Related papers: Contextual-Utterance Training for Automatic Speech…

End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to…

The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM layers, the Conformer…

Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-talker speech in which many voices overlap. One conventional…

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…

Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and…

Automatic speech recognition (ASR) models are normally trained to operate over single utterances, with a short duration of less than 30 seconds. This choice has been made in part due to computational constraints, but also reflects a common,…

Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off…

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting…

Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural…

In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the…

Automatic Speech Recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community. We investigate data selection and preparation choices aiming for improved robustness of RNN-T ASR to…

Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usability. Despite its importance, the integration of streaming…

Compared to hybrid automatic speech recognition (ASR) systems that use a modular architecture in which each component can be independently adapted to a new domain, recent end-to-end (E2E) ASR system are harder to customize due to their…

It's challenging to customize transducer-based automatic speech recognition (ASR) system with context information which is dynamic and unavailable during model training. In this work, we introduce a light-weight contextual spelling…

Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified…