Related papers: Separate and Reconstruct: Asymmetric Encoder-Decod…

The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an…

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…

Self-supervised speech representations are known to encode both speaker and phonetic information, but how they are distributed in the high-dimensional space remains largely unexplored. We hypothesize that they are encoded in orthogonal…

In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's…

For the task of speech separation, previous study usually treats multi-channel and single-channel scenarios as two research tracks with specialized solutions developed respectively. Instead, we propose a simple and unified architecture -…

Speech separation always faces the challenge of handling prolonged time sequences. Past methods try to reduce sequence lengths and use the Transformer to capture global information. However, due to the quadratic time complexity of the…

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis…

We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our…

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA) results on a number of speech separation benchmarks. One…

Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired…

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger…

When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance ASR performance in conversational or meeting environments,…

Recent advances in self-supervised learning (SSL) on Transformers have significantly improved speaker verification (SV) by providing domain-general speech representations. However, existing approaches have underutilized the multi-layered…

Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token. In contrast, we develop a discourse segmenter utilizing a set of pairing…

Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…

The performance of speech enhancement and separation systems in anechoic environments has been significantly advanced with the recent progress in end-to-end neural network architectures. However, the performance of such systems in…

This paper proposes a novel framework for unsupervised audio source separation using a deep autoencoder. The characteristics of unknown source signals mixed in the mixed input is automatically by properly configured autoencoders implemented…