相关论文: Efficient Training of Neural Transducer for Speech…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices. The transducer models provide competitive accuracy within a reasonable memory footprint alleviating…

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection.…

The parallel advances in language modeling and speech representation learning have raised the prospect of learning language directly from speech without textual intermediates. This requires extracting semantic representations directly from…

In traditional conversational intelligence from speech, a cascaded pipeline is used, involving tasks such as voice activity detection, diarization, transcription, and subsequent processing with different NLP models for tasks like semantic…

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare their accuracy and training times: (i) a recurrent model using LSTMs; (ii) a fully…

Neural speech synthesis models have recently demonstrated the ability to synthesize high quality speech for text-to-speech and compression applications. These new models often require powerful GPUs to achieve real-time operation, so being…

Recurrent neural transducer (RNN-T) is a promising end-to-end (E2E) model in automatic speech recognition (ASR). It has shown superior performance compared to traditional hybrid ASR systems. However, training RNN-T from scratch is still…

This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units. Recurrent neural networks (RNN) have become a standard technique to model sequential data…

We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these…

GPUs have been favored for training deep learning models due to their highly parallelized architecture. As a result, most studies on training optimization focus on GPUs. There is often a trade-off, however, between cost and efficiency when…

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech…

Recent work has shown how to train Convolutional Neural Networks (CNNs) rapidly on large image datasets, then transfer the knowledge gained from these models to a variety of tasks. Following [Radford 2017], in this work, we demonstrate…

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…

Large language models have led to state-of-the-art accuracies across a range of tasks. However, training these models efficiently is challenging for two reasons: a) GPU memory capacity is limited, making it impossible to fit large models on…

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,…