Related papers: Non-autoregressive Transformer with Unified Bidire…

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…

The network architecture of end-to-end (E2E) automatic speech recognition (ASR) can be classified into several models, including connectionist temporal classification (CTC), recurrent neural network transducer (RNN-T), attention mechanism,…

In recent years BERT shows apparent advantages and great potential in natural language processing tasks. However, both training and applying BERT requires intensive time and resources for computing contextual language representations, which…

RNN-T-based keyword spotting (KWS) with autoregressive decoding~(AR) has gained attention due to its streaming architecture and superior performance. However, the simplicity of the prediction network in RNN-T poses an overfitting issue,…

With the rapid advancement of Neural Machine Translation (NMT), enhancing translation efficiency and quality has become a focal point of research. Despite the commendable performance of general models such as the Transformer in various…

Semantic parsing (SP) is a core component of modern virtual assistants like Google Assistant and Amazon Alexa. While sequence-to-sequence-based auto-regressive (AR) approaches are common for conversational semantic parsing, recent studies…

Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem. Therefore, extensive efforts have been continued on exploring different RNN-based encoder-decoder…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with…

Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with…

Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens. However,…

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in…

Recently very deep transformers have outperformed conventional bi-directional long short-term memory networks by a large margin in speech recognition. However, to put it into production usage, inference computation cost is still a serious…

Recently, continuous diffusion models (CDM) have been introduced into non-autoregressive (NAR) text-to-text generation. However, the discrete nature of text increases the difficulty of CDM to generate coherent and fluent texts, and also…

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

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…

In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target decoding position,…

Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis…

Fast Automatic Speech Recognition (ASR) is critical for latency-sensitive applications such as real-time captioning and meeting transcription. However, truly parallel ASR decoding remains challenging due to the sequential nature of…

The Directed Acyclic Transformer is a fast non-autoregressive (NAR) model that performs well in Neural Machine Translation. Two issues prevent its application to general Natural Language Generation (NLG) tasks: frequent Out-Of-Vocabulary…