19 accepted papers
Magnitude spectrum-based features are the most widely employed front-ends for acoustic modelling in automatic speech recognition (ASR) systems. In this paper, we investigate the possibility and efficacy of acoustic modelling using the raw short-time phase spectrum. In particular, we study the useful…
Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in general, freezing the trained feature extractor (the lower layers) and retraining the classifier (the upper layers) on the…
Previous work has encouraged domain-invariance in deep speaker embedding by adversarially classifying the dataset or labelled environment to which the generated features belong. We propose a training strategy which aims to produce features that are invariant at the granularity of the recording or ch…
We propose a method for zero-resource domain adaptation of DNN acoustic models, for use in low-resource situations where the only in-language training data available may be poorly matched to the intended target domain. Our method uses a multi-lingual model in which several DNN layers are shared betw…
End-to-end models yield impressive speech recognition results on clean datasets while having inferior performance on noisy datasets. To address this, we propose transfer learning from a clean dataset (WSJ) to a noisy dataset (CHiME4) for connectionist temporal classification models. We argue that th…
We propose a multi-scale octave convolution layer to learn robust speech representations efficiently. Octave convolutions were introduced by Chen et al [1] in the computer vision field to reduce the spatial redundancy of the feature maps by decomposing the output of a convolutional layer into featur…
DNNs play a major role in the state-of-the-art ASR systems. They can be used for extracting features and building probabilistic models for acoustic and language modelling. Despite their huge practical success, the level of theoretical understanding has remained shallow. This paper investigates DNNs…
Ultrasound tongue imaging (UTI) provides a convenient way to visualize the vocal tract during speech production. UTI is increasingly being used for speech therapy, making it important to develop automatic methods to assist various time-consuming manual tasks currently performed by speech therapists.…
The usual attention mechanisms used for encoder-decoder models do not constrain the relationship between input and output sequences to be monotonic. To address this we explore windowed attention mechanisms which restrict attention to a block of source hidden states. Rule-based windowing restricts at…
We explore dynamic evaluation, where sequence models are adapted to the recent sequence history using gradient descent, assigning higher probabilities to re-occurring sequential patterns. We develop a dynamic evaluation approach that outperforms existing adaptation approaches in our comparisons. We…
Deep learning has significantly advanced state-of-the-art of speech recognition in the past few years. However, compared to conventional Gaussian mixture acoustic models, neural network models are usually much larger, and are therefore not very deployable in embedded devices. Previously, we investig…
We introduce multiplicative LSTM (mLSTM), a novel recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures. mLSTM is characterised by its ability to have different recurrent transition funct…
In this paper we present an extension of our previously described neural machine translation based system for punctuated transcription. This extension allows the system to map from per frame acoustic features to word level representations by replacing the traditional encoder in the encoder-decoder a…
Recently, there has been an increasing interest in end-to-end speech recognition using neural networks, with no reliance on hidden Markov models (HMMs) for sequence modelling as in the standard hybrid framework. The recurrent neural network (RNN) encoderdecoder is such a model, performing sequence t…
This paper extends learning hidden unit contributions (LHUC) unsupervised speaker adaptation with speaker adaptive training (SAT). Contrary to other SAT approaches, the proposed technique does not require speaker-dependent features, the generation of auxiliary generative models to estimate or extrac…
This paper proposes a differentiable pooling mechanism to perform model-based neural network speaker adaptation. The proposed technique learns a speaker-dependent combination of activations within pools of hidden units, was shown to work well unsupervised, and does not require speaker-adaptive train…
Given a transcription, sampling from a good model of acoustic feature trajectories should result in plausible realizations of an utterance. However, samples from current probabilistic speech synthesis systems result in low quality synthetic speech. Henter et al. have demonstrated the need to capture…
Acoustic models based on Gaussian mixture models (GMMs) typically use short span acoustic feature inputs. This does not capture long-term temporal information from speech owing to the conditional independence assumption of hidden Markov models. In this paper, we present an implicit approach that app…
The use of context-dependent targets has become standard in hybrid DNN systems for automatic speech recognition. However, we argue that despite the use of state-tying, optimising to context-dependent targets can lead to over-fitting, and that discriminating between arbitrary tied context-dependent t…