Related papers: SCA: Streaming Cross-attention Alignment for Echo …
The opaque nature of deep learning models presents significant challenges for the ethical deployment of hate speech detection systems. To address this limitation, we introduce Supervised Rational Attention (SRA), a framework that explicitly…
Recent advances in deep learning show that end-to-end speech to text translation model is a promising approach to direct the speech translation field. In this work, we provide an overview of different end-to-end architectures, as well as…
A generalized downlink multi-antenna non-orthogonal multiple access (NOMA) transmission framework is proposed with the novel concept of cluster-free successive interference cancellation (SIC). In contrast to conventional NOMA approaches,…
This study addresses the task of performing robust and reliable time-delay estimation in signals in noisy and reverberating environments. In contrast to the popular signal processing based methods, this paper proposes to transform the input…
Streaming end-to-end multi-talker speech recognition aims at transcribing the overlapped speech from conversations or meetings with an all-neural model in a streaming fashion, which is fundamentally different from a modular-based approach…
Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelization . In this paper, we propose a self-attention transducer…
We present an end-to-end multichannel speaker-attributed automatic speech recognition (MC-SA-ASR) system that combines a Conformer-based encoder with multi-frame crosschannel attention and a speaker-attributed Transformer-based decoder. To…
This article describes an efficient training method for online streaming attention-based encoder-decoder (AED) automatic speech recognition (ASR) systems. AED models have achieved competitive performance in offline scenarios by jointly…
In most control applications, theoretical analysis of the systems is crucial in ensuring stability or convergence, so as to ensure safe and reliable operations and also to gain a better understanding of the systems for further developments.…
Concurrent Speaker Detection (CSD), the task of identifying active speakers and their overlaps in an audio signal, is essential for various audio applications, including meeting transcription, speaker diarization, and speech separation.…
Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade…
End-to-end spoken language understanding (SLU) has recently attracted increasing interest. Compared to the conventional tandem-based approach that combines speech recognition and language understanding as separate modules, the new approach…
In recent years, convolutional neural networks (CNNs) with channel-wise feature refining mechanisms have brought noticeable benefits to modelling channel dependencies. However, current attention paradigms fail to infer an optimal channel…
Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…
In this paper a generalized postfilter algorithm design issues are presented. This postfilter is used to jointly suppress late reverberation, residual echo, and background noise. When residual echo and noise are suppressed, the best result…
End-to-end speech translation, a hot topic in recent years, aims to translate a segment of audio into a specific language with an end-to-end model. Conventional approaches employ multi-task learning and pre-training methods for this task,…
Continuous sign language recognition (CSLR) aims to recognize signs in untrimmed sign language videos to textual glosses. A key challenge of CSLR is achieving effective cross-modality alignment between video and gloss sequences to enhance…
The most common approach to speaker diarization is clustering of speaker embeddings. However, the clustering-based approach has a number of problems; i.e., (i) it is not optimized to minimize diarization errors directly, (ii) it cannot…
This paper introduces the NWPU Team's entry to the ICASSP 2022 AEC Challenge. We take a hybrid approach that cascades a linear AEC with a neural post-filter. The former is used to deal with the linear echo components while the latter…
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…