Related papers: Toward Cross-Domain Speech Recognition with End-to…

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…

Mapping two modalities, speech and text, into a shared representation space, is a research topic of using text-only data to improve end-to-end automatic speech recognition (ASR) performance in new domains. However, the length of speech…

The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios. Differences in speaker accents are a significant source of such mismatch. The traditional approach to deal…

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific,…

We present an end-to-end method for transforming audio from one style to another. For the case of speech, by conditioning on speaker identities, we can train a single model to transform words spoken by multiple people into multiple target…

Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are…

In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss acoustic models that can effectively exploit variable-length…

Training acoustic models with sequentially incoming data -- while both leveraging new data and avoiding the forgetting effect-- is an essential obstacle to achieving human intelligence level in speech recognition. An obvious approach to…

Automatic Speech Recognition(ASR) has been dominated by deep learning-based end-to-end speech recognition models. These approaches require large amounts of labeled data in the form of audio-text pairs. Moreover, these models are more…

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then,…

In this paper, we present an end-to-end training framework for building state-of-the-art end-to-end speech recognition systems. Our training system utilizes a cluster of Central Processing Units(CPUs) and Graphics Processing Units (GPUs).…

Emotion and intent recognition from speech is essential and has been widely investigated in human-computer interaction. The rapid development of social media platforms, chatbots, and other technologies has led to a large volume of speech…

Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data. While recently developed end-to-end methods largely simplify the modeling pipelines, they still suffer from the data…

The deep learning based time-domain models, e.g. Conv-TasNet, have shown great potential in both single-channel and multi-channel speech enhancement. However, many experiments on the time-domain speech enhancement model are done in…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words or document-level features, we focus our study on the…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

As end-to-end automatic speech recognition (ASR) models reach promising performance, various downstream tasks rely on good confidence estimators for these systems. Recent research has shown that model-based confidence estimators have a…