Speaker embeddings achieve promising results on many speaker verification tasks.
Phonetic information, as an important component of speech, is rarely considered in the …

Although researchers have proposed numerous techniques for speech emotion recognition,
its performance remains unsatisfactory in many application scenarios. In this study, we …

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging
unlabelled utterances, due to the classification loss over training speakers. In this paper, we …

Sound classification is a task to classify sounds into different classes. In earlier days, the
researchers mainly used conventional machine learning techniques to classify sounds. In …

Factorizing speech as disentangled speech representations is vital to achieve highly
controllable style transfer in voice conversion (VC). Conventional speech representation …

Deep speaker embedding has demonstrated state-of-the-art performance in speaker
recognition tasks. However, one potential issue with this approach is that the speaker …

Variations of speech content increase the difficulty of speaker verification. In this paper, to
alleviate the negative effect of the variations, phoneme-unit-specific time-delay neural …

Voice conversion has made great progress in the past few years under the studio-quality test
scenario in terms of speech quality and speaker similarity. However, in real applications, test …

Speech content is closely related to the stability of speaker embeddings in speaker
verification tasks. In this paper, we propose a novel architecture based on self-constraint …

Speech disentanglement aims to decompose independent causal factors of speech signals
into separate codes. Perfect disentanglement benefits to a broad range of speech …