Related papers: Multi-path RNN for hierarchical modeling of long s…

Multi-channel speech enhancement aims to extract clean speech from a noisy mixture using signals captured from multiple microphones. Recently proposed methods tackle this problem by incorporating deep neural network models with spatial…

The most recent deep neural network (DNN) models exhibit impressive denoising performance in the time-frequency (T-F) magnitude domain. However, the phase is also a critical component of the speech signal that is easily overlooked. In this…

In many signal processing applications, metadata may be advantageously used in conjunction with a high dimensional signal to produce a desired output. In the case of classical Sound Source Localization (SSL) algorithms, information from a…

Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and…

Multi-frame approaches for single-microphone speech enhancement, e.g., the multi-frame minimum-power-distortionless-response (MFMPDR) filter, are able to exploit speech correlations across neighboring time frames. In contrast to…

We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditions. We aim at both speaker separation and dereverberation.…

In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specifically, we train deep bi-directional Long Short-Term Memory…

Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the…

The primary goal of ad-hoc retrieval (document retrieval in the context of question answering) is to find relevant documents satisfied the information need posted in a natural language query. It requires a good understanding of the query…

Mamba is a newly proposed architecture which behaves like a recurrent neural network (RNN) with attention-like capabilities. These properties are promising for speaker diarization, as attention-based models have unsuitable memory…

ASR models often suffer from a long-form deletion problem where the model predicts sequential blanks instead of words when transcribing a lengthy audio (in the order of minutes or hours). From the perspective of a user or downstream system…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many…

In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without…

Monaural Singing Voice Separation (MSVS) is a challenging task and has been studied for decades. Deep neural networks (DNNs) are the current state-of-the-art methods for MSVS. However, the existing DNNs are often designed manually, which is…

Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields. Previous work essentially improves the model performance by widening or…

Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce…

Short fixed-length inputs are the main bottleneck of deep learning methods in long time-series forecasting tasks. Prolonging input length causes overfitting, rapidly deteriorating accuracy. Our research indicates that the overfitting is a…

Long-term prediction of multivariate time series is still an important but challenging problem. The key to solve this problem is to capture the spatial correlations at the same time, the spatio-temporal relationships at different times and…

Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications. Existing methods usually choose…