Related papers: Multi-Utterance Speech Separation and Association …

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…

This paper proposes APSS, a novel neural speech separation model with parallel amplitude and phase spectrum estimation. Unlike most existing speech separation methods, the APSS distinguishes itself by explicitly estimating the phase…

The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN with the…

Improving distant speech recognition is a crucial step towards flexible human-machine interfaces. Current technology, however, still exhibits a lack of robustness, especially when adverse acoustic conditions are met. Despite the significant…

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…

Recently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks. However, most systems do not fully utilize spatial information. In this paper, we propose a target speech extraction…

Deep neural networks have shown recent promise in many language-related tasks such as the modeling of conversations. We extend RNN-based sequence to sequence models to capture the long range discourse across many turns of conversation. We…

Deep neural networks (DNNs) have achieved substantial predictive performance in various speech processing tasks. Particularly, it has been shown that a monaural speech separation task can be successfully solved with a DNN-based method…

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

Recent advances in deep learning have significantly improved multichannel speech enhancement algorithms, yet conventional training loss functions such as the scale-invariant signal-to-distortion ratio (SDR) may fail to preserve fine-grained…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

Speech segmentation is an essential part of speech translation (ST) systems in real-world scenarios. Since most ST models are designed to process speech segments, long-form audio must be partitioned into shorter segments before translation.…

Sequence prediction and classification are ubiquitous and challenging problems in machine learning that can require identifying complex dependencies between temporally distant inputs. Recurrent Neural Networks (RNNs) have the ability, in…

One of the fundamental principles of contemporary linguistics states that language processing requires the ability to extract recursively nested tree structures. However, it remains unclear whether and how this code could be implemented in…

Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker verification. This new method has been tested on text-dependent…

Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or…

We propose a tensor-to-vector regression approach to multi-channel speech enhancement in order to address the issue of input size explosion and hidden-layer size expansion. The key idea is to cast the conventional deep neural network (DNN)…

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

The real-time processing of time series signals is a critical issue for many real-life applications. The idea of real-time processing is especially important in audio domain as the human perception of sound is sensitive to any kind of…