Related papers: Deformable TDNN with adaptive receptive fields for…
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…
Time series data, characterized by its intrinsic long and short-range dependencies, poses a unique challenge across analytical applications. While Transformer-based models excel at capturing long-range dependencies, they face limitations in…
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…
Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional…
Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…
Deep neural network (DNN)-based models for environmental sound classification are not robust against a domain to which training data do not belong, that is, out-of-distribution or unseen data. To utilize pretrained models for the unseen…
State of the art time automatic speech recognition (ASR) systems are becoming increasingly complex and expensive for practical applications. This paper presents the development of a high performance and low-footprint 4-bit quantized LF-MMI…
Deep neural network (DNN)-based speech enhancement algorithms in microphone arrays have now proven to be efficient solutions to speech understanding and speech recognition in noisy environments. However, in the context of ad-hoc microphone…
Formant tracking is one of the most fundamental problems in speech processing. Traditionally, formants are estimated using signal processing methods. Recent studies showed that generic convolutional architectures can outperform recurrent…
In this paper we present a domain adaptation technique for formant estimation using a deep network. We first train a deep learning network on a small read speech dataset. We then freeze the parameters of the trained network and use several…
Spiking neural networks (SNNs) are rapidly gaining momentum as an alternative to conventional artificial neural networks in resource constrained edge systems. In this work, we continue a recent research line on recurrent SNNs where axonal…
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…
In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the…
This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units. Recurrent neural networks (RNN) have become a standard technique to model sequential data…
This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these…
Recent advances in neural network based acoustic modelling have shown significant improvements in automatic speech recognition (ASR) performance. In order for acoustic models to be able to handle large acoustic variability, large amounts of…
Discrete-Time Dynamic Graphs (DTDGs), which are prevalent in real-world implementations and notable for their ease of data acquisition, have garnered considerable attention from both academic researchers and industry practitioners. The…
Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with…
This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the…
Enabled by multi-head self-attention, Transformer has exhibited remarkable results in speech emotion recognition (SER). Compared to the original full attention mechanism, window-based attention is more effective in learning fine-grained…