Triple-0: Zero-shot denoising and dereverberation on an end-to-end frozen anechoic speech separation network.

Speech enhancement is crucial both for human and machine listening applications. Over the last decade, the use of deep learning for speech enhancement has resulted in tremendous improvement over the classical signal processing and machine learning methods. However, training a deep neural network is not only time-consuming; it also requires extensive computational resources and a large training dataset. Transfer learning, i.e. using a pretrained network for a new task, comes to the rescue by reducing the amount of training time, computational resources, and the required dataset, but the network still needs to be fine-tuned for the new task. This paper presents a novel method of speech denoising and dereverberation (SD&D) on an end-to-end frozen binaural anechoic speech separation network. The frozen network requires neither any architectural change nor any fine-tuning for the new task, as is usually required for transfer learning. The interaural cues of a source placed inside noisy and echoic surroundings are given as input to this pretrained network to extract the target speech from noise and reverberation. Although the pretrained model used in this paper has never seen noisy reverberant conditions during its training, it performs satisfactorily for zero-shot testing (ZST) under these conditions. It is because the pretrained model used here has been trained on the direct-path interaural cues of an active source and so it can recognize them even in the presence of echoes and noise. ZST on the same dataset on which the pretrained network was trained (homo-corpus) for the unseen class of interference, has shown considerable improvement over the weighted prediction error (WPE) algorithm in terms of four objective speech quality and intelligibility metrics. Also, the proposed model offers similar performance provided by a deep learning SD&D algorithm for this dataset under varying conditions of noise and reverberations. Similarly, ZST on a different dataset has provided an improvement in intelligibility and almost equivalent quality as provided by the WPE algorithm.

Solid Self-Nanoemulsifying Drug Delivery Systems of Furosemide: In Vivo Proof of Concept for Enhanced Predictable Therapeutic Response.

Liquid self-nano emulsifying drug delivery systems (SNEDDS) of furosemide (FSM) have been explored as a potential solution for enhancing solubility and permeability but are associated with rapid emulsification, spontaneous drug release, and poor in vivo correlation. To overcome the shortcoming, this study aimed to develop liquid and solid self-emulsifying drug delivery systems for FSM, compare formulation dynamics, continue in vivo therapeutic efficacy, and investigate the advantages of solidification. For this purpose, liquid SNEDDS (L-SEDDS-FSM) were formed using oleic acid as an oil, chremophore EL, Tween 80, Tween 20 as a surfactant, and PEG 400 as a co-surfactant containing 53 mg/mL FSM. At the same time, solid SNEDDS (S-SEDDS-FSM) was developed by adsorbing liquid SNEDDS onto microcrystalline cellulose in a 1:1 ratio. Both formulations were evaluated for size, zeta potential, lipase degradation, and drug release. Moreover, in vivo diuretic studies regarding urine volume were carried out in mice to investigate the therapeutic responses of liquid and solid SNEDDS formulations. After dilution, L-SEDDS-FSM showed a mean droplet size of 115 ± 4.5 nm, while S-SEDDS-FSM depicted 116 ± 2.6 nm and zeta potentials of -5.4 ± 0.55 and -6.22 ± 1.2, respectively. S-SEDDS-FSM showed 1.8-fold reduced degradation by lipase enzymes in comparison to L-SEDDS-FSM. S-SEDDS-FSM demonstrated a sustained drug release pattern, releasing 63% of the drug over 180 min, in contrast to L-SEDDS-FSM, exhibiting 90% spontaneous drug release within 30 min. L-SEDDS-FSM exhibited a rapid upsurge in urine output (1550 ± 56 µL) compared to S-SEDDS-FSM, showing gradual urine output (969 ± 29 µL) till the 4th h of the study, providing sustained urine output yet a predictable therapeutic response. The solidification of SNEDDS effectively addresses challenges associated with spontaneous drug release and precipitation observed in liquid SNEDDS, highlighting the potential benefits of solid SNEDDS in improving the therapeutic response of furosemide.

DEW: A wavelet approach of rare sound event detection.

This paper presents a novel sound event detection (SED) system for rare events occurring in an open environment. Wavelet multiresolution analysis (MRA) is used to decompose the input audio clip of 30 seconds into five levels. Wavelet denoising is then applied on the third and fifth levels of MRA to filter out the background. Significant transitions, which may represent the onset of a rare event, are then estimated in these two levels by combining the peak-finding algorithm with the K-medoids clustering algorithm. The small portions of one-second duration, called 'chunks' are cropped from the input audio signal corresponding to the estimated locations of the significant transitions. Features from these chunks are extracted by the wavelet scattering network (WSN) and are given as input to a support vector machine (SVM) classifier, which classifies them. The proposed SED framework produces an error rate comparable to the SED systems based on convolutional neural network (CNN) architecture. Also, the proposed algorithm is computationally efficient and lightweight as compared to deep learning models, as it has no learnable parameter. It requires only a single epoch of training, which is 5, 10, 200, and 600 times lesser than the models based on CNNs and deep neural networks (DNNs), CNN with long short-term memory (LSTM) network, convolutional recurrent neural network (CRNN), and CNN respectively. The proposed model neither requires concatenation with previous frames for anomaly detection nor any additional training data creation needed for other comparative deep learning models. It needs to check almost 360 times fewer chunks for the presence of rare events than the other baseline systems used for comparison in this paper. All these characteristics make the proposed system suitable for real-time applications on resource-limited devices.