相关论文: AMRConvNet: AMR-Coded Speech Enhancement Using Con…

We explore the possibility of leveraging accelerometer data to perform speech enhancement in very noisy conditions. Although it is possible to only partially reconstruct user's speech from the accelerometer, the latter provides a strong…

Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion…

Deep complex U-Net structure and convolutional recurrent network (CRN) structure achieve state-of-the-art performance for monaural speech enhancement. Both deep complex U-Net and CRN are encoder and decoder structures with skip connections,…

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network.…

In this paper, we tackle the problem of handling narrowband and wideband speech by building a single acoustic model (AM), also called mixed bandwidth AM. In the proposed approach, an auxiliary input feature is used to provide the bandwidth…

Convolutions have become essential in state-of-the-art end-to-end Automatic Speech Recognition~(ASR) systems due to their efficient modelling of local context. Notably, its use in Conformers has led to superior performance compared to…

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…

Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech…

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…

Speech coding facilitates the transmission of speech over low-bandwidth networks with minimal distortion. Neural-network based speech codecs have recently demonstrated significant improvements in quality over traditional approaches. While…

In order to efficiently transmit and store speech signals, speech codecs create a minimally redundant representation of the input signal which is then decoded at the receiver with the best possible perceptual quality. In this work we…

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

Recent research advances in deep neural network (DNN)-based beamformers have shown great promise for speech enhancement under adverse acoustic conditions. Different network architectures and input features have been explored in estimating…

Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…

This work performs a preliminary, comparative analysis of the end-to-end quality guaranteed by Voice over LTE (VoLTE), examining several millions of VoLTE calls that employ two popular speech audio codecs, namely, Adaptive Multi-Rate (AMR)…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy…

To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. The AFE output, however, could be unreliable, as the…

Due to the simple design pipeline, end-to-end (E2E) neural models for speech enhancement (SE) have attracted great interest. In order to improve the performance of the E2E model, the locality and temporal sequential properties of speech…

From hearing aids to augmented and virtual reality devices, binaural speech enhancement algorithms have been established as state-of-the-art techniques to improve speech intelligibility and listening comfort. In this paper, we present an…

Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to mitigate this is to train or fine-tune models with more…