algorithm, originally designed for speech recognition.

5 s of the cortical processes supporting human speech recognition.

6 ided speech recognition and postimplantation speech recognition.

7 tures like georeferencing, image tagging and speech recognition.

8 sts an involvement of the sensory thalami in speech recognition.

9 ing input to the auditory cortex facilitates speech recognition.

10 ren's multitasking abilities during degraded speech recognition.

11 ask costs while multitasking during degraded speech recognition.

12 specific tasks, such as image processing and speech recognition.

13 ion cues may be a strong predictor for aided speech recognition.

14 to show the application of these devices in speech recognition.

15 hesized to have additive negative effects on speech recognition.

16 eech sounds and is behaviorally relevant for speech recognition.

17 neighborhoods may shift, adversely affecting speech recognition.

18 cular frequencies, or formants, essential in speech recognition.

19 complex forms of sensory processing, such as speech recognition.

20 ory modalities--face recognition and speaker/speech recognition.

21 l-world tasks, such as vision, language, and speech recognition.

22 s demonstrate that individual differences in speech recognition abilities are reflected in the underl

23 task-dependent modulation is associated with speech recognition abilities.

24 bed spectrotemporal statistics, we show that speech recognition accuracy at a fixed noise level varie

25 erberation can cause severe difficulties for speech recognition algorithms and hearing-impaired peopl

26 istic modeling methods akin to those used in speech recognition and computational linguistics were us

27 ng Lips under face masks, enabling effective speech recognition and fostering conversational accessib

28 l source separation can be applied to robust speech recognition and hearing aids and may be extended

29 Speech recognition and language learning can be affected

30 ata involved speaker segmentation, automatic speech recognition and machine learning classification.

31 g fully automated methods based on automatic speech recognition and natural language processing algor

32 the TFS in natural speech sentences on both speech recognition and neural coding.

33 dynamic behaviors (motifs), as it is done in speech recognition and other data mining applications.

34 hat report comparisons of preoperative aided speech recognition and postimplantation speech recogniti

35 chieved spectacular performance in image and speech recognition and synthesis.

36 ural networks (RNN) that are widely used for speech-recognition and natural language processing have

37 l to significantly improve music perception, speech recognition, and speech prosody perception in CI

38 ic technologies such as machine translation, speech recognition, and speech synthesis.

39 ng human and ASR solutions to the problem of speech recognition, and suggest the potential for furthe

40 pectral resolution, temporal resolution, and speech recognition are well defined in adults with cochl

41 sks, like image classification and automatic speech recognition, are now the best predictors of neura

42 omputational tasks, from image processing to speech recognition, artificial intelligence and deep lea

43 Automatic Speech Recognition (ASR) systems with near-human levels

44 Automated speech recognition (ASR) systems, which use sophisticate

45 d speech technology tools, such as Automatic Speech Recognition (ASR) systems.

46 By leveraging text-to-speech and automatic speech recognition (ASR) technologies, the cost, time, a

47 ocial cognition and communication (affective speech recognition (ASR), reading the mind in the eyes,

48 exceptional performance of SSL in Automatic Speech Recognition (ASR).

49 mple, nonbiological motion as well as visual speech recognition compared with TMS over the vertex, an

50 ata imply that previously reported emotional speech recognition deficits in basal ganglia patients ma

51 d deficits in neural synchrony contribute to speech recognition deficits.

52 aks down in hearing-impaired individuals and speech recognition devices.

53 Ms show potential for automatic detection of speech recognition errors in radiology reports.

54 ative large language models (LLMs) to detect speech recognition errors in radiology reports.

55 MRI reports was assessed by radiologists for speech recognition errors.

56 est that tinnitus negatively affected masked speech recognition even in individuals with no measurabl

57 f vocoder CI simulations is assessed through speech recognition experiments with normally-hearing sub

58 longer-term improvements in the accuracy of speech recognition following perceptual learning resulte

59 (n = 7) for actual continuous and fluent lip speech recognition for 93 English sentences, even observ

60 e for normal hearing listeners and automatic speech recognition for machines.

61 eficial in many disciplines including visual speech recognition, for surgical outcome assessment in p

62 Using speech recognition, gaze points corresponding to each le

63 ication, but their relative contributions to speech recognition have not been fully explored.

64 reliable neural representation suitable for speech recognition, however, remains elusive.

65 Speech recognition in a single-talker masker differed on

66 ners in everyday conversations, meaning that speech recognition in conventional tests might overestim

67 The masking release (MR; i.e., better speech recognition in fluctuating compared with continuo

68 portant in acoustic communication, including speech recognition in humans.

69 o-haptic" stimulation substantially improved speech recognition in multi-talker noise when the speech

70 ABA levels, greater central gain, and poorer speech recognition in noise (SIN).

71 Speech recognition in noise can be challenging for older

72 gnition of time-compressed speech and poorer speech recognition in noise for both younger and older a

73 In addition, participants' speech recognition in noise improved, with a lower score

74 come Inventory for Hearing Aids (IOI-HA) and speech recognition in noise measured using an abbreviate

75 formance on the adapted cognitive test and a speech recognition in noise task.

76 Speech recognition in noise was compared for cochlear im

77 Improvement of speech recognition in noise was positively associated wi

78 ognition in quiet, FM significantly enhances speech recognition in noise, as well as speaker and tone

79 cal representation limits the performance of speech recognition in noise.

80 larly their effectiveness in improving human speech recognition in noise.

81 fect size r = 0.3 [95% CI, 0.0-0.5]) but not speech recognition in noise.

82 ce of "statistical" adaptation for improving speech recognition in noisy backgrounds.

