相关论文: Speech enhancement aided end-to-end multi-task lea…

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

In self-supervised learning, it is challenging to reduce the gap between the enhancement performance on the estimated and target speech signals with existed pre-tasks. In this paper, we propose a multi-task pre-training method to improve…

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…

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…

Recent studies in neural network-based monaural speech separation (SS) have achieved a remarkable success thanks to increasing ability of long sequence modeling. However, they would degrade significantly when put under realistic noisy…

Background noise reduces speech intelligibility and quality, making speaker verification (SV) in noisy environments a challenging task. To improve the noise robustness of SV systems, additive noise data augmentation method has been commonly…

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

In this work we present a novel single-channel Voice Activity Detector (VAD) approach. We utilize a Convolutional Neural Network (CNN) which exploits the spatial information of the noisy input spectrum to extract frame-wise embedding…

Traditional supervised voice activity detection (VAD) methods work well in clean and controlled scenarios, with performance severely degrading in real-world applications. One possible bottleneck is that speech in the wild contains…

The common target speech separation directly estimate the target source, ignoring the interrelationship between different speakers at each frame. We propose a multiple-target speech separation model (MTSS) to simultaneously extract each…

Recently, the end-to-end approach has proven its efficacy in monaural multi-speaker speech recognition. However, high word error rates (WERs) still prevent these systems from being used in practical applications. On the other hand, the…

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to…

Self-supervised learning approaches have lately achieved great success on a broad spectrum of machine learning problems. In the field of speech processing, one of the most successful recent self-supervised models is wav2vec 2.0. In this…

Blind speech separation (BSS) aims to recover multiple speech sources from multi-channel, multi-speaker mixtures under unknown array geometry and room impulse responses. In unsupervised setup where clean target speech is not available for…

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…

Recent studies demonstrate the effectiveness of Self Supervised Learning (SSL) speech representations for Speech Inversion (SI). However, applying SI in real-world scenarios remains challenging due to the pervasive presence of background…

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of…

Recently, deep neural network (DNN) based time-frequency (T-F) mask estimation has shown remarkable effectiveness for speech enhancement. Typically, a single T-F mask is first estimated based on DNN and then used to mask the spectrogram of…

Automatic speech recognition (ASR) has shown rapid advances in recent years but still degrades significantly in far-field and noisy environments. The recent development of self-supervised learning (SSL) technology can improve the ASR…