Related papers: Multi-Span Acoustic Modelling using Raw Waveform S…

The effective exploitation of richer contextual information in language models (LMs) is a long-standing research problem for automatic speech recognition (ASR). A cross-utterance LM (CULM) is proposed in this paper, which augments the input…

Modeling long-term dependencies for audio signals is a particularly challenging problem, as even small-time scales yield on the order of a hundred thousand samples. With the recent advent of Transformers, neural architectures became good at…

Inspired by the progress of the End-to-End approach [1], this paper systematically studies the effects of Number of Filters of convolutional layers on the model prediction accuracy of CNN+RNN (Convolutional Neural Networks adding to…

The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…

In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values…

This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin…

This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in…

Convolutional neural networks (CNNs) are widely used in computer vision. They can be used not only for conventional digital image material to recognize patterns, but also for feature extraction from digital imagery representing spectral and…

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending…

Recent literature has shown that a learned front end with multi-channel audio input can outperform traditional beam-forming algorithms for automatic speech recognition (ASR). In this paper, we present our study on multi-channel acoustic…

Traditional Active Noise Control (ANC) systems are mostly based on FxLMS algorithms, but such algorithms rely on linear assumptions and are often limited in handling broadband non-stationary noise or nonlinear acoustic paths. Not only that,…

In this work, we propose Mel-FullSubNet, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance. Mel-FullSubNet takes as input the noisy…

High-accuracy speech recognition is especially challenging when large datasets are not available. It is possible to bridge this gap with careful and knowledge-driven parsing combined with the biologically inspired CNN and the learning…

Respiratory sound analysis is a crucial tool for screening asthma and other pulmonary pathologies, yet traditional auscultation remains subjective and experience-dependent. Our prior research established a CNN baseline using DenseNet201,…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in most speech and speaker recognition applications. In this work, we propose a modified Mel filter bank to extract MFCCs from subsampled speech. We…

Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper…

Despite significant efforts over the last few years to build a robust automatic speech recognition (ASR) system for different acoustic settings, the performance of the current state-of-the-art technologies significantly degrades in noisy…