相关论文: On Feature Importance and Interpretability of Spea…

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…

Many neural network speaker recognition systems model each speaker using a fixed-dimensional embedding vector. These embeddings are generally compared using either linear or 2nd-order scoring and, until recently, do not handle…

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features correlated with…

An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance…

An important step in speaker verification is extracting features that best characterize the speaker voice. This paper investigates a front-end processing that aims at improving the performance of speaker verification based on the SVMs…

The popular i-vector model represents speakers as low-dimensional continuous vectors (i-vectors), and hence it is a way of continuous speaker embedding. In this paper, we investigate binary speaker embedding, which transforms i-vectors to…

Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but…

In this work we revisit discriminative training of the i-vector extractor component in the standard speaker verification (SV) system. The motivation of our research lies in the robustness and stability of this large generative model, which…

Prosody modeling is important, but still challenging in expressive voice conversion. As prosody is difficult to model, and other factors, e.g., speaker, environment and content, which are entangled with prosody in speech, should be removed…

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully…

Speech time reversal refers to the process of reversing the entire speech signal in time, causing it to play backward. Such signals are completely unintelligible since the fundamental structures of phonemes and syllables are destroyed.…

Disentanglement-based speaker anonymization involves decomposing speech into a semantically meaningful representation, altering the speaker embedding, and resynthesizing a waveform using a neural vocoder. State-of-the-art systems of this…

With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of…

This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker. Speech rhythm is one of the essential factors among speaker characteristics, along with acoustic…

Recent studies have shown that frame-level deep speaker features can be derived from a deep neural network with the training target set to discriminate speakers by a short speech segment. By pooling the frame-level features, utterance-level…

In the highly constrained context of low-resource language studies, we explore vector representations of speech from a pretrained model to determine their level of abstraction with regard to the audio signal. We propose a new unsupervised…

Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information…

Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware speaker embeddings…

Disentangled representation learning aims to extract explanatory features or factors and retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents a way to disentangle a speech signal into sequential-level…

This paper presents an end-to-end text-independent speaker verification framework by jointly considering the speaker embedding (SE) network and automatic speech recognition (ASR) network. The SE network learns to output an embedding vector…