Search Results for author:
Found 33 papers, 11 papers with code
Mask-combine Decoding and Classification Approach for Punctuation Prediction with real-time Inference Constraints
In this work, we unify several existing decoding strategies for punctuation prediction in one framework and introduce a novel strategy which utilises multiple predictions at each word across different windows.
Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR
We present a method for cross-lingual training an ASR system using absolutely no transcribed training data from the target language, and with no phonetic knowledge of the language in question.
Fusing ASR Outputs in Joint Training for Speech Emotion Recognition
However, due to the scarcity of emotion labelled data and the difficulty of recognizing emotional speech, it is hard to obtain reliable linguistic features and models in this research area.
It's not what you said, it's how you said it: discriminative perception of speech as a multichannel communication system
People convey information extremely effectively through spoken interaction using multiple channels of information transmission: the lexical channel of what is said, and the non-lexical channel of how it is said.
Segmenting Subtitles for Correcting ASR Segmentation Errors
Typical ASR systems segment the input audio into utterances using purely acoustic information, which may not resemble the sentence-like units that are expected by conventional machine translation (MT) systems for Spoken Language Translation.
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.
Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning
(2) To improve the already strong results further, we created a small dataset (ClassArch) consisting of ancient Greek vase paintings from the 6-5th century BCE with person and pose annotations.
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.
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.
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.
Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines
In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation.
Understanding Compositional Structures in Art Historical Images using Pose and Gaze Priors
These compositions are useful in analyzing the interactions in an image to study artists and their artworks.
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.
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.
Subtitles to Segmentation: Improving Low-Resource Speech-to-TextTranslation Pipelines
In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation.
Recognizing Characters in Art History Using Deep Learning
We present experiments and analysis on three different models and show that the model trained on domain related data gives the best performance for recognizing character.
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.
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.
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.
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.
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.
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.
Few-shot learning with attention-based sequence-to-sequence models
End-to-end approaches have recently become popular as a means of simplifying the training and deployment of speech recognition systems.
Learning to adapt: a meta-learning approach for speaker adaptation
The performance of automatic speech recognition systems can be improved by adapting an acoustic model to compensate for the mismatch between training and testing conditions, for example by adapting to unseen speakers.
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.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
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.
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%.
