reeva Work on speech restoration in people with aphasia

The article deals with the problem of speech restoration in persons with local lesions of the cerebral cortex, the peculiarities of interaction with patients and their relatives. The principles, tasks of restorative work in aphasia, the value of complex treatment are revealed.

Experimental filler design influences error correction rates in a word restoration paradigm

Including fillers or distractors in psycholinguistic experiments has been standard for decades; yet, relatively little is known how the design of these items interacts with critical manipulations. In this paper, we ask about the role that contextual statistical information in filler items plays in determining if and how to correct a given error, and how grammatical expectations interact with context. We first replicate a speech restoration experiment conducted by Mack, J. E., C. Clifton, L. Frazier & P. V. Taylor. 2012. (Not) hearing optional subjects: The effects of pragmatic usage preferences. Journal of Memory and Language 67. 211–223, measuring usage preferences of null-subject constructions. Then we report two additional experiments in which we manipulated only the filler items, either having noise appear uniformly at random, or with a particular bias. Our results (1) demonstrate that listeners are sensitive to statistical patterns in the distribution of noise within the experiment, and (2) suggest that this paradigm can be used to investigate interaction between the mechanisms that govern grammatical preferences, and those that govern error correction processes.

Speech enhancement by LSTM-based noise suppression followed by CNN-based speech restoration

Single-channel speech enhancement in highly non-stationary noise conditions is a very challenging task, especially when interfering speech is included in the noise. Deep learning-based approaches have notably improved the performance of speech enhancement algorithms under such conditions, but still introduce speech distortions if strong noise suppression shall be achieved. We propose to address this problem by using a two-stage approach, first performing noise suppression and subsequently restoring natural sounding speech, using specifically chosen neural network topologies and loss functions for each task. A mask-based long short-term memory (LSTM) network is employed for noise suppression and speech restoration is performed via spectral mapping with a convolutional encoder-decoder network (CED). The proposed method improves speech quality (PESQ) over state-of-the-art single-stage methods by about 0.1 points for unseen highly non-stationary noise types including interfering speech. Furthermore, it is able to increase intelligibility in low-SNR conditions and consistently outperforms all reference methods.

SPEECH REHABILITATION OF PATIENTS WITH ORAL CAVITY AND OROPHARYNGEAL CANCERS AFTER RECONSTRUCTIVE SURGERY

Oral cavity and oropharyngeal cancers usually require extensive surgeries accompanied by damages to anatomical structures and impaired speech function. The use of reconstructive-plastic techniques to replace defects after surgical resection allows the creation of a favorable functional basis for speech restoration.The purpose of the study was to compare the effectiveness and terms of speech restoration in patients with oral cavity and oropharyngeal cancers after surgical treatment using various reconstructive surgery techniques to restore postoperative defects.Material and Methods. Speech rehabilitation results were analyzed in 56 patients with stage II–IV oral cavity and oropharyngeal cancers. The age of the patients ranged from 26 to 70 years. The patients underwent either hemiglossectomy or glossectomy followed by reconstructive surgery. Postoperative speech rehabilitation was performed according to the technique developed in the Department of Head and Neck Tumors of the Cancer Research Institute. Speech function was assessed before starting treatment, at the beginning of treatment and after completion of speech rehabilitation.Results. After surgery, all patients demonstrated impaired speech function, ranging from distorted pronunciation to the complete absence of verbal communication for 5 (71.4%) and 4 (80%) patients from Ib and IIb respectively. Speech rehabilitation started 16 to 32 days after surgery. Restoration of the activity and coordination of the articulatory apparatus muscles, speech exhalation and reconstructed tongue was followed by a sound pronunciation. Postoperative speech rehabilitation allowed improvement of speech function in 100 % of cases (56 patients). A complete speech restoration was achieved for 7 patients (12.5%). The majority of these patients were from the group with hemiglossectomy. In the group of patients with glossectomy, the amplitude and coordination of movements, which could be achieved by performing articulation exercises for the reconstructed tongue, depended on the size of the remaining part of their own tissues.Conclusion. Good values of all studied parameters were observed in patients, who underwent hemiglossectomy followed by reconstruction with a free revascularized flap. No statistically significant differences between the studied parameters were found in patients, who underwent glossectomy. Speech restoration parameters were significantly better in the group of patients with hemiglossectomy and reconstruction with a free revascularized flap than in the group of patients with glossectomy).