Related papers: Exploiting semi-supervised training through a drop…
Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…
We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…
Self-training (ST), or pseudo-labeling has sparked significant interest in the automatic speech recognition (ASR) community recently because of its success in harnessing unlabeled data. Unlike prior semi-supervised learning approaches that…
The end-to-end (E2E) automatic speech recognition (ASR) systems are often required to operate in reverberant conditions, where the long-term sub-band envelopes of the speech are temporally smeared. In this paper, we develop a feature…
End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…
Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to…
Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…
In this paper, we investigate the semi-supervised joint training of text to speech (TTS) and automatic speech recognition (ASR), where a small amount of paired data and a large amount of unpaired text data are available. Conventional…
Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…
In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of…
We consider the cross-domain sentiment classification problem, where a sentiment classifier is to be learned from a source domain and to be generalized to a target domain. Our approach explicitly minimizes the distance between the source…
Recent work has designed methods to demonstrate that model updates in ASR training can leak potentially sensitive attributes of the utterances used in computing the updates. In this work, we design the first method to demonstrate…
Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years. %Despite the substantial advancement% While most existing work assumes a simple and fixed degradation model (e.g., bicubic…
Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance. However, the approach mostly focus on in-domain performance for public datasets. In this study, we…
Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search,…
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…
We address the problem of language model customization in applications where the ASR component needs to manage domain-specific terminology; although current state-of-the-art speech recognition technology provides excellent results for…
Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introduces a novel approach…
Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…
The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…