Related papers: ADL-MVDR: All deep learning MVDR beamformer for ta…

This paper describes our NPU-ASLP system for the Audio-Visual Diarization and Recognition (AVDR) task in the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. Specifically, the weighted prediction error (WPE) and guided…

Recently, deep clustering (DPCL) based speaker-independent speech separation has drawn much attention, since it needs little speaker prior information. However, it still has much room of improvement, particularly in reverberant…

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

We propose a neural network model that can separate target speech sources from interfering sources at different angular regions using two microphones. The model is trained with simulated room impulse responses (RIRs) using omni-directional…

Single-channel, speaker-independent speech separation methods have recently seen great progress. However, the accuracy, latency, and computational cost of such methods remain insufficient. The majority of the previous methods have…

Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging…

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…

Automatic speech recognition (ASR) in multichannel, multi-speaker scenarios remains challenging due to ambient noise, reverberation and overlapping speakers. In this paper, we propose a beamforming approach that processes specific angular…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

This work introduces the Cleanformer, a streaming multichannel neural based enhancement frontend for automatic speech recognition (ASR). This model has a conformer-based architecture which takes as inputs a single channel each of raw and…

Besides reducing undesired sources (interfering sources and background noise), another important objective of a binaural beamforming algorithm is to preserve the spatial impression of the acoustic scene, which can be achieved by preserving…

Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…

Deep neural networks are often coupled with traditional spatial filters, such as MVDR beamformers for effectively exploiting spatial information. Even though single-stage end-to-end supervised models can obtain impressive enhancement,…

Any-to-any voice conversion problem aims to convert voices for source and target speakers, which are out of the training data. Previous works wildly utilize the disentangle-based models. The disentangle-based model assumes the speech…

Automatic recognition of overlapped speech remains a highly challenging task to date. Motivated by the bimodal nature of human speech perception, this paper investigates the use of audio-visual technologies for overlapped speech…

To date, mainstream target speech separation (TSS) approaches are formulated to estimate the complex ratio mask (cRM) of the target speech in time-frequency domain under supervised deep learning framework. However, the existing deep models…

Multichannel convolutive blind speech source separation refers to the problem of separating different speech sources from the observed multichannel mixtures without much a priori information about the mixing system. Multichannel nonnegative…

We investigate the effectiveness of convolutive prediction, a novel formulation of linear prediction for speech dereverberation, for speaker separation in reverberant conditions. The key idea is to first use a deep neural network (DNN) to…