Related papers: Distortion-controlled Training for End-to-end Reve…

With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the codeswitching phenomenon remains a major obstacle that hinders…

The goal of speech separation is to extract multiple speech sources from a single microphone recording. Recently, with the advancement of deep learning and availability of large datasets, speech separation has been formulated as a…

Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an…

The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent…

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active…

In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from…

The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often extensive data…

We investigate the effectiveness of convolutive prediction, a novel formulation of linear prediction for speech dereverberation, for speaker separation in reverberant conditions. The key idea is to first use a deep neural network (DNN) to…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

This paper aims at eliminating the interfering speakers' speech, additive noise, and reverberation from the noisy multi-talker speech mixture that benefits automatic speech recognition (ASR) backend. While the recently proposed Weighted…

Neural speech separation has made remarkable progress and its integration with automatic speech recognition (ASR) is an important direction towards realizing multi-speaker ASR. This work provides an insightful investigation of speech…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

This report proposes state-of-the-art research in the field of Computer Assisted Language Learning (CALL). Mispronunciation detection is one of the core components of Computer Assisted Pronunciation Training (CAPT) systems which is a subset…

Reverberation results in reduced intelligibility for both normal and hearing-impaired listeners. This paper presents a novel psychoacoustic approach of dereverberation of a single speech source by recycling a pre-trained binaural anechoic…

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…

In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized for such situations. To address this issue, we propose a…

The wav2vec 2.0 and integrated spectro-temporal graph attention network (AASIST) based countermeasure achieves great performance in speech anti-spoofing. However, current spoof speech detection systems have fixed training and evaluation…

Recently, supervised speech separation has made great progress. However, limited by the nature of supervised training, most existing separation methods require ground-truth sources and are trained on synthetic datasets. This ground-truth…