Related papers: SALADnet: Self-Attentive multisource Localization …

Decoding human activity accurately from wearable sensors can aid in applications related to healthcare and context awareness. The present approaches in this domain use recurrent and/or convolutional models to capture the spatio-temporal…

Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization. Different from neural machine translation, in the task of…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

State-of-the-art deep reading comprehension models are dominated by recurrent neural nets. Their sequential nature is a natural fit for language, but it also precludes parallelization within an instances and often becomes the bottleneck for…

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Speech activity detection (SAD) plays an important role in current speech processing systems, including automatic speech recognition (ASR). SAD is particularly difficult in environments with acoustic noise. A practical solution is to…

Generative adversarial networks (GANs) have been indicated their superiority in usage of the real-time speech synthesis. Nevertheless, most of them make use of deep convolutional layers as their backbone, which may cause the absence of…

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

Recurrent neural network transducer (RNN-T) is an end-to-end speech recognition framework converting input acoustic frames into a character sequence. The state-of-the-art encoder network for RNN-T is the Conformer, which can effectively…

This paper explores the task of language-agnostic speaker replication, a novel endeavor that seeks to replicate a speaker's voice irrespective of the language they are speaking. Towards this end, we introduce a multi-level attention…

Time series forecasting is a key component in many industrial and business decision processes and recurrent neural network (RNN) based models have achieved impressive progress on various time series forecasting tasks. However, most of the…

We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing. Autofocus layers adaptively change the size of the effective receptive…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

This paper proposes a deep neural network for estimating the directions of arrival (DOA) of multiple sound sources. The proposed stacked convolutional and recurrent neural network (DOAnet) generates a spatial pseudo-spectrum (SPS) along…

As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper, a new deep learning structure for speech enhancement is…

While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer…

Speaker change detection (SCD) is an important task in dialog modeling. Our paper addresses the problem of text-based SCD, which differs from existing audio-based studies and is useful in various scenarios, for example, processing dialog…

Recently, multi-channel speech enhancement has drawn much interest due to the use of spatial information to distinguish target speech from interfering signal. To make full use of spatial information and neural network based masking…