相关论文: A Speech Enhancement Method Using Fast Fourier Tra…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of all algorithms that are based on traditional Auto-Encoders:…

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within…

Dynamic Magnetic Resonance Imaging (MRI) of the vocal tract has become an increasingly adopted imaging modality for speech motor studies. Beyond image signals, systematic data loss, noise pollution, and audio file corruption can occur due…

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

The reconstruction mechanisms built by the human auditory system during sound reconstruction are still a matter of debate. The purpose of this study is to refine the auditory cortex model introduced in [9], and inspired by the geometrical…

Speech compression is commonly used to send voice over radio channels in applications such as mobile telephony and two-way push-to-talk (PTT) radio. In classical systems, the speech codec is combined with forward error correction,…

In this work, we investigate the effectiveness of two techniques for improving variational autoencoder (VAE) based voice conversion (VC). First, we reconsider the relationship between vocoder features extracted using the high quality…

Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved. In this paper we finetune Whisper, a…

B-mode ultrasound tongue imaging is widely used in the speech production field. However, efficient interpretation is in a great need for the tongue image sequences. Inspired by the recent success of unsupervised deep learning approach, we…

Dysarthria speech contains the pathological characteristics of vocal tract and vocal fold, but so far, they have not yet been included in traditional acoustic feature sets. Moreover, the nonlinearity and non-stationarity of speech have been…

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

Two-stage pipeline is popular in speech enhancement tasks due to its superiority over traditional single-stage methods. The current two-stage approaches usually enhance the magnitude spectrum in the first stage, and further modify the…

Source separation and other audio applications have traditionally relied on the use of short-time Fourier transforms as a front-end frequency domain representation step. The unavailability of a neural network equivalent to forward and…

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing…

We propose an end-to-end speech enhancement method with trainable time-frequency~(T-F) transform based on invertible deep neural network~(DNN). The resent development of speech enhancement is brought by using DNN. The ordinary DNN-based…