Related papers: Learning deep representations by multilayer bootst…
A promising approach for speech dereverberation is based on supervised learning, where a deep neural network (DNN) is trained to predict the direct sound from noisy-reverberant speech. This data-driven approach is based on leveraging prior…
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…
A promising approach for multi-microphone speech separation involves two deep neural networks (DNN), where the predicted target speech from the first DNN is used to compute signal statistics for time-invariant minimum variance…
This paper describes multichannel speech enhancement for improving automatic speech recognition (ASR) in noisy environments. Recently, the minimum variance distortionless response (MVDR) beamforming has widely been used because it works…
This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…
Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…
While neural networks for learning representation of multi-view data have been previously proposed as one of the state-of-the-art multi-view dimension reduction techniques, how to make the representation discriminative with only a small…
Conventional methods for speaker diarization involve windowing an audio file into short segments to extract speaker embeddings, followed by an unsupervised clustering of the embeddings. This multi-step approach generates speaker assignments…
Recognition of overlapped speech has been a highly challenging task to date. State-of-the-art multi-channel speech separation system are becoming increasingly complex and expensive for practical applications. To this end, low-bit neural…
Speaker diarization remains challenging due to the need for structured speaker representations, efficient modeling, and robustness to varying conditions. We propose a performant, compact diarization framework that integrates conformer…
Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability…
Deep clustering is a recently introduced deep learning architecture that uses discriminatively trained embeddings as the basis for clustering. It was recently applied to spectrogram segmentation, resulting in impressive results on…
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…
Unsupervised deep learning is one of the most powerful representation learning techniques. Restricted Boltzman machine, sparse coding, regularized auto-encoders, and convolutional neural networks are pioneering building blocks of deep…
The goal of this paper is to adapt speaker embeddings for solving the problem of speaker diarisation. The quality of speaker embeddings is paramount to the performance of speaker diarisation systems. Despite this, prior works in the field…
We explore why deep convolutional neural networks (CNNs) with small two-dimensional kernels, primarily used for modeling spatial relations in images, are also effective in speech recognition. We analyze the representations learned by deep…
In this paper, we tackle the problem of handling narrowband and wideband speech by building a single acoustic model (AM), also called mixed bandwidth AM. In the proposed approach, an auxiliary input feature is used to provide the bandwidth…
Very deep CNNs with small 3x3 kernels have recently been shown to achieve very strong performance as acoustic models in hybrid NN-HMM speech recognition systems. In this paper we investigate how to efficiently scale these models to larger…
In this paper, we propose a novel algorithm for speaker diarization using metric learning for graph based clustering. The graph clustering algorithms use an adjacency matrix consisting of similarity scores. These scores are computed between…
Most existing deep learning based binaural speaker separation systems focus on producing a monaural estimate for each of the target speakers, and thus do not preserve the interaural cues, which are crucial for human listeners to perform…