Related papers: Decomposed Temporal Dynamic CNN: Efficient Time-Ad…

Time-variant factors often occur in real-world full-duplex communication applications. Some of them are caused by the complex environment such as non-stationary environmental noises and varying acoustic path while some are caused by the…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

Speech Emotion Recognition (SER) is crucial in human-machine interactions. Mainstream approaches utilize Convolutional Neural Networks or Recurrent Neural Networks to learn local energy feature representations of speech segments from speech…

Due to the unprecedented breakthroughs brought about by deep learning, speech enhancement (SE) techniques have been developed rapidly and play an important role prior to acoustic modeling to mitigate noise effects on speech. To increase the…

Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Neural Networks (DNN), as they are able to better reduce spectral variation in the input signal. This has also been confirmed experimentally, with CNNs showing…

We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features…

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains…

The attenuation of acoustic loudspeaker echoes remains to be one of the open challenges to achieve pleasant full-duplex hands free speech communication. In many modern signal enhancement interfaces, this problem is addressed by a linear…

This paper presents a transfer learning method in speech emotion recognition based on a Time-Delay Neural Network (TDNN) architecture. A major challenge in the current speech-based emotion detection research is data scarcity. The proposed…

Speaker extraction is to extract a target speaker's voice from multi-talker speech. It simulates humans' cocktail party effect or the selective listening ability. The prior work mostly performs speaker extraction in frequency domain, then…

This paper proposes multistream CNN, a novel neural network architecture for robust acoustic modeling in speech recognition tasks. The proposed architecture processes input speech with diverse temporal resolutions by applying different…

We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic…

This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studies of deep neural…

Powerful deep learning tools, such as convolutional neural networks (CNN), are able to learn the input-output relationships of large complicated systems directly from data. Encoder-decoder deep CNNs are able to extract features directly…

The Dynamic Communication Network (DCN) describes the interactions over time among various communication nodes, and it is widely used in Big-data applications as a data source. As the number of communication nodes increases and temporal…

We propose an end-to-end speech enhancement method with trainable time-frequency~(T-F) transform based on invertible deep neural network~(DNN). The resent development of speech enhancement is brought by using DNN. The ordinary DNN-based…

In this work, we propose Tiny-CRNN (Tiny Convolutional Recurrent Neural Network) models applied to the problem of wakeword detection, and augment them with scaled dot product attention. We find that, compared to Convolutional Neural Network…

Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states - i.e.…

In addition to being extremely non-linear, modern problems require millions if not billions of parameters to solve or at least to get a good approximation of the solution, and neural networks are known to assimilate that complexity by…

Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, prosody and long-term…