Related papers: U2++: Unified Two-pass Bidirectional End-to-end Mo…

We introduce a technique for augmenting neural text-to-speech (TTS) with lowdimensional trainable speaker embeddings to generate different voices from a single model. As a starting point, we show improvements over the two state-ofthe-art…

Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing a unified tokenizer. However, existing tokenizers face a…

Conventional automatic speaker verification systems can usually be decomposed into a front-end model such as time delay neural network (TDNN) for extracting speaker embeddings and a back-end model such as statistics-based probabilistic…

The increasing reliability of automatic speech recognition has proliferated its everyday use. However, for research purposes, it is often unclear which model one should choose for a task, particularly if there is a requirement for speed as…

U-Net is a widely adopted neural network in the domain of medical image segmentation. Despite its quick embracement by the medical imaging community, its performance suffers on complicated datasets. The problem can be ascribed to its simple…

The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits…

End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space through data augmentation. Meanwhile, human auditory inspired…

Scene text spotting is of great importance to the computer vision community due to its wide variety of applications. Recent methods attempt to introduce linguistic knowledge for challenging recognition rather than pure visual…

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are…

The lack of speech data annotated with labels required for spoken language understanding (SLU) is often a major hurdle in building end-to-end (E2E) systems that can directly process speech inputs. In contrast, large amounts of text data…

Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of…

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

In this paper, we propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition (ASR). For acoustic modeling, the wav2vec 2.0 pre-trained model is fine-tuned by…

End-to-end (E2E) systems have played a more and more important role in automatic speech recognition (ASR) and achieved great performance. However, E2E systems recognize output word sequences directly with the input acoustic feature, which…

Continual Learning entails progressively acquiring knowledge from new data while retaining previously acquired knowledge, thereby mitigating ``Catastrophic Forgetting'' in neural networks. Our work presents a novel uncertainty-driven…

Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have…

Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR). AED models, however, still have drawbacks when deploying in commercial…

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

Conventional automatic speech recognition systems do not produce punctuation marks which are important for the readability of the speech recognition results. They are also needed for subsequent natural language processing tasks such as…

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas…