相关论文: Improving Unsupervised Sparsespeech Acoustic Model…

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main…

Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of…

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are…

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…

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

In this work, we build upon our previous publication and use diffusion-based generative models for speech enhancement. We present a detailed overview of the diffusion process that is based on a stochastic differential equation and delve…

Scribble-supervised medical image segmentation tackles the limitation of sparse masks. Conventional approaches alternate between: labeling pseudo-masks and optimizing network parameters. However, such iterative two-stage paradigm is…

Semi-supervised learning has received considerable attention for its potential to leverage abundant unlabeled data to enhance model robustness. Pseudo labeling is a widely used strategy in semi supervised learning. However, existing methods…

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

Speech embeddings are fixed-size acoustic representations of variable-length speech sequences. They are increasingly used for a variety of tasks ranging from information retrieval to unsupervised term discovery and speech segmentation.…

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.…

Discrete speech tokens have gained attention for their storage efficiency and integration with Large Language Models (LLMs). They are commonly categorized into acoustic and semantic tokens, with the latter being more advantageous for…

Automatic Speech Recognition (ASR) is widely used within consumer devices such as mobile phones. Recently, personalization or on-device model fine-tuning has shown that adaptation of ASR models towards target user speech improves their…

Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating…

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed approach uses a teacher model which is updated as the…

We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support…

Prototype-driven text generation uses non-parametric models that first choose from a library of sentence "prototypes" and then modify the prototype to generate the output text. While effective, these methods are inefficient at test time as…

We present the Perceptimatic English Benchmark, an open experimental benchmark for evaluating quantitative models of speech perception in English. The benchmark consists of ABX stimuli along with the responses of 91 American…

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

This study investigates the impact of integrating a dataset of disordered speech recordings ($\sim$1,000 hours) into the fine-tuning of a near state-of-the-art ASR baseline system. Contrary to what one might expect, despite the data being…