Related papers: Mel-FullSubNet: Mel-Spectrogram Enhancement for Im…
Quality and intelligibility of speech signals are degraded under additive background noise which is a critical problem for hearing aid and cochlear implant users. Motivated to address this problem, we propose a novel speech enhancement…
Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time…
Signal reconstruction from its mel-spectrogram is known as mel-spectrogram inversion and has many applications, including speech and foley sound synthesis. In this paper, we propose a mel-spectrogram inversion method based on a rigorous…
This paper describes multichannel speech enhancement for improving automatic speech recognition (ASR) in noisy environments. Recently, the minimum variance distortionless response (MVDR) beamforming has widely been used because it works…
Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation. This created the need for an ASR system that can operate in realistic crowded…
We study speech enhancement using deep learning (DL) for virtual meetings on cellular devices, where transmitted speech has background noise and transmission loss that affects speech quality. Since the Deep Noise Suppression (DNS) Challenge…
We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support…
This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections.…
Recent research has successfully adapted vision-based convolutional neural network (CNN) architectures for audio recognition tasks using Mel-Spectrograms. However, these CNNs have high computational costs and memory requirements, limiting…
Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…
We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…
Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker…
Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical…
This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections.…
Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression. We use a neural network to predict clean…
We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work demonstrates that GANs can effectively…
Decoding speech from brain signals is a challenging research problem. Although existing technologies have made progress in reconstructing the mel spectrograms of auditory stimuli at the word or letter level, there remain core challenges in…
Enhancing noisy speech is an important task to restore its quality and to improve its intelligibility. In traditional non-machine-learning (ML) based approaches the parameters required for noise reduction are estimated blindly from the…
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…
This paper presents a novel neural vocoder named APNet which reconstructs speech waveforms from acoustic features by predicting amplitude and phase spectra directly. The APNet vocoder is composed of an amplitude spectrum predictor (ASP) and…