Related papers: Improving End-to-End Speech Recognition with Polic…

In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised…

Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Conventionally, the manner of articulations in speech signal are derived using discriminative signal processing techniques or deep learning approaches. However, training such complex systems involves feature extraction, phoneme force…

Automatic speech recognition (ASR) technologies today are primarily optimized for given datasets; thus, any changes in the application environment (e.g., acoustic conditions or topic domains) may inevitably degrade the performance. We can…

In this paper, we describe the Maximum Uniformity of Distribution (MUD) algorithm with the power-law nonlinearity. In this approach, we hypothesize that neural network training will become more stable if feature distribution is not too much…

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

The biases present in training datasets have been shown to affect models for sentence pair classification tasks such as natural language inference (NLI) and fact verification. While fine-tuning models on additional data has been used to…

This paper proposes an unsupervised data selection method by using a submodular function based on contrastive loss ratios of target and training data sets. A model using a contrastive loss function is trained on both sets. Then the ratio of…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

Voice conversion (VC) using sequence-to-sequence learning of context posterior probabilities is proposed. Conventional VC using shared context posterior probabilities predicts target speech parameters from the context posterior…

Self-supervised pre-training of language models usually consists in predicting probability distributions over extensive token vocabularies. In this study, we propose an innovative method that shifts away from probability prediction and…

Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end acoustic model that extends the standard Recurrent Neural Network Transducer (RNN-T) for the purpose of the external language model (LM) fusion. In HAT, the blank…

Modern mispronunciation detection and diagnosis systems have seen significant gains in accuracy due to the introduction of deep learning. However, these systems have not been evaluated for the ability to be run in real-time, an important…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

Many end-to-end Automatic Speech Recognition (ASR) systems still rely on pre-processed frequency-domain features that are handcrafted to emulate the human hearing. Our work is motivated by recent advances in integrated learnable feature…

We present a system for the Zero Resource Speech Challenge 2021, which combines a Contrastive Predictive Coding (CPC) with deep cluster. In deep cluster, we first prepare pseudo-labels obtained by clustering the outputs of a CPC network…

Different studies have shown the importance of visual cues throughout the speech perception process. In fact, the development of audiovisual approaches has led to advances in the field of speech technologies. However, although noticeable…

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel…