Related papers: Spoken Digit Recognition and Speaker Classificatio…

Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, these methods can sometimes be inadequate, resulting in…

Spoken Question-Answering (SQA) is a core capability for useful and interactive artificial intelligence systems. Recently, several speech-language models (SpeechLMs) have been released with a specific focus on improving their SQA…

This paper presents a Pronunciation-Aware Contextualized (PAC) framework to address two key challenges in Large Language Model (LLM)-based Automatic Speech Recognition (ASR) systems: effective pronunciation modeling and robust homophone…

Self-supervised speech representations (SSSRs) have been successfully applied to a number of speech-processing tasks, e.g. as feature extractor for speech quality (SQ) prediction, which is, in turn, relevant for assessment and training…

In this paper, we propose a privacy-preserving method with a secret key for convolutional neural network (CNN)-based speech classification tasks. Recently, many methods related to privacy preservation have been developed in image…

Non-intrusive intelligibility prediction is important for its application in realistic scenarios, where a clean reference signal is difficult to access. The construction of many non-intrusive predictors require either ground truth…

The increasingly stringent requirement on quality-of-experience in 5G/B5G communication systems has led to the emerging neural speech enhancement techniques, which however have been developed in isolation from the existing expert-rule based…

Speech encoding models use auditory representations to predict how the human brain responds to spoken language stimuli. Most performant encoding models linearly map the hidden states of artificial neural networks to brain data, but this…

This paper proposes a novel approach that uses deep neural networks for classifying imagined speech, significantly increasing the classification accuracy. The proposed approach employs only the EEG channels over specific areas of the brain…

In this paper, we propose a novel technique for direct recognition of multiple speech streams given the single channel of mixed speech, without first separating them. Our technique is based on permutation invariant training (PIT) for…

The paradigm of reservoir computing exploits the nonlinear dynamics of a physical reservoir to perform complex time-series processing tasks such as speech recognition and forecasting. Unlike other machine-learning approaches, reservoir…

The electroencephalography (EEG) signals recorded in parallel with speech are used to perform isolated and continuous speech recognition. During speaking process, one also hears his or her own speech and this speech perception is also…

Efficient audio feature extraction is critical for low-latency, resource-constrained speech recognition. Conventional preprocessing techniques, such as Mel Spectrogram, Perceptual Linear Prediction (PLP), and Learnable Spectrogram, achieve…

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Speech separation approaches for single-channel, dry speech mixtures have significantly improved. However, real-world spatial and reverberant acoustic environments remain challenging, limiting the effectiveness of these approaches for…

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

Non-intrusive intelligibility prediction estimates how well hearing-impaired listeners understand hearing-aid-processed speech without a clean reference. We study this task in the 3rd Clarity Prediction Challenge using two frozen speech…

Physical reservoir computing provides a powerful machine learning paradigm that exploits nonlinear physical dynamics for efficient information processing. By incorporating quantum effects, quantum reservoir computing offers superior…

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module,…

The current methodology in tackling Acoustic Scene Classification (ASC) task can be described in two steps, preprocessing of the audio waveform into log-mel spectrogram and then using it as the input representation for Convolutional Neural…