Related papers: Estimating Phoneme Class Conditional Probabilities…
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…
This article surveys convolution-based models including convolutional neural networks (CNNs), Conformers, ResNets, and CRNNs-as speech signal processing models and provide their statistical backgrounds and speech recognition, speaker…
In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…
Environmental audio tagging is a newly proposed task to predict the presence or absence of a specific audio event in a chunk. Deep neural network (DNN) based methods have been successfully adopted for predicting the audio tags in the…
Phoneme recognition is a very important part of speech recognition that requires the ability to extract phonetic features from multiple frames. In this paper, we compare and analyze CNN, RNN, Transformer, and Conformer models using phoneme…
As for the humanoid robots, the internal noise, which is generated by motors, fans and mechanical components when the robot is moving or shaking its body, severely degrades the performance of the speech recognition accuracy. In this paper,…
In this paper, we propose a method to improve sound classification performance by combining signal features, derived from the time-frequency spectrogram, with human perception. The method presented herein exploits an artificial neural…
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…
Most mainstream Automatic Speech Recognition (ASR) systems consider all feature frames equally important. However, acoustic landmark theory is based on a contradictory idea, that some frames are more important than others. Acoustic landmark…
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…
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…
Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to…
Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…
The Mandarin Chinese language is known to be strongly influenced by a rich set of regional accents, while Mandarin speech with each accent is quite low resource. Hence, an important task in Mandarin speech recognition is to appropriately…
Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to…
In this paper, we propose a privacy-preserving method with a secret key for convolutional neural network (CNN)-based speech classification tasks. Recently, many methods related to privacy preservation have been developed in image…
In this paper, we present an acoustic scene classification framework based on a large-margin factorized convolutional neural network (CNN). We adopt the factorized CNN to learn the patterns in the time-frequency domain by factorizing the 2D…
Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…
In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speech phone classification. We combine modern neural networks…
We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of…