26 accepted papers
Grammatical feedback is crucial for L2 learners, teachers, and testers. Spoken grammatical error correction (GEC) aims to supply feedback to L2 learners on their use of grammar when speaking. This process usually relies on a cascaded pipeline comprising an ASR system, disfluency removal, and GEC, wi…
Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech. Most efforts have focused on sophisticated neural architectures intended to better model the data distribution. Yet, in evaluations it is generally found that no single model is preferred for al…
Efficiently and reliably estimating uncertainty is an important objective in deep learning. It is especially pertinent to autoregressive sequence tasks, where training and inference costs are typically very high. However, existing research has predominantly focused on tasks with static data such as…
Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model’s prediction to ensure appropriate decisions are made by the system. Deep ensembles are the de-facto standard approach to obtaining various measures…
A significant concern with deep learning based approaches is that they are difficult to interpret, which means detecting bias in network predictions can be challenging. Concept Activation Vectors (CAVs) have been proposed to address this problem. These use representations - perturbations of activati…
For many challenging tasks there is often limited data to train the systems in an end-to-end fashion, which has become increasingly popular for deep-learning. However, these tasks can normally be split into multiple separate modules, with significant quantities of data associated with each module. S…
Ensemble approaches are commonly used techniques to improving a system by combining multiple model predictions. Additionally these schemes allow the uncertainty, as well as the source of the uncertainty, to be derived for the prediction. Unfortunately these benefits come at a computational and memor…
Recently, there has been growth in providers of speech transcription services enabling others to leverage technology they would not normally be able to use. As a result, speech-enabled solutions have become commonplace. Their success critically relies on the quality, accuracy, and reliability of the…
Automatic language assessment and learning systems are required to support the global growth in English language learning. They need to be able to provide reliable and meaningful feedback to help learners develop their skills. This paper considers the question of detecting "grammatical" errors in no…
The standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word. In the simplest case, these scores are word posterior probabilities whilst more complex schemes utilise bi-directional recurrent neural network (Bi…
State-of-the-art English automatic speech recognition systems typically use phonetic rather than graphemic lexicons. Graphemic systems are known to perform less well for English as the mapping from the written form to the spoken form is complicated. However, in recent years the representational powe…
Word units are a popular choice in statistical language modelling. For inflective and agglutinative languages this choice may result in a high out of vocabulary rate. Subword units, such as morphs, provide an interesting alternative to words. These units can be derived in an unsupervised fashion and…
Recurrent neural network language models (RNNLMs) have becoming increasingly popular in many applications such as automatic speech recognition (ASR). Significant performance improvements in both perplexity and word error rate over standard n-gram LMs have been widely reported on ASR tasks. In contra…
Training neural network acoustic models on limited quantities of data is a challenging task. A number of techniques have been proposed to improve generalisation. This paper investigates one such technique called stimulated training. It enables standard criteria such as cross-entropy to enforce spati…
In recent years, recurrent neural network language models (RNNLMs) have become increasingly popular for a range of applications including speech recognition. However, the training of RNNLMs is computationally expensive, which limits the quantity of data, and size of network, that can be used. In ord…
Rapid adaptation of deep neural networks (DNNs) with limited unsupervised data remains a significant challenge. This paper investigates the combination of two schemes that have been proposed to address this problem: i-vector representations and multi-basis adaptive neural networks (MBANNs). Two appr…
Automatic segmentation is a crucial initial processing step for processing multi-genre broadcast (MGB) audio. It is very challenging since the data exhibits a wide range of both speech types and background conditions with many types of non-speech audio. This paper describes a segmentation system for…
Improved speech recognition performance can often be obtained by combining multiple systems together. Joint decoding, where scores from multiple systems are combined during decoding rather than combining hypotheses, is one efficient approach for system combination. In standard joint decoding the fra…
The number of languages for which speech recognition systems have become available is growing each year. This paper proposes to view languages as points in some rich space, termed language space, where bases are eigen-languages and a particular selection of the projection determines points. Such an…
This paper introduces a method to produce high-quality transcriptions of speech data from only two crowd-sourced transcriptions. These transcriptions, produced cheaply by people on the Internet, for example through Amazon Mechanical Turk, are often of low quality. Often, multiple crowd-sourced trans…
Recurrent neural network language models (RNNLMs) are becoming increasingly popular for speech recognition. Previously, we have shown that RNNLMs with a full (non-classed) output layer (F-RNNLMs) can be trained efficiently using a GPU giving a large reduction in training time over conventional class…
Recent progress in acoustic modeling with deep neural network has significantly improved the performance of automatic speech recognition systems. However, it remains as an open problem how to rapidly adapt these networks with limited, unsupervised, data. Most existing methods to adapt a neural netwo…
Recurrent neural network language models (RNNLM) have become an increasingly popular choice for state-of-the-art speech recognition systems. Linguistic factors in??uencing the realization of surface word sequences, for example, expressive richness, are only implicitly learned by RNNLMs. Observed sen…
In recent years recurrent neural network language models (RNNLMs) have been successfully applied to a range of tasks including speech recognition. However, an important issue that limits the quantity of data used, and their possible application areas, is the computational cost in training. A signi??…
In this paper we investigate the use of noise-robust features characterizing the speech excitation signal as complementary features to the usually considered vocal tract based features for Automatic Speech Recognition (ASR). The proposed Excitation-based Features (EBF) are tested in a state-of-the-a…
Large vocabulary continuous speech recognition systems require a mapping from words, or tokens, into sub-word units to enable robust estimation of acoustic model parameters, and to model words not seen in the training data. The standard approach to achieve this is to manually generate a lexicon wher…