Related papers: Synchronous Transformers for End-to-End Speech Rec…

Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigned Conformer with a…

Despite the great success of Transformer networks in various applications such as natural language processing and computer vision, their theoretical aspects are not well understood. In this paper, we study the approximation and estimation…

State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. The sequential nature of this generation process causes fundamental latency in…

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

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,…

Sequence-to-sequence models have achieved impressive results on various tasks. However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output…

Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial. Previous works utilize linear interpolation or a fusion network to integrate external language models. However, these approaches…

In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we propose a new type of decoder for NMT, which splits the decode…

Speaker change detection is an important task in multi-party interactions such as meetings and conversations. In this paper, we address the speaker change detection task from the perspective of sequence transduction. Specifically, we…

We discuss the problem of echographic transcription in autoregressive sequence-to-sequence attentional architectures for automatic speech recognition, where a model produces very long sequences of repetitive outputs when presented with…

Recent advancements in transformer-based models have greatly improved time series analysis, providing robust solutions for tasks such as forecasting, anomaly detection, and classification. A crucial element of these models is positional…

The attention-based encoder-decoder modeling paradigm has achieved promising results on a variety of speech processing tasks like automatic speech recognition (ASR), text-to-speech (TTS) and among others. This paradigm takes advantage of…

Encoder-decoder models have been widely used to solve sequence to sequence prediction tasks. However current approaches suffer from two shortcomings. First, the encoders compute a representation of each word taking into account only the…

Most existing Neural Machine Translation models use groups of characters or whole words as their unit of input and output. We propose a model with a hierarchical char2word encoder, that takes individual characters both as input and output.…

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers,…

Recently Convolution-augmented Transformer (Conformer) has shown promising results in Automatic Speech Recognition (ASR), outperforming the previous best published Transformer Transducer. In this work, we believe that the output information…

Conventional automatic speech recognition systems do not produce punctuation marks which are important for the readability of the speech recognition results. They are also needed for subsequent natural language processing tasks such as…

We demonstrate that an attention-based encoder-decoder model can be used for sentence-level grammatical error identification for the Automated Evaluation of Scientific Writing (AESW) Shared Task 2016. The attention-based encoder-decoder…

We consider the problem of slotted asynchronous coded communication, where in each time frame (slot), the transmitter is either silent or transmits a codeword from a given (randomly selected) codebook. The task of the decoder is to decide…

Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model…