Related papers: Reinforcement Learning Based Speech Enhancement fo…
Automatic speech recognition systems based on deep learning are mainly trained under empirical risk minimization (ERM). Since ERM utilizes the averaged performance on the data samples regardless of a group such as healthy or dysarthric…
Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress…
Previous studies have confirmed that by augmenting acoustic features with the place/manner of articulatory features, the speech enhancement (SE) process can be guided to consider the broad phonetic properties of the input speech when…
Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…
In recent years, the joint training of speech enhancement front-end and automatic speech recognition (ASR) back-end has been widely used to improve the robustness of ASR systems. Traditional joint training methods only use enhanced speech…
We propose ARiSE, an auto-regressive algorithm for multi-channel speech enhancement. ARiSE improves existing deep neural network (DNN) based frame-online multi-channel speech enhancement models by introducing auto-regressive connections,…
We propose a multi-objective framework to learn both secondary targets not directly related to the intended task of speech enhancement (SE) and the primary target of the clean log-power spectra (LPS) features to be used directly for…
Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch between the training and inference conditions. In the…
Automatic speech recognition (ASR) systems play a key role in many commercial products including voice assistants. Typically, they require large amounts of clean speech data for training which gives an undue advantage to large organizations…
The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's…
We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…
Integrating front-end speech enhancement (SE) models with self-supervised learning (SSL)-based speech models is effective for downstream tasks in noisy conditions. SE models are commonly fine-tuned using SSL representations with mean…
End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…
The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…
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.…
Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial…
In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…
Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a…
Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example pruning words due to acoustics using short-term context, prior to rescoring with…
Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…