Related papers: Multi-Convformer: Extending Conformer with Multipl…

This paper presents a simple but effective method that uses multi-resolution feature maps with convolutional neural networks (CNNs) for anti-spoofing in automatic speaker verification (ASV). The central idea is to alleviate the problem that…

Large language models have demonstrated remarkable performance across various tasks, yet they face challenges such as low computational efficiency, gradient vanishing, and difficulties in capturing complex feature interactions. To address…

We present a decoder-only Conformer for automatic speech recognition (ASR) that processes speech and text in a single stack without external speech encoders or pretrained large language models (LLM). The model uses a modality-aware sparse…

The spatial covariance matrix has been considered to be significant for beamformers. Standing upon the intersection of traditional beamformers and deep neural networks, we propose a causal neural beamformer paradigm called Embedding and…

General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to directly separate speech from multiple microphone recordings,…

Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech…

We propose an adapter based multi-domain Transformer based language model (LM) for Transformer ASR. The model consists of a big size common LM and small size adapters. The model can perform multi-domain adaptation with only the small size…

Transformers for language modeling usually rely on deterministic internal computation, with uncertainty expressed mainly at the output layer. We introduce variational neurons into Transformer feed-forward computation so that uncertainty…

Region proposal based methods like R-CNN and Faster R-CNN models have proven to be extremely successful in object detection and segmentation tasks. Recently, Transformers have also gained popularity in the domain of Computer Vision, and are…

Speech separation remains an important topic for multi-speaker technology researchers. Convolution augmented transformers (conformers) have performed well for many speech processing tasks but have been under-researched for speech…

Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are…

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational…

Integrating audio encoders with LLMs through connectors has enabled these models to process and comprehend audio modalities, significantly enhancing speech-to-text tasks, including automatic speech recognition (ASR) and automatic speech…

Attempts to develop speech enhancement algorithms with improved speech intelligibility for cochlear implant (CI) users have met with limited success. To improve speech enhancement methods for CI users, we propose to perform speech…

With the development of teleconferencing and in-vehicle voice assistants, far-field multi-speaker speech recognition has become a hot research topic. Recently, a multi-channel transformer (MCT) has been proposed, which demonstrates the…

Automatic Cued Speech Recognition (ACSR) provides an intelligent human-machine interface for visual communications, where the Cued Speech (CS) system utilizes lip movements and hand gestures to code spoken language for hearing-impaired…