Related papers: A New Method Towards Speech Files Local Features I…

Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users…

A new language model for speech recognition is presented. The model develops hidden hierarchical syntactic-like structure incrementally and uses it to extract meaningful information from the word history, thus complementing the locality of…

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…

Investigating linguistic relationships on a global scale requires analyzing diverse features such as syntax, phonology and prosody, which evolve at varying rates influenced by internal diversification, language contact, and sociolinguistic…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

Second-order statistical methods show very good results for automatic speaker identification in controlled recording conditions. These approaches are generally used on the entire speech material available. In this paper, we study the…

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in…

When comparing speech sounds across languages, scholars often make use of feature representations of individual sounds in order to determine fine-grained sound similarities. Although binary feature systems for large numbers of speech sounds…

Speaker verification is the process by which a speakers claim of identity is tested against a claimed speaker by his or her voice. Speaker verification is done by the use of some parameters (features) from the speakers voice which can be…

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…

Transformer-based speech recognition models have achieved great success due to the self-attention (SA) mechanism that utilizes every frame in the feature extraction process. Especially, SA heads in lower layers capture various phonetic…

In recent years several novel models were developed to process natural language, development of accurate language translation systems have helped us overcome geographical barriers and communicate ideas effectively. These models are…

This study explores the potential of using acoustic features of segmental speech sounds to detect deepfake audio. These features are highly interpretable because of their close relationship with human articulatory processes and are expected…

Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper…

In this paper we investigate a technique to find out vocal source based features from the LP residual of speech signal for automatic speaker identification. Autocorrelation with some specific lag is computed for the residual signal to…

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as…

Synthesized speech is common today due to the prevalence of virtual assistants, easy-to-use tools for generating and modifying speech signals, and remote work practices. Synthesized speech can also be used for nefarious purposes, including…

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice,…

(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…