Related papers: Contaminated speech training methods for robust DN…
We present a deep-learning approach for the task of Concurrent Speaker Detection (CSD) using a modified transformer model. Our model is designed to handle multi-microphone data but can also work in the single-microphone case. The method can…
In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…
In this paper, we present several adaptation methods for non-native speech recognition. We have tested pronunciation modelling, MLLR and MAP non-native pronunciation adaptation and HMM models retraining on the HIWIRE foreign accented…
Current state-of-the-art speech recognition models are trained to map acoustic signals into sub-lexical units. While these models demonstrate superior performance, they remain vulnerable to out-of-distribution conditions such as background…
Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on…
In this work, we conducted an empirical comparative study of the performance of text-independent speaker verification in emotional and stressful environments. This work combined deep models with shallow architecture, which resulted in novel…
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…
We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…
Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…
Speech recognition in adverse real-world environments is highly affected by reverberation and nonstationary background noise. A well-known strategy to reduce such undesired signal components in multi-microphone scenarios is spatial…
Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddings can be learned…
Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design decisions including network architecture, size, and training…
Recently, progressive learning has shown its capacity to improve speech quality and speech intelligibility when it is combined with deep neural network (DNN) and long short-term memory (LSTM) based monaural speech enhancement algorithms,…
Acoustic modeling for child speech is challenging due to the high acoustic variability caused by physiological differences in the vocal tract. The dearth of publicly available datasets makes the task more challenging. In this work, we…
This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to…
In recent years, deep learning based machine lipreading has gained prominence. To this end, several architectures such as LipNet, LCANet and others have been proposed which perform extremely well compared to traditional lipreading DNN-HMM…
Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…
Audio-visual speaker extraction has attracted increasing attention, as it removes the need for pre-registered speech and leverages the visual modality as a complement to audio. Although existing methods have achieved impressive performance,…
Diffusion models have recently shown promising results for difficult enhancement tasks such as the conditional and unconditional restoration of natural images and audio signals. In this work, we explore the possibility of leveraging a…
For speech recognition, deep neural networks (DNNs) have significantly improved the recognition accuracy in most of benchmark datasets and application domains. However, compared to the conventional Gaussian mixture models, DNN-based…