Related papers: Semi-supervised Development of ASR Systems for Mul…

We focus on the problem of language modeling for code-switched language, in the context of automatic speech recognition (ASR). Language modeling for code-switched language is challenging for (at least) three reasons: (1) lack of available…

In recent years, automatic speech recognition (ASR) systems have significantly improved, especially in languages with a vast amount of transcribed speech data. However, ASR systems tend to perform poorly for low-resource languages with…

Recently, there has been significant progress made in Automatic Speech Recognition (ASR) of code-switched speech, leading to gains in accuracy on code-switched datasets in many language pairs. Code-switched speech co-occurs with monolingual…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Developing Automatic Speech Recognition (ASR) for low-resource languages is a challenge due to the small amount of transcribed audio data. For many such languages, audio and text are available separately, but not audio with transcriptions.…

The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and…

Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint…

Languages usually switch within a multilingual speech signal, especially in a bilingual society. This phenomenon is referred to as code-switching (CS), making automatic speech recognition (ASR) challenging under a multilingual scenario. We…

Recognizing code-switched speech is challenging for Automatic Speech Recognition (ASR) for a variety of reasons, including the lack of code-switched training data. Recently, we showed that monolingual ASR systems fine-tuned on code-switched…

Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel corpus of speech and orthographic transcriptions. Recently,…

Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but also navigate the intricacies of linguistic diversity. In this paper, we address…

Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited,…

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for…

Automatic speech recognition for low-resource languages remains fundamentally constrained by the scarcity of labeled data and computational resources required by state-of-the-art models. We present a systematic investigation into…

Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to…

Code-switching (CS), common in multilingual settings, presents challenges for ASR due to scarce and costly transcribed data caused by linguistic complexity. This study investigates building CS-ASR using synthetic CS data. We propose a…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more…

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to…