Related papers: Personalization for BERT-based Discriminative Spee…

We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token…

Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These…

While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subjective judgments due to their cost efficiency. This paper…

Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the…

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on…

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,…

Stuttering -- characterized by involuntary disfluencies such as blocks, prolongations, and repetitions -- is often misinterpreted by automatic speech recognition (ASR) systems, resulting in elevated word error rates and making voice-driven…

Automatic reading aloud evaluation can provide valuable support to teachers by enabling more efficient scoring of reading exercises. However, research on reading evaluation systems and applications remains limited. We present a novel…

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…

Named entity recognition (NER) is frequently addressed as a sequence classification task where each input consists of one sentence of text. It is nevertheless clear that useful information for the task can often be found outside of the…

Varying data augmentation policies and regularization over the course of optimization has led to performance improvements over using fixed values. We show that population based training is a useful tool to continuously search those…

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Dysfluencies and variations in speech pronunciation can severely degrade speech recognition performance, and for many individuals with moderate-to-severe speech disorders, voice operated systems do not work. Current speech recognition…

Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements. At the…

This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to…

We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs.…

Language identification from speech is a common preprocessing step in many spoken language processing systems. In recent years, this field has seen fast progress, mostly due to the use of self-supervised models pretrained on multilingual…

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

Automatic speech recognition (ASR) systems often encounter difficulties in accurately recognizing rare words, leading to errors that can have a negative impact on downstream tasks such as keyword spotting, intent detection, and text…