83 o the auditory cortex.SIGNIFICANCE STATEMENT Speech recognition in noisy environments is a challengin

84 tures in a task-specific manner to deal with speech recognition in noisy environments.

85 ry assistive technologies aimed at enhancing speech recognition in noisy settings.

86 esolution were significantly correlated with speech recognition in quiet or noise for children with C

87 mber of spectral bands may be sufficient for speech recognition in quiet, FM significantly enhances s

88 h-frequency pure-tone average (4-12 kHz) and speech-recognition in noise performance measured with WI

89 for experimental and clinical assessment of speech recognition, in which good performance can arise

90 ause of resident-to-attending discrepancies, speech recognition inaccuracies, and large workload.

91 that (1) this task-dependent modulation for speech recognition increases in parallel with the sensor

92 factor suggested to correlate with CI-aided speech recognition is frequency-to-place mismatch, or th

93 er, results suggest that noise adaptation in speech recognition is probably mediated by neural dynami

94 Speech recognition is remarkably robust to the listening

95 n deals with such sensory uncertainty during speech recognition is to-date missing.

96 ng normal aging in humans, preserving robust speech recognition late into life.

97 usoidal amplitude modulation detection), and speech recognition (measured via monosyllabic word recog

98 etween 12-month postoperative improvement in speech recognition measures and screening positive or no

99 roach, we utilized an advanced deep learning speech recognition model to investigate the intelligibil

100 Our findings demonstrate the potential of speech recognition models in facilitating auditory resea

101 arious contexts, such as computer vision and speech recognition, multiview learning has not yet been

102 ound in numerous fields, including image and speech recognition, natural language processing, and aut

103 strategy employed in, for example, image or speech recognition or health data evaluations, among oth

104 associated with the degree of improvement of speech recognition or patient-reported outcome measures

105 r understanding of individual differences in speech recognition outcomes and contributes to more comp

106 Speech recognition outcomes with a cochlear implant (CI)

107 atch was negatively correlated with CI-aided speech recognition outcomes, but the association was onl

108 nificantly associated with improved CI-aided speech recognition outcomes.

109 amount of task-dependent modulation and the speech recognition performance across participants withi

110 onsiderable overlap in the audiograms and in speech recognition performance in the unimplanted ear be

111 In general, measures of speech recognition performance were well accounted for b

112 of the neuromorphic hardware to the overall speech recognition performance.

113 s where NH and HI listeners both showed high speech recognition performance.

114 al study, with respect to preoperative aided speech recognition, postoperative cochlear implant outco

115 This research aims to bridge the gap between speech recognition processes in humans and machines, usi

116 These data, combined with more rigorous speech recognition results in older children, merit a gr

117 noise ratio) scores, and association of each speech recognition score change with aided preoperative

118 modulation is positively correlated with the speech recognition scores of individual subjects.

119 CIQOL-35 domains had greater improvement in speech recognition scores than patients who did not, but

120 ns between age at implantation and change in speech recognition scores were -0.12 (95% CI, -0.23 to -

121 processed by a machine learning model using speech recognition software.

122 Speech recognition starts with representations of basic

123 mations and the neuromorphic hardware to the speech recognition success rate.

124 al synchrony were the strongest predictor of speech recognition, such that poorer synchrony predicted

125 Associations between neural synchrony and speech recognition suggest that individual and age-relat

126 Reports were then entered into the speech recognition system so that each report was associ

127 uce a variant model of the WHISPER automatic speech recognition system that flags intonation unit bou

128 diobook comprehension with the deep-learning speech recognition system Whisper.

129 abled automatic report population within the speech recognition system.

130 e 6- and 4-channel conditions of the primary speech recognition task with decreased accuracy on the v

131 In a speech recognition task with no overt motor component, m

132 Artificial neural networks excel in speech recognition tasks and offer promising computation

133 niculate body, MGB) response is modulated by speech recognition tasks and the amount of this task-dep

134 : there are higher responses in left MGB for speech recognition tasks that require tracking of fast-v

135 for ameliorating hearing loss and improving speech recognition technology in the presence of backgro

136 uce these performance differences and ensure speech recognition technology is inclusive.

137 alian prospective cohort study used advanced speech recognition technology to capture young children'

138 re has direct translational implications for speech recognition technology.

139 Speech recognition telephone calls to parents in the int

140 statistically significant improvement in all speech recognition tests postoperatively beyond measurem

141 month postoperative measures using 1 or more speech recognition tests were studied.

142 and implant experience to undergo adult-type speech recognition tests, surgical series show that thes

143 o and audio processing, computer vision, and speech recognition, their applications to three-dimensio

144 Originally developed for speech recognition, this method has been used in data mi

145 ts (aged 55 or older underwent pure-tone and speech-recognition thresholding.

146 Speech recognition thresholds (SRTs) were measured with

147 For competing speech, speech recognition thresholds were measured for differen

148 Speech recognition thresholds were measured for target s

149 th standardized pure-tone averages (PTA) and speech-recognition thresholds (SRT).

150 -2.0 self-supervised framework for automatic speech recognition to continuous seismic signals emanati

151 Human speech recognition transforms a continuous acoustic sign

152 omplementary contributions to support robust speech recognition under realistic listening situations.

153 ramatically improved the state-of-the-art in speech recognition, visual object recognition, object de

154 Eye tracking with speech recognition was 92% accurate in labeling lesion l

155 ols, behavioral improvement in auditory-only speech recognition was based on an area typically involv

156 evealed that FM is particularly critical for speech recognition with a competing voice and is indepen

157 Each circuit markedly improved speech recognition, with greater improvement observed fo