Related papers: Improving Frame-Online Neural Speech Enhancement w…

Invariance to microphone array configuration is a rare attribute in neural beamformers. Filter-and-sum (FS) methods in this class define the target signal with respect to a reference channel. However, this not only complicates formulation…

In this paper, a two-stage dual tree complex wavelet packet transform (DTCWPT) based speech enhancement algorithm has been proposed, in which a speech presence probability (SPP) estimator and a generalized minimum mean squared error (MMSE)…

To cope with reverberation and noise in single channel acoustic scenarios, typical supervised deep neural network~(DNN)-based techniques learn a mapping from reverberant and noisy input features to a user-defined target. Commonly used…

Overfitting is defined as the fact that the current model fits a specific data set perfectly, resulting in weakened generalization, and ultimately may affect the accuracy in predicting future data. In this research we used an EHR dataset…

A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…

Processing of speech and audio signals with time-frequency representations require windowing methods which allow perfect reconstruction of the original signal and where processing artifacts have a predictable behavior. The most common…

This paper proposes an improved version of the current online learning algorithm for a general fuzzy min-max neural network (GFMM) to tackle existing issues concerning expansion and contraction steps as well as the way of dealing with…

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…

Mainstream deep learning-based dysarthric speech detection approaches typically rely on processing the magnitude spectrum of the short-time Fourier transform of input signals, while ignoring the phase spectrum. Although considerable insight…

We introduce Amortized Neural Networks (AmNets), a compute cost- and latency-aware network architecture particularly well-suited for sequence modeling tasks. We apply AmNets to the Recurrent Neural Network Transducer (RNN-T) to reduce…

The OTFS (Orthogonal Time Frequency Space) is widely acknowledged for its ability to combat Doppler spread in time-varying channels. In this paper, another advantage of OTFS over OFDM (Orthogonal Frequency Division Multiplexing) will be…

Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to…

Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep filtering (DF) recently demonstrated its capabilities for low-latency scenarios like hearing…

Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired…

Target speech separation is the process of filtering a certain speaker's voice out of speech mixtures according to the additional speaker identity information provided. Recent works have made considerable improvement by processing signals…

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…

This paper presents a novel neural speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra. The proposed model is a cascade of a residual convolutional network and a parallel estimation…

Post-training processes are essential phases in grounding pre-trained language models to real-world tasks, with learning from demonstrations or preference signals playing a crucial role in this adaptation. We present a unified theoretical…

Voice activity and overlapped speech detection (respectively VAD and OSD) are key pre-processing tasks for speaker diarization. The final segmentation performance highly relies on the robustness of these sub-tasks. Recent studies have shown…

We propose Mobile Audio Streaming Networks (MASnet) for efficient low-latency speech enhancement, which is particularly suitable for mobile devices and other applications where computational capacity is a limitation. MASnet processes…