Related papers: Differentiable K-means for Fully-optimized Discret…

State-of-the-art Automatic Speech Recognition (ASR) systems are known to exhibit disparate performance on varying speech accents. To improve performance on a specific target accent, a commonly adopted solution is to finetune the ASR model…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Automatic Speech Recognition (ASR) models have achieved remarkable accuracy in general settings, yet their performance often degrades in domain-specific applications due to data mismatch and linguistic variability. This challenge is…

Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to…

Self-supervised learning (SSL) has recently shown notable success in various visual tasks. However, in terms of discriminability, SSL is still not on par with supervised learning (SL). This paper identifies a key issue, the ``crowding…

Large self-supervised speech (SSL) models achieve strong downstream performance, but their size limits deployment in resource-constrained settings. We present HArnESS, an Arabic-centric self-supervised speech model family trained from…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in…

Discrete tokens extracted provide efficient and domain adaptable speech features. Their application to disordered speech that exhibits articulation imprecision and large mismatch against normal voice remains unexplored. To improve their…

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

We examine the text-free speech representations of raw audio obtained from a self-supervised learning (SSL) model by analyzing the synthesized speech using the SSL representations instead of conventional text representations. Since raw…

Semi-Supervised Learning (SSL) has become a preferred paradigm in many deep learning tasks, which reduces the need for human labor. Previous studies primarily focus on effectively utilising the labelled and unlabeled data to improve…

Self-Supervised Learning (SSL) has proven to be useful in various speech tasks. However, these methods are generally very demanding in terms of data, memory, and computational resources. BERT-based Speech pre-Training with Random-projection…

This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a neural network,…

While large multilingual automatic speech recognition (ASR) models achieve remarkable performance, the internal mechanisms of the end-to-end pipeline, particularly concerning fairness and efficacy across languages, remain underexplored.…

Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two…

In this study, we investigate the benefits of domain-specific self-supervised pre-training for both offline and streaming ASR in Air Traffic Control (ATC) environments. We train BEST-RQ models on 4.5k hours of unlabeled ATC data, then…

In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this loss is less tolerant to semantically similar samples due to…

Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask:…

In recent years, much work has been done on processing of wireless spectrum data involving machine learning techniques in domain-related problems for cognitive radio networks, such as anomaly detection, modulation classification, technology…