相关论文: Towards Online End-to-end Transformer Automatic Sp…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can…

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from…

The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text…

We live in a world where 60% of the population can speak two or more languages fluently. Members of these communities constantly switch between languages when having a conversation. As automatic speech recognition (ASR) systems are being…

Transformer models have been introduced into end-to-end speech recognition with state-of-the-art performance on various tasks owing to their superiority in modeling long-term dependencies. However, such improvements are usually obtained…

Currently, the chunk-wise schemes are often used to make Automatic Speech Recognition (ASR) models to support streaming deployment. However, existing approaches are unable to capture the global context, lack support for parallel training,…

Automatic transcription of stuttered speech remains a challenge, even for modern end-to-end (E2E) automatic speech recognition (ASR) frameworks. Dysfluencies and fluency-shaping artifacts are often overlooked, resulting in non-verbatim…

Automatic speech recognition (ASR) with an encoder equipped with self-attention, whether streaming or non-streaming, takes quadratic time in the length of the speech utterance. This slows down training and decoding, increase their cost, and…

In order to learn universal sentence representations, previous methods focus on complex recurrent neural networks or supervised learning. In this paper, we propose a mean-max attention autoencoder (mean-max AAE) within the encoder-decoder…

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et…

Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for…

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks. A special end-of-chunk (EOC) symbol advances from one chunk…

Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and…

Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional…

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more…

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…

Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experiences of audio AI modules deployed in the wild. To support a…

Transformer with self-attention has achieved great success in the area of nature language processing. Recently, there have been a few studies on transformer for end-to-end speech recognition, while its application for hybrid acoustic model…