Related papers: IR-UWB Radar-Based Contactless Silent Speech Recog…

To better model the contextual information and increase the generalization ability of Speech Activity Detection (SAD) system, this paper leverages a multi-lingual Automatic Speech Recognition (ASR) system to perform SAD. Sequence…

This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100%…

In automatic speech recognition, any factor that alters the acoustic properties of speech can pose a challenge to the system's performance. This paper presents a novel approach for automatic whispered speech recognition in the Irish dialect…

The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…

The paper characterizes the fundamental limits of integrated sensing and communication (ISAC) systems with a bi-static radar, where the radar receiver is located close to the transmitter and estimates or detects the state based on the…

Segmentation for continuous Automatic Speech Recognition (ASR) has traditionally used silence timeouts or voice activity detectors (VADs), which are both limited to acoustic features. This segmentation is often overly aggressive, given that…

This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. The proposed NAR systems employ a Conformer encoder that applies connectionist…

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…

Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large…

Form about four decades human beings have been dreaming of an intelligent machine which can master the natural speech. In its simplest form, this machine should consist of two subsystems, namely automatic speech recognition (ASR) and speech…

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…

Cued Speech (CS) is an innovative visual communication system that integrates lip-reading with hand coding, designed to enhance effective communication for individuals with hearing impairments. Automatic CS Recognition (ACSR) refers to the…

Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw…

Speech emotion recognition (SER) is crucial for enhancing affective computing and enriching the domain of human-computer interaction. However, the main challenge in SER lies in selecting relevant feature representations from speech signals…

Speech enhancement (SE) systems are typically evaluated using a variety of instrumental metrics. The use of automatic speech recognition (ASR) systems to evaluate SE performance is common in literature, usually in terms of word error rate…

In this paper we explore continuous silent speech recognition using electroencephalography (EEG) signals. We implemented a connectionist temporal classification (CTC) automatic speech recognition (ASR) model to translate EEG signals…

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. Our approach uses a novel application of a…

An effective way to increase the noise robustness of automatic speech recognition is to label noisy speech features as either reliable or unreliable (missing) prior to decoding, and to replace the missing ones by clean speech estimates. We…

End-to-end learning models using raw waveforms as input have shown superior performances in many audio recognition tasks. However, most model architectures are based on convolutional neural networks (CNN) which were mainly developed for…

Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR). However, adjacent acoustic units (i.e., frames) are highly correlated, and…