Related papers: Multi-Span Acoustic Modelling using Raw Waveform S…

In this work, we investigate the joint use of articulatory and acoustic features for automatic speech recognition (ASR) of pathological speech. Despite long-lasting efforts to build speaker- and text-independent ASR systems for people with…

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…

Acoustic-to-articulatory inversion (AAI) methods estimate articulatory movements from the acoustic speech signal, which can be useful in several tasks such as speech recognition, synthesis, talking heads and language tutoring. Most earlier…

This work introduces sequential neural beamforming, which alternates between neural network based spectral separation and beamforming based spatial separation. Our neural networks for separation use an advanced convolutional architecture…

This paper presents an end-to-end deep learning model for Automatic Speech Recognition (ASR) that transcribes Nepali speech to text. The model was trained and tested on the OpenSLR (audio, text) dataset. The majority of the audio dataset…

In this paper, we presents a low-complexity deep learning frameworks for acoustic scene classification (ASC). The proposed framework can be separated into three main steps: Front-end spectrogram extraction, back-end classification, and late…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design decision assumes the primary input data source does not change…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply when they are deployed in the real world. We find that the…

The goal of this paper is to simulate the benefits of jointly applying active learning (AL) and semi-supervised training (SST) in a new speech recognition application. Our data selection approach relies on confidence filtering, and its…

We propose a learnable mel-frequency cepstral coefficient (MFCC) frontend architecture for deep neural network (DNN) based automatic speaker verification. Our architecture retains the simplicity and interpretability of MFCC-based features…

Environmental audio tagging is a newly proposed task to predict the presence or absence of a specific audio event in a chunk. Deep neural network (DNN) based methods have been successfully adopted for predicting the audio tags in the…

Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…

Acoustic Echo Cancellation (AEC) is essential for accurate recognition of queries spoken to a smart speaker that is playing out audio. Previous work has shown that a neural AEC model operating on log-mel spectral features (denoted "logmel"…

Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to…

For multi-channel speech recognition, speech enhancement techniques such as denoising or dereverberation are conventionally applied as a front-end processor. Deep learning-based front-ends using such techniques require aligned clean and…

Recent advances in supervised, semi-supervised and self-supervised deep learning algorithms have shown significant improvement in the performance of automatic speech recognition(ASR) systems. The state-of-the-art systems have achieved a…

We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given…

Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even…