Related papers: Conv-Transformer Transducer: Low Latency, Low Fram…

The tradeoff between reconstruction quality and compute required for video super-resolution (VSR) remains a formidable challenge in its adoption for deployment on resource-constrained edge devices. While transformer-based VSR models have…

Achieving high accuracy with low latency has always been a challenge in streaming end-to-end automatic speech recognition (ASR) systems. By attending to more future contexts, a streaming ASR model achieves higher accuracy but results in…

Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-talker speech in which many voices overlap. One conventional…

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming…

Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…

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…

Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer…

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…

Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT to speech translation (ST) remains challenging, as existing…

Audio-visual automatic speech recognition (AV-ASR) extends speech recognition by introducing the video modality as an additional source of information. In this work, the information contained in the motion of the speaker's mouth is used to…

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…

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding and require a lot of learnable parameters. This paper explores Transformer-based speech separation…

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory,…

Attention-based encoder-decoder, e.g. transformer and its variants, generates the output sequence in an autoregressive (AR) manner. Despite its superior performance, AR model is computationally inefficient as its generation requires as many…

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier…

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to…

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications.…