Search Results for author:
Found 47 papers, 16 papers with code
Towards Robust Waveform-Based Acoustic Models
We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions.
Automatic audiovisual synchronisation for ultrasound tongue imaging
Our results demonstrate the strength of our approach and its ability to generalise to data from new domains.
European Language Grid: A Joint Platform for the European Language Technology Community
Europe is a multilingual society, in which dozens of languages are spoken.
Exploiting ultrasound tongue imaging for the automatic detection of speech articulation errors
For automatic velar fronting error detection, the best results are obtained when jointly using ultrasound and audio.
Silent versus modal multi-speaker speech recognition from ultrasound and video
We observe that silent speech recognition from imaging data underperforms compared to modal speech recognition, likely due to a speaking-mode mismatch between training and testing.
Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos
We present the Tongue and Lips corpus (TaL), a multi-speaker corpus of audio, ultrasound tongue imaging, and lip videos.
Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models
To the best of our knowledge, we have achieved state-of-the-art end-to-end Transformer based model performance on Switchboard and AMI.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers
Self-attention models such as Transformers, which can capture temporal relationships without being limited by the distance between events, have given competitive speech recognition results.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Leveraging speaker attribute information using multi task learning for speaker verification and diarization
On a test set of US Supreme Court recordings, we show that by leveraging two additional forms of speaker attribute information derived respectively from the matched training data, and VoxCeleb corpus, we improve the performance of our deep speaker embeddings for both verification and diarization tasks, achieving a relative improvement of 26. 2% in DER and 6. 7% in EER compared to baselines using speaker labels only.
Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation.
Word Error Rate Estimation Without ASR Output: e-WER2
Measuring the performance of automatic speech recognition (ASR) systems requires manually transcribed data in order to compute the word error rate (WER), which is often time-consuming and expensive.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
When Can Self-Attention Be Replaced by Feed Forward Layers?
Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition.
European Language Grid: An Overview
With 24 official EU and many additional languages, multilingualism in Europe and an inclusive Digital Single Market can only be enabled through Language Technologies (LTs).
DropClass and DropAdapt: Dropping classes for deep speaker representation learning
The first proposed method, DropClass, works via periodically dropping a random subset of classes from the training data and the output layer throughout training, resulting in a feature extractor trained on many different classification tasks.
Multi-scale Octave Convolutions for Robust Speech Recognition
We propose a multi-scale octave convolution layer to learn robust speech representations efficiently.
Channel adversarial training for speaker verification and diarization
Previous work has encouraged domain-invariance in deep speaker embedding by adversarially classifying the dataset or labelled environment to which the generated features belong.
Speaker Adaptive Training using Model Agnostic Meta-Learning
Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions.
Acoustic Model Adaptation from Raw Waveforms with SincNet
Raw waveform acoustic modelling has recently gained interest due to neural networks' ability to learn feature extraction, and the potential for finding better representations for a given scenario than hand-crafted features.
Embeddings for DNN speaker adaptive training
In this work, we investigate the use of embeddings for speaker-adaptive training of DNNs (DNN-SAT) focusing on a small amount of adaptation data per speaker.
Top-down training for neural networks
Interpreting the top layers as a classifier and the lower layers a feature extractor, one can hypothesize that unwanted network convergence may occur when the classifier has overfit with respect to the feature extractor.
Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions
We investigate the automatic processing of child speech therapy sessions using ultrasound visual biofeedback, with a specific focus on complementing acoustic features with ultrasound images of the tongue for the tasks of speaker diarization and time-alignment of target words.
Speaker-independent classification of phonetic segments from raw ultrasound in child speech
Ultrasound tongue imaging (UTI) provides a convenient way to visualize the vocal tract during speech production.
Synchronising audio and ultrasound by learning cross-modal embeddings
Audiovisual synchronisation is the task of determining the time offset between speech audio and a video recording of the articulators.
Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models
Acoustic model adaptation to unseen test recordings aims to reduce the mismatch between training and testing conditions.
Lattice-based lightly-supervised acoustic model training
This text data can be used for lightly supervised training, in which text matching the audio is selected using an existing speech recognition model.
Dynamic Evaluation of Transformer Language Models
This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation.
Ranked #1 on
Language Modelling
on Hutter Prize
Analyzing deep CNN-based utterance embeddings for acoustic model adaptation
We analyze the representations learned by deep CNNs and compare them with deep neural network (DNN) representations and i-vectors, in the context of acoustic model adaptation.
Word Error Rate Estimation for Speech Recognition: e-WER
Measuring the performance of automatic speech recognition (ASR) systems requires manually transcribed data in order to compute the word error rate (WER), which is often time-consuming and expensive.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
WERd: Using Social Text Spelling Variants for Evaluating Dialectal Speech Recognition
We study the problem of evaluating automatic speech recognition (ASR) systems that target dialectal speech input.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Speech Recognition Challenge in the Wild: Arabic MGB-3
Two hours of audio per dialect were released for development and a further two hours were used for evaluation.
Dynamic Evaluation of Neural Sequence Models
We present methodology for using dynamic evaluation to improve neural sequence models.
Ranked #10 on
Language Modelling
on Hutter Prize
End-to-End Neural Segmental Models for Speech Recognition
Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Small-footprint Highway Deep Neural Networks for Speech Recognition
Furthermore, HDNNs are more controllable than DNNs: the gate functions of an HDNN can control the behavior of the whole network using a very small number of model parameters.
Multiplicative LSTM for sequence modelling
We introduce multiplicative LSTM (mLSTM), a recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures.
Ranked #14 on
Language Modelling
on Hutter Prize
Multi-view Dimensionality Reduction for Dialect Identification of Arabic Broadcast Speech
In this work, we present a new Vector Space Model (VSM) of speech utterances for the task of spoken dialect identification.
The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition
For language modelling, we made available over 110M words crawled from Aljazeera Arabic website Aljazeera. net for a 10 year duration 2000-2011.
Knowledge Distillation for Small-footprint Highway Networks
We have shown that HDNN-based acoustic models can achieve comparable recognition accuracy with much smaller number of model parameters compared to plain deep neural network (DNN) acoustic models.
Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
The results of this paper describe a novel approach to the automatic story segmentation and storyline clustering problem.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Differentiable Pooling for Unsupervised Acoustic Model Adaptation
We present a deep neural network (DNN) acoustic model that includes parametrised and differentiable pooling operators.
Segmental Recurrent Neural Networks for End-to-end Speech Recognition
This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction.
Ranked #16 on
Speech Recognition
on TIMIT
Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation
This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) -- a method that linearly re-combines hidden units in a speaker- or environment-dependent manner using small amounts of unsupervised adaptation data.
Small-footprint Deep Neural Networks with Highway Connections for Speech Recognition
For speech recognition, deep neural networks (DNNs) have significantly improved the recognition accuracy in most of benchmark datasets and application domains.
Automatic Dialect Detection in Arabic Broadcast Speech
We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of 100%.
Tied Probabilistic Linear Discriminant Analysis for Speech Recognition
Acoustic models using probabilistic linear discriminant analysis (PLDA) capture the correlations within feature vectors using subspaces which do not vastly expand the model.
