Related papers: Spatial Processing Front-End For Distant ASR Explo…

In this paper, we present end-to-end and speech embedding based systems trained in a self-supervised fashion to participate in the ACM Multimedia 2022 ComParE Challenge, specifically the stuttering sub-challenge. In particular, we exploit…

Recently, multi-channel speech enhancement has drawn much interest due to the use of spatial information to distinguish target speech from interfering signal. To make full use of spatial information and neural network based masking…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Amplify-and-forward two-way relay network (AFTWRN) was introduced to realize high-data rate transmission over the wireless frequency-selective channel. However, AFTWRC requires the knowledge of channel state information (CSI) not only for…

Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech…

Personalized speech enhancement has been a field of active research for suppression of speechlike interferers such as competing speakers or TV dialogues. Compared with single channel approaches, multichannel PSE systems can be more…

This paper presents an innovative approach to mitigating the peak-to-average power ratio (PAPR). The proposed method uses a deep learning model called autoencoders (AEs) to simplify the process and avoid the complex calculations of…

Whispering is an important mode of human speech, but no end-to-end recognition results for it were reported yet, probably due to the scarcity of available whispered speech data. In this paper, we present several approaches for end-to-end…

The CHiME-7 and 8 distant speech recognition (DASR) challenges focus on multi-channel, generalizable, joint automatic speech recognition (ASR) and diarization of conversational speech. With participation from 9 teams submitting 32 diverse…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…

In this paper, we present a statistical beamforming algorithm as a pre-processing step for robust automatic speech recognition (ASR). By modeling the target speech as a non-stationary Laplacian distribution, a mask-based statistical…

Recently, streaming end-to-end automatic speech recognition (E2E-ASR) has gained more and more attention. Many efforts have been paid to turn the non-streaming attention-based E2E-ASR system into streaming architecture. In this work, we…

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…

In next-generation wireless communications systems, accurate sparse channel estimation (SCE) is required for coherent detection. This paper studies SCE in terms of adaptive filtering theory, which is often termed as adaptive channel…

End-to-end speech recognition has become popular in recent years, since it can integrate the acoustic, pronunciation and language models into a single neural network. Among end-to-end approaches, attention-based methods have emerged as…

This paper presents the Speech Technology Center (STC) speaker recognition (SR) systems submitted to the VOiCES From a Distance challenge 2019. The challenge's SR task is focused on the problem of speaker recognition in single channel…

DeepFake Audio, unlike DeepFake images and videos, has been relatively less explored from detection perspective, and the solutions which exist for the synthetic speech classification either use complex networks or dont generalize to…

Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…