相关论文: Implicit Self-supervised Language Representation f…

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect…

While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the…

In this paper, we propose to employ a dual-mode framework on the x-vector self-attention (XSA-LID) model with knowledge distillation (KD) to enhance its language identification (LID) performance for both long and short utterances. The…

Code-switching deals with alternative languages in communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is especially challenging as code-switching training data are always…

As state-of-the-art Large Language Models (LLMs) have become ubiquitous, ensuring equitable performance across diverse demographics is critical. However, it remains unclear whether these disparities arise from the explicitly stated identity…

Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we…

The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable actions as in traditional systems, which hinders humans from…

Natural language understanding (NLU) is the task of semantic decoding of human languages by machines. NLU models rely heavily on large training data to ensure good performance. However, substantial languages and domains have very few data…

In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-information that is often available for a given speech…

Fast and accurate solution of time-dependent partial differential equations (PDEs) is of key interest in many research fields including physics, engineering, and biology. Generally, implicit schemes are preferred over the explicit ones for…

Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final…

End-to-end (E2E) automatic speech recognition models like Recurrent Neural Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR applications like voice assistants. While E2E models are very effective at learning…

Word vector representations are a crucial part of Natural Language Processing (NLP) and Human Computer Interaction. In this paper, we propose a novel word vector representation, Confusion2Vec, motivated from the human speech production and…

In this paper, we propose to improve end-to-end (E2E) spoken language understand (SLU) in an RNN transducer model (RNN-T) by incorporating a joint self-conditioned CTC automatic speech recognition (ASR) objective. Our proposed model is akin…

ASR systems designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, \textbf{(i)} we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model…

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…

Visual speech recognition (VSR) systems decode spoken words from an input sequence using only the video data. Practical applications of such systems include medical assistance as well as human-machine interactions. A VSR system is typically…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…