Related papers: Towards Using Context-Dependent Symbols in CTC Wit…
Phoneme-based acoustic modeling of large vocabulary automatic speech recognition takes advantage of phoneme context. The large number of context-dependent (CD) phonemes and their highly varying statistics require tying or smoothing to…
Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from…
Code-Switching (CS) remains a challenge for Automatic Speech Recognition (ASR), especially character-based models. With the combined choice of characters from multiple languages, the outcome from character-based models suffers from phoneme…
Deep neural networks based on layer-stacking architectures have historically suffered from poor inherent interpretability. Meanwhile, symbolic probabilistic models function with clear interpretability, but how to combine them with neural…
Connectionist Temporal Classification has recently attracted a lot of interest as it offers an elegant approach to building acoustic models (AMs) for speech recognition. The CTC loss function maps an input sequence of observable feature…
Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional…
Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics. However, with high-quality contextualized document representations, do we really need…
Although connectionist temporal classification (CTC) has the label context independence assumption, it can still implicitly learn a context-dependent internal language model (ILM) due to modern powerful encoders. In this work, we…
Non-native speech causes automatic speech recognition systems to degrade in performance. Past strategies to address this challenge have considered model adaptation, accent classification with a model selection, alternate pronunciation…
In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned with deep learning models. Motivated by the human approach to…
Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…
Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but sometimes fails to converge, especially in…
We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length. To this end we propose a convolutional neural network (CNN) based architecture which…
We first observe a potential weakness of continuous vector representations of symbols in neural machine translation. That is, the continuous vector representation, or a word embedding vector, of a symbol encodes multiple dimensions of…
External knowledge is often useful for natural language understanding tasks. We introduce a contextual text representation model called Conceptual-Contextual (CC) embeddings, which incorporates structured knowledge into text…
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…
Deep Neural Networks trained as image auto-encoders have recently emerged as a promising direction for advancing the state-of-the-art in image compression. The key challenge in learning such networks is twofold: To deal with quantization,…
Deep neural networks (DNNs) are powerful tools in learning sophisticated but fixed mapping rules between inputs and outputs, thereby limiting their application in more complex and dynamic situations in which the mapping rules are not kept…
Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work…
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…