Related papers: Multi-Level Modeling Units for End-to-End Mandarin…

Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages. Some of these models employ language adapters in their formulation, which helps to…

State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown…

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally, neural correction models are composed of encoder-decoder…

Although automatic speech recognition (ASR) systems achieved significantly improvements in recent years, spoken language recognition error occurs which can be easily spotted by human beings. Various language modeling techniques have been…

Previous works on expressive speech synthesis mainly focus on current sentence. The context in adjacent sentences is neglected, resulting in inflexible speaking style for the same text, which lacks speech variations. In this paper, we…

In Chinese Named Entity Recognition, character substitution is a complicated linguistic phenomenon. Some Chinese characters are quite similar as they share the same components or have similar pronunciations. People replace characters in a…

This article describes a system for analyzing acoustic data to assist in the diagnosis and classification of children's speech sound disorders (SSDs) using a computer. The analysis concentrated on identifying and categorizing four distinct…

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or…

With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the codeswitching phenomenon remains a major obstacle that hinders…

Convolutions have become essential in state-of-the-art end-to-end Automatic Speech Recognition~(ASR) systems due to their efficient modelling of local context. Notably, its use in Conformers has led to superior performance compared to…

Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for…

We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…

Conventional Deep Learning frameworks for continuous sign language recognition (CSLR) are comprised of a single or multi-modal feature extractor, a sequence-learning module, and a decoder for outputting the glosses. The sequence learning…

Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision. This could result in recognition errors due to…

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle…

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from…

Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…

Automatic speech recognition (ASR) systems are typically optimized for verbatim transcription, which preserves disfluencies, filler words, and informal spoken structures that are often unsuitable for downstream writing-oriented…