Related papers: Improved training for online end-to-end speech rec…

Temporal expression (TE) normalization is a well-studied problem. However, the predominately used rule-based systems are highly restricted to specific settings, and upcoming machine learning approaches suffer from a lack of labeled data. In…

The idea of end-to-end learning of communication systems through neural network-based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning algorithm which alleviates…

This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR…

Sequence-to-sequence models with an implicit alignment mechanism (e.g. attention) are closing the performance gap towards traditional hybrid hidden Markov models (HMM) for the task of automatic speech recognition. One important factor to…

Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity. However, prior works have shown that modelling A2W…

When building state-of-the-art speech translation models, the need for large computational resources is a significant obstacle due to the large training data size and complex models. The availability of pre-trained models is a promising…

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

In end-to-end automatic speech recognition system, one of the difficulties for language expansion is the limited paired speech and text training data. In this paper, we propose a novel method to generate augmented samples with unpaired…

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as…

In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks. We start with a pre-trained English ASR model and show that transfer learning can be effectively…

Large pretrained language models (LMs) have become the central building block of many NLP applications. Training these models requires ever more computational resources and most of the existing models are trained on English text only. It is…

Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition…

Language-agnostic many-to-one end-to-end speech translation models can convert audio signals from different source languages into text in a target language. These models do not need source language identification, which improves user…

End-to-end approaches have recently become popular as a means of simplifying the training and deployment of speech recognition systems. However, they often require large amounts of data to perform well on large vocabulary tasks. With the…

Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit…

Data-driven models achieve successful results in Speech Emotion Recognition (SER). However, these models, which are often based on general acoustic features or end-to-end approaches, show poor performance when the testing set has a…