Related papers: Personalization Strategies for End-to-End Speech R…
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…
Whispering is an important mode of human speech, but no end-to-end recognition results for it were reported yet, probably due to the scarcity of available whispered speech data. In this paper, we present several approaches for end-to-end…
Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears…
End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore,…
Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words.…
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).…
End-to-end automatic speech recognition suffers from adaptation to unknown target domain speech despite being trained with a large amount of paired audio--text data. Recent studies estimate a linguistic bias of the model as the internal…
End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and…
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…
Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E) models on words rarely seen during training, when used in either the shallow fusion or the rescoring setups. In this work, we introduce LMs in the…
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-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers. However, these systems do not always generalize well for…
Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…
End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed…
End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…
Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…
Multilingual end-to-end automatic speech recognition models are attractive due to its simplicity in training and deployment. Recent work on large-scale training of such models has shown promising results compared to monolingual models.…
Recently, the end-to-end training approach for neural beamformer-supported multi-channel ASR has shown its effectiveness in multi-channel speech recognition. However, the integration of multiple modules makes it more difficult to perform…
Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…
Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…