相关论文: Blank-regularized CTC for Frame Skipping in Neural…

Connectionist temporal classification (CTC) -based models are attractive because of their fast inference in automatic speech recognition (ASR). Language model (LM) integration approaches such as shallow fusion and rescoring can improve the…

We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR).…

Automatic Phoneme Recognition (APR) systems are often trained using pseudo phoneme-level annotations generated from text through Grapheme-to-Phoneme (G2P) systems. These G2P systems frequently output multiple possible pronunciations per…

Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating positive examples that assist the model in learning robust and…

Predicting the altered acoustic frames is an effective way of self-supervised learning for speech representation. However, it is challenging to prevent the pretrained model from overfitting. In this paper, we proposed to introduce two…

This paper introduces a novel method to diagnose the source-target attention in state-of-the-art end-to-end speech recognition models with joint connectionist temporal classification (CTC) and attention training. Our method is based on the…

End-to-end automatic speech recognition has become the dominant paradigm in both academia and industry. To enhance recognition performance, the Weighted Finite-State Transducer (WFST) is widely adopted to integrate acoustic and language…

We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of…

We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly…

This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model. Streaming RNN-T trained from scratch usually performs worse than…

Temporal action segmentation tags action labels for every frame in an input untrimmed video containing multiple actions in a sequence. For the task of temporal action segmentation, we propose an encoder-decoder-style architecture named…

Mispronunciation Detection and Diagnosis (MDD) requires modeling fine-grained acoustic deviations. However, current ASR-derived MDD systems often face inherent limitations. In particular, CTC-based models favor sequence-level alignments…

In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy. Although a few existing methods are able to achieve this goal, they are difficult to…

Training large language representation models has become a standard in the natural language processing community. This allows for fine tuning on any number of specific tasks, however, these large high capacity models can continue to train…

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…

This paper proposes an adaptation method for end-to-end speech recognition. In this method, multiple automatic speech recognition (ASR) 1-best hypotheses are integrated in the computation of the connectionist temporal classification (CTC)…

In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by…

The transducer architecture is becoming increasingly popular in the field of speech recognition, because it is naturally streaming as well as high in accuracy. One of the drawbacks of transducer is that it is difficult to decode in a fast…

Catastrophic forgetting (CF) occurs when a neural network loses the information previously learned while training on a set of samples from a different distribution, i.e., a new task. Existing approaches have achieved remarkable results in…

We report an extension of a Keras Model, called CTCModel, to perform the Connectionist Temporal Classification (CTC) in a transparent way. Combined with Recurrent Neural Networks, the Connectionist Temporal Classification is the reference…