Time course of a perceptual enhancement effect for noise-masked speech in reverberant environments.
Ontology highlight
ABSTRACT:
SUBMITTER: Brandewie E
PROVIDER: S-EPMC3732299 | biostudies-other | 2013 Aug
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Speech signals are degraded in real-life environments, as a product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions. To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combinations of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation was made based on quality measurements of the signal's spectrum, the training time of the networks, and statistical validation of results. In total, 120 artificial neural networks of eight different types were trained and compared. The results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, given that reduction in training time is on the order of 30%, in processes that can normally take several days or weeks, depending on the amount of data. The results also present advantages in efficiency, but without a significant drop in quality.
| S-EPMC7148527 | biostudies-literature
Project description:Humans are adept at understanding speech despite the fact that our natural listening environment is often filled with interference. An example of this capacity is phoneme restoration, in which part of a word is completely replaced by noise, yet listeners report hearing the whole word. The neurological basis for this unconscious fill-in phenomenon is unknown, despite being a fundamental characteristic of human hearing. Here, using direct cortical recordings in humans, we demonstrate that missing speech is restored at the acoustic-phonetic level in bilateral auditory cortex, in real-time. This restoration is preceded by specific neural activity patterns in a separate language area, left frontal cortex, which predicts the word that participants later report hearing. These results demonstrate that during speech perception, missing acoustic content is synthesized online from the integration of incoming sensory cues and the internal neural dynamics that bias word-level expectation and prediction.
| S-EPMC5187421 | biostudies-literature
Project description:Sensory and motor skills can be improved with training, but learning is often restricted to practice stimuli. As an exception, training on closed-loop (CL) sensorimotor interfaces, such as action video games and musical instruments, can impart a broad spectrum of perceptual benefits. Here we ask whether computerized CL auditory training can enhance speech understanding in levels of background noise that approximate a crowded restaurant. Elderly hearing-impaired subjects trained for 8 weeks on a CL game that, like a musical instrument, challenged them to monitor subtle deviations between predicted and actual auditory feedback as they moved their fingertip through a virtual soundscape. We performed our study as a randomized, double-blind, placebo-controlled trial by training other subjects in an auditory working-memory (WM) task. Subjects in both groups improved at their respective auditory tasks and reported comparable expectations for improved speech processing, thereby controlling for placebo effects. Whereas speech intelligibility was unchanged after WM training, subjects in the CL training group could correctly identify 25% more words in spoken sentences or digit sequences presented in high levels of background noise. Numerically, CL audiomotor training provided more than three times the benefit of our subjects' hearing aids for speech processing in noisy listening conditions. Gains in speech intelligibility could be predicted from gameplay accuracy and baseline inhibitory control. However, benefits did not persist in the absence of continuing practice. These studies employ stringent clinical standards to demonstrate that perceptual learning on a computerized audio game can transfer to "real-world" communication challenges.
| S-EPMC5997394 | biostudies-literature
Project description:Speech perception performance for degraded speech can improve with practice or exposure. Such perceptual learning is thought to be reliant on attention and theoretical accounts like the predictive coding framework suggest a key role for attention in supporting learning. However, it is unclear whether speech perceptual learning requires undivided attention. We evaluated the role of divided attention in speech perceptual learning in two online experiments (N = 336). Experiment 1 tested the reliance of perceptual learning on undivided attention. Participants completed a speech recognition task where they repeated forty noise-vocoded sentences in a between-group design. Participants performed the speech task alone or concurrently with a domain-general visual task (dual task) at one of three difficulty levels. We observed perceptual learning under divided attention for all four groups, moderated by dual-task difficulty. Listeners in easy and intermediate visual conditions improved as much as the single-task group. Those who completed the most challenging visual task showed faster learning and achieved similar ending performance compared to the single-task group. Experiment 2 tested whether learning relies on domain-specific or domain-general processes. Participants completed a single speech task or performed this task together with a dual task aiming to recruit domain-specific (lexical or phonological), or domain-general (visual) processes. All secondary task conditions produced patterns and amount of learning comparable to the single speech task. Our results demonstrate that the impact of divided attention on perceptual learning is not strictly dependent on domain-general or domain-specific processes and speech perceptual learning persists under divided attention.
| S-EPMC10408355 | biostudies-literature
Project description:Ideal time-frequency (TF) masks can reject noise and improve the recognition of speech-noise mixtures. An ideal TF mask is constructed with prior knowledge of the target speech signal. The intelligibility of a processed speech-noise mixture depends upon the threshold criterion used to define the TF mask. The study reported here assessed the effect of training on the recognition of speech in noise after processing by ideal TF masks that did not restore perfect speech intelligibility. Two groups of listeners with normal hearing listened to speech-noise mixtures processed by TF masks calculated with different threshold criteria. For each group, a threshold criterion that initially produced word recognition scores between 0.56-0.69 was chosen for training. Listeners practiced with one set of TF-masked sentences until their word recognition performance approached asymptote. Perceptual learning was quantified by comparing word-recognition scores in the first and last training sessions. Word recognition scores improved with practice for all listeners with the greatest improvement observed for the same materials used in training.
| S-EPMC3606232 | biostudies-other
Project description:Perceptual adaptation to a talker enables listeners to efficiently resolve the many-to-many mapping between variable speech acoustics and abstract linguistic representations. However, models of speech perception have not delved into the variety or the quantity of information necessary for successful adaptation, nor how adaptation unfolds over time. In three experiments using speeded classification of spoken words, we explored how the quantity (duration), quality (phonetic detail), and temporal continuity of talker-specific context contribute to facilitating perceptual adaptation to speech. In single- and mixed-talker conditions, listeners identified phonetically-confusable target words in isolation or preceded by carrier phrases of varying lengths and phonetic content, spoken by the same talker as the target word. Word identification was always slower in mixed-talker conditions than single-talker ones. However, interference from talker variability decreased as the duration of preceding speech increased but was not affected by the amount of preceding talker-specific phonetic information. Furthermore, efficiency gains from adaptation depended on temporal continuity between preceding speech and the target word. These results suggest that perceptual adaptation to speech may be understood via models of auditory streaming, where perceptual continuity of an auditory object (e.g., a talker) facilitates allocation of attentional resources, resulting in more efficient perceptual processing.
| S-EPMC6732236 | biostudies-literature
Project description:PurposeThe purpose of this study was to examine the effects of varying wide dynamic range compression (WDRC) release time on intelligibility and clarity of reverberant speech. The study also considered the role of individual working memory.MethodThirty older listeners with mild to moderately-severe sloping sensorineural hearing loss participated. Individuals were divided into high and low working memory groups on the basis of the results of a reading span test. Participants listened binaurally to sentence stimuli simulated at a range of reverberation conditions and WDRC release times using a high compression ratio. Outcome measures included objective intelligibility and subjective clarity ratings.ResultsSpeech intelligibility and clarity ratings both decreased as a function of reverberation. The low working memory group demonstrated a greater decrease in intelligibility with increasing amounts of reverberation than the high working memory group. Both groups, regardless of working memory, had higher speech intelligibility and clarity ratings with longer WDRC release times. WDRC release time had a larger effect on speech intelligibility under more reverberant conditions.ConclusionsReverberation significantly affects speech intelligibility, particularly for individuals with lower working memory. In addition, longer release times in hearing aids may improve listener speech intelligibility and clarity in reverberant environments.
| S-EPMC5399768 | biostudies-literature
Project description:Word in noise identification is facilitated by acoustic differences between target and competing sounds and temporal separation between the onset of the masker and that of the target. Younger and older adults are able to take advantage of onset delay when the masker is dissimilar (Noise) to the target word, but only younger adults are able to do so when the masker is similar (Babble). We examined the neural underpinning of this age difference using cortical evoked responses to words masked by either Babble or Noise when the masker preceded the target word by 100 or 600 ms in younger and older adults, after adjusting the signal-to-noise ratios (SNRs) to equate behavioural performance across age groups and conditions. For the 100 ms onset delay, the word in noise elicited an acoustic change complex (ACC) response that was comparable in younger and older adults. For the 600 ms onset delay, the ACC was modulated by both masker type and age. In older adults, the ACC to a word in babble was not affected by the increase in onset delay whereas younger adults showed a benefit from longer delays. Hence, the age difference in sensitivity to temporal delay is indexed by early activity in the auditory cortex. These results are consistent with the hypothesis that an increase in onset delay improves stream segregation in younger adults in both noise and babble, but only in noise for older adults and that this change in stream segregation is evident in early cortical processes.
| S-EPMC9389464 | biostudies-literature
Project description:Speech understanding in noisy environments is still one of the major challenges for cochlear implant (CI) users in everyday life. We evaluated a speech enhancement algorithm based on neural networks (NNSE) for improving speech intelligibility in noise for CI users. The algorithm decomposes the noisy speech signal into time-frequency units, extracts a set of auditory-inspired features and feeds them to the neural network to produce an estimation of which frequency channels contain more perceptually important information (higher signal-to-noise ratio, SNR). This estimate is used to attenuate noise-dominated and retain speech-dominated CI channels for electrical stimulation, as in traditional n-of-m CI coding strategies. The proposed algorithm was evaluated by measuring the speech-in-noise performance of 14 CI users using three types of background noise. Two NNSE algorithms were compared: a speaker-dependent algorithm, that was trained on the target speaker used for testing, and a speaker-independent algorithm, that was trained on different speakers. Significant improvements in the intelligibility of speech in stationary and fluctuating noises were found relative to the unprocessed condition for the speaker-dependent algorithm in all noise types and for the speaker-independent algorithm in 2 out of 3 noise types. The NNSE algorithms used noise-specific neural networks that generalized to novel segments of the same noise type and worked over a range of SNRs. The proposed algorithm has the potential to improve the intelligibility of speech in noise for CI users while meeting the requirements of low computational complexity and processing delay for application in CI devices.
| S-EPMC5256482 | biostudies-literature
Project description:The learning curve in perceptual learning is typically sampled in blocks of trials, which could result in imprecise and possibly biased estimates, especially when learning is rapid. Recently, Zhao, Lesmes, and Lu (2017, 2019) developed a Bayesian adaptive quick Change Detection (qCD) method to accurately, precisely, and efficiently assess the time course of perceptual sensitivity change. In this study, we implemented and tested the qCD method in assessing the learning curve in a four-alternative forced-choice global motion direction identification task in both simulations and a psychophysical experiment. The stimulus intensity in each trial was determined by the qCD, staircase or random stimulus selection (RSS) methods. Simulations showed that the accuracy (bias) and precision (standard deviation or confidence bounds) of the estimated learning curves from the qCD were much better than those obtained by the staircase and RSS method; this is true for both trial-by-trial and post hoc segment-by-segment qCD analyses. In the psychophysical experiment, the average half widths of the 68.2% credible interval of the estimated thresholds from the trial-by-trial and post hoc segment-by-segment qCD analyses were both quite small. Additionally, the overall estimates from the qCD and staircase methods matched extremely well in this task where the behavioral rate of learning is relatively slow. Our results suggest that the qCD method can precisely and accurately assess the trial-by-trial time course of perceptual learning.
| S-EPMC6510278 | biostudies-literature