Related papers: Unsupervised Automatic Speech Recognition: A Revie…

Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR outputs. However, under resource-limited conditions, the…

Unsupervised automatic speech recognition (ASR) aims to learn the mapping between the speech signal and its corresponding textual transcription without the supervision of paired speech-text data. A word/phoneme in the speech signal is…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…

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…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Unsupervised representation learning for speech processing has matured greatly in the last few years. Work in computer vision and natural language processing has paved the way, but speech data offers unique challenges. As a result, methods…

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…

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…

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…

We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of…

Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a relatively big unlabeled data set for such languages is more…

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish…

We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given…

End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes…

Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-switched speech. These monolingual data may be more closely…

Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar…

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…