Related papers: Double Multi-Head Attention for Speaker Verificati…
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…
This paper explores three novel approaches to improve the performance of speaker verification (SV) systems based on deep neural networks (DNN) using Multi-head Self-Attention (MSA) mechanisms and memory layers. Firstly, we propose the use…
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…
A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for…
Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a…
Speech Emotion Recognition (SER) research has faced limitations due to the lack of standard and sufficiently large datasets. Recent studies have leveraged pre-trained models to extract features for downstream tasks such as SER. This work…
Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…
End-to-end neural speaker diarization systems are able to address the speaker diarization task while effectively handling speech overlap. This work explores the incorporation of speaker information embeddings into the end-to-end systems to…
Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the…
Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker…
The recently proposed self-attentive pooling (SAP) has shown good performance in several speaker recognition systems. In SAP systems, the context vector is trained end-to-end together with the feature extractor, where the role of context…
In this paper, a hierarchical attention network to generate utterance-level embeddings (H-vectors) for speaker identification is proposed. Since different parts of an utterance may have different contributions to speaker identities, the use…
This paper describes the multi-query multi-head attention (MQMHA) pooling and inter-topK penalty methods which were first proposed in our submitted system description for VoxCeleb speaker recognition challenge (VoxSRC) 2021. Most multi-head…
In multi-speaker applications is common to have pre-computed models from enrolled speakers. Using these models to identify the instances in which these speakers intervene in a recording is the task of speaker tracking. In this paper, we…
Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…
This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the…
Current speaker diarization systems rely on an external voice activity detection model prior to speaker embedding extraction on the detected speech segments. In this paper, we establish that the attention system of a speaker embedding…
State-of-the-art transformer models for Speech Emotion Recognition (SER) rely on temporal feature aggregation, yet advanced pooling methods remain underexplored. We systematically benchmark pooling strategies, including Multi-Query…
In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers. Inspired by the recent success of deep neural networks (DNNs) in semantic inferencing, triplet…
We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including…