TASLP Volume 30 | 2022

Deep neural networks (DNNs) represent the mainstream methodology for supervised speech enhancement, primarily due to their capability to model complex functions using hierarchical representations. However, a recent study revealed that DNNs trained on a single corpus fail to generalize to untrained corpora, especially in low signal-to-noise ratio (SNR) conditions.

In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain data are accessible (e.g., no intent labels for the intent classification task).

The perception of one’s own voice influences the acceptance of hearing devices, such as headphones, headsets or hearing aids. When these devices fully or partially occlude the ear canal, the wearer’s own voice sounds boomy or like talking in a barrel. This is called occlusion effect . Occluding the ear canal results in an amplification of body-conducted sounds, mainly at low frequencies, and an attenuation of air-conducted sounds, predominantly at high frequencies, compared to the open ear. 

Transcribing structural data into readable text (data-to-text) is a fundamental language generation task. One of its challenges is to plan the input records for text realization. Recent works tackle this problem with a static planner, which performs record planning in advance for text realization. However, they cannot revise plans to cope with unexpected realized text and require golden plans for supervised training. To address these issues, we first propose a model that contains a dynamic planner.

We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural waveform codec (NWC) during its feedforward routine. The proposed NWC also defines quantization and entropy coding as a trainable module, so the coding artifacts and bitrate control are handled during the optimization process.

Automatically solving math word problems is a critical task in the field of natural language processing. Recent models have reached their performance bottleneck and require more high-quality data for training. We propose a novel data augmentation method that reverses the mathematical logic of math word problems to produce new high-quality math problems and introduce new knowledge points that can benefit learning the mathematical reasoning logic.