Search Results (4)

This paper presents an echo suppression system that combines a linear acoustic echo canceller (AEC) with a deep complex convolutional recurrent network (DCCRN) for residual echo suppression. The filter taps of the AEC are adjusted in subbands by using the normalized sign-error least mean squares (NSLMS) algorithm. The NSLMS is compared with the commonly-used normalized least mean squares (NLMS), and the combination of each with the proposed deep residual echo suppression model is studied. The utilization of a pre-trained deep-learning speech denoising model as an alternative to a residual echo suppressor (RES) is also studied. The results showed that the performance of the NSLMS is superior to that of the NLMS in all settings. With the NSLMS output, the proposed RES achieved better performance than the larger pre-trained speech denoiser model. More notably, the denoiser performed considerably better on the NSLMS output than on the NLMS output, and the performance gap was greater than the respective gap when employing the RES, indicating that the residual echo in the NSLMS output was more akin to noise than speech. Therefore, when little data is available to train an RES, a pre-trained speech denoiser is a viable alternative when employing the NSLMS for the preceding linear AEC. Full article

Acoustic echo in full-duplex telecommunication systems is a common problem that may cause desired-speech quality degradation during double-talk periods. This problem is especially challenging in low signal-to-echo ratio (SER) scenarios, such as hands-free conversations over mobile phones when the loudspeaker volume is high. This paper proposes a two-stage deep-learning approach to residual echo suppression focused on the low SER scenario. The first stage consists of a speech spectrogram masking model integrated with a double-talk detector (DTD). The second stage consists of a spectrogram refinement model optimized for speech quality by minimizing a perceptual evaluation of speech quality (PESQ) related loss function. The proposed integration of DTD with the masking model outperforms several other configurations based on previous studies. We conduct an ablation study that shows the contribution of each part of the proposed system. We evaluate the proposed system in several SERs and demonstrate its efficiency in the challenging setting of a very low SER. Finally, the proposed approach outperforms competing methods in several residual echo suppression metrics. We conclude that the proposed system is well-suited for the task of low SER residual echo suppression. Full article

Patients with inflammatory bowel disease (IBD) treated with anti-tumor-necrosis factor-alpha (TNFα) exhibited lower serologic responses one-month following the second dose of the COVID-19 BNT162b2 vaccine compared to those not treated with anti-TNFα (non-anti-TNFα) or to healthy controls (HCs). We comprehensively analyzed long-term humoral responses, including anti-spike (S) antibodies, serum inhibition, neutralization, cross-reactivity and circulating B cell six months post BNT162b2, in patients with IBD stratified by therapy compared to HCs. Subjects enrolled in a prospective, controlled, multi-center Israeli study received two BNT162b2 doses. Anti-S levels, functional activity, specific B cells, antigen cross-reactivity, anti-nucleocapsid levels, adverse events and IBD disease score were detected longitudinally. In total, 240 subjects, 151 with IBD (94 not treated with anti-TNFα and 57 treated with anti-TNFα) and 89 HCs participated. Six months after vaccination, patients with IBD treated with anti-TNFα had significantly impaired BNT162b2 responses, specifically, more seronegativity, decreased specific circulating B cells and cross-reactivity compared to patients untreated with anti-TNFα. Importantly, all seronegative subjects were patients with IBD; of those, >90% were treated with anti-TNFα. Finally, IBD activity was unaffected by BNT162b2. Altogether these data support the earlier booster dose administration in these patients. Full article

Background: Crohn’s disease (CD) and ulcerative colitis (UC) are chronic, immune-mediated inflammatory bowel diseases (IBD) affecting millions of people worldwide. IBD therapies, designed for continuous immune suppression, often render patients more susceptible to infections. The effect of the immune suppression on the risk of coronavirus disease-19 (COVID-19) is not fully determined yet. Objective: To describe COVID-19 characteristics and outcomes and to evaluate the association between IBD phenotypes, infection outcomes and immunomodulatory therapies. Methods: In this multi-center study, we prospectively followed IBD patients with proven COVID-19. De-identified data from medical charts were collected including age, gender, IBD type, IBD clinical activity, IBD treatments, comorbidities, symptoms and outcomes of COVID-19. A multivariable regression model was used to examine the effect of immunosuppressant drugs on the risk of infection by COVID-19 and the outcomes. Results: Of 144 IBD patients, 104 (72%) were CD and 40 (28%) were UC. Mean age was 32.2 ± 12.6 years. No mortalities were reported. In total, 94 patients (65.3%) received biologic therapy. Of them, 51 (54%) at escalated doses, 10 (11%) in combination with immunomodulators and 9 (10%) with concomitant corticosteroids. Disease location, behavior and activity did not correlate with the severity of COVID-19. Biologics as monotherapy or with immunomodulators or corticosteroids were not associated with more severe infection. On the contrary, patients receiving biologics had significantly milder infection course (p = 0.001) and were less likely to be hospitalized (p = 0.001). Treatment was postponed in 34.7% of patients until recovery from COVID-19, without consequent exacerbation. Conclusion: We did not witness aggravated COVID-19 outcomes in patients with IBD. Patients treated with biologics had a favorable outcome. Full article