Related papers: Revisiting MFCCs: Evidence for Spectral-Prosodic C…
Arabic dialect recognition presents a significant challenge in speech technology due to the linguistic diversity of Arabic and the scarcity of large annotated datasets, particularly for underrepresented dialects. This research investigates…
Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked…
Conversational Speech Synthesis (CSS) aims to generate speech with natural prosody by understanding the multimodal dialogue history (MDH). The latest work predicts the accurate prosody expression of the target utterance by modeling the…
Vocal disorders have affected several patients all over the world. Due to the inherent difficulty of diagnosing vocal disorders without sophisticated equipment and trained personnel, a number of patients remain undiagnosed. To alleviate the…
Despite the widely reported success of embedding-based machine learning methods on natural language processing tasks, the use of more easily interpreted engineered features remains common in fields such as cognitive impairment (CI)…
Encoding models provide a powerful framework for linking continuous stimulus features to neural activity; however, traditional voxelwise approaches are limited by measurement noise, inter-subject variability, and redundancy arising from…
The speech signal conveys information on different time scales from short time scale or segmental, associated to phonological and phonetic information to long time scale or supra segmental, associated to syllabic and prosodic information.…
Speaker verification aims to verify whether an input speech corresponds to the claimed speaker, and conventionally, this kind of system is deployed based on single-stream scenario, wherein the feature extractor operates in full frequency…
Most phoneme recognition state-of-the-art systems rely on a classical neural network classifiers, fed with highly tuned features, such as MFCC or PLP features. Recent advances in ``deep learning'' approaches questioned such systems, but…
Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and…
In audio signal processing, probabilistic time-frequency models have many benefits over their non-probabilistic counterparts. They adapt to the incoming signal, quantify uncertainty, and measure correlation between the signal's amplitude…
This Paper discusses the usefulness of the residual signal for speaker recognition. It is shown that the combination of both a measure defined over LPCC coefficients and a measure defined over the energy of the residual signal gives rise to…
As the most important human-machine interfacing tool, an insignificant amount of work has been carried out on Bangla Speech Recognition compared to the English language. Motivated by this, in this work, the performance of…
We propose a multi-objective framework to learn both secondary targets not directly related to the intended task of speech enhancement (SE) and the primary target of the clean log-power spectra (LPS) features to be used directly for…
Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations and using two sequence-to-sequence tasks to decouple TTS.…
It has been observed that an interesting class of non-Gaussian stationary processes is obtained when in the harmonics of a signal with random amplitudes and phases, frequencies can also vary randomly. In the resulting models, the…
We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal…
Spoken language understanding research to date has generally carried a heavy text perspective. Most datasets are derived from text, which is then subsequently synthesized into speech, and most models typically rely on automatic…
Speech deepfake detection (SDD) is essential for maintaining trust in voice-driven technologies and digital media. Although recent SDD systems increasingly rely on self-supervised learning (SSL) representations that capture rich contextual…
Complex-valued sparse coding is a data representation which employs a dictionary of two-dimensional subspaces, while imposing a sparse, factorial prior on complex amplitudes. When trained on a dataset of natural image patches, it learns…