Related papers: Prosodic-Enhanced Siamese Convolutional Neural Net…

The ResNet-based architecture has been widely adopted to extract speaker embeddings for text-independent speaker verification systems. By introducing the residual connections to the CNN and standardizing the residual blocks, the ResNet…

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%…

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…

Neural vocoders are central to speech synthesis; despite their success, most still suffer from limited prosody modeling and inaccurate phase reconstruction. We propose a vocoder that introduces prosody-guided harmonic attention to enhance…

In this paper, we propose a noise robust bottleneck feature representation which is generated by an adversarial network (AN). The AN includes two cascade connected networks, an encoding network (EN) and a discriminative network (DN).…

While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been…

Modern sequence to sequence neural TTS systems provide close to natural speech quality. Such systems usually comprise a network converting linguistic/phonetic features sequence to an acoustic features sequence, cascaded with a neural…

This work proposes a novel support vector machine (SVM) based robust automatic speech recognition (ASR) front-end that operates on an ensemble of the subband components of high-dimensional acoustic waveforms. The key issues of selecting the…

Existing speaker verification (SV) systems often suffer from performance degradation if there is any language mismatch between model training, speaker enrollment, and test. A major cause of this degradation is that most existing SV methods…

Tacotron-based end-to-end speech synthesis has shown remarkable voice quality. However, the rendering of prosody in the synthesized speech remains to be improved, especially for long sentences, where prosodic phrasing errors can occur…

Speaker verification is to judge the similarity between two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small…

Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific…

Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications. However, mirroring the rise of deep learning in various domains, neural network based audio…

Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was…

This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as spoof embeddings. Building on established work in speaker…

Speaker Identification refers to the process of identifying a person using one's voice from a collection of known speakers. Environmental noise, reverberation and distortion make the task of automatic speaker identification challenging as…

Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel…

Speech Emotion Recognition (SER) affective technology enables the intelligent embedded devices to interact with sensitivity. Similarly, call centre employees recognise customers' emotions from their pitch, energy, and tone of voice so as to…