Related papers: Deep multi-metric learning for text-independent sp…

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent years. However, accessing and controlling speech attributes such as speaker identity, prosody, and emotion in a text-to-speech system remains a challenge.…

The development of robust, multilingual speaker recognition systems is hindered by a lack of large-scale, publicly available and multilingual datasets, particularly for the read-speech style crucial for applications like anti-spoofing. To…

Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, prosody and long-term…

Zero-shot multi-speaker Text-to-Speech (TTS) generates target speaker voices given an input text and the corresponding speaker embedding. In this work, we investigate the effectiveness of the TTS reconstruction objective to improve…

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…

Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…

Automatic speech transcription and speaker recognition are usually treated as separate tasks even though they are interdependent. In this study, we investigate training a single network to perform both tasks jointly. We train the network in…

Motivated by unconsolidated data situation and the lack of a standard benchmark in the field, we complement our previous efforts and present a comprehensive corpus designed for training and evaluating text-independent multi-channel speaker…

When beginners learn to speak a non-native language, it is difficult for them to judge for themselves whether they are speaking well. Therefore, computer-assisted pronunciation training systems are used to detect learner mispronunciations.…

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Lately there have been novel developments in deep learning towards solving the cocktail party problem. Initial results are very promising and allow for more research in the domain. One technique that has not yet been explored in the neural…

In forensic applications, it is very common that only small naturalistic datasets consisting of short utterances in complex or unknown acoustic environments are available. In this study, we propose a pipeline solution to improve speaker…

We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

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…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Deep learning technology has been widely applied to speech enhancement. While testing the effectiveness of various network structures, researchers are also exploring the improvement of the loss function used in network training. Although…

Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2.0 (W2V2), have become the backbone of many speech tasks. In this paper, to achieve speaker diarisation and speech recognition using a single model, a…