Speaker Characterization by means of Attention Pooling
State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode variable-length utterances into fixed-length speaker vectors. The authors have recently proposed the use of a Double Multi-Head Self-Attention pooling for speaker recognition, placed between a CNN-based front-end and a set of fully connected layers. This has shown to be an excellent approach to efficiently select the most relevant features captured by the front-end from the speech signal. In this paper we show excellent experimental results by adapting this architecture to other different speaker characterization tasks, such as emotion recognition, sex classification and COVID-19 detection.
Code (0)
등록된 구현이 없습니다.
Tasks
Emotion RecognitionSpeaker RecognitionSpeaker VerificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Attentive Statistics Pooling for Deep Speaker Embedding
This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single u…
Speaker VerificationText-Independent Speaker VerificationDeep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
In this paper, gating mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, a gated convolution neural network (GCNN) is employed for modeling the f…
Speaker VerificationText-Independent Speaker VerificationSerialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utter…
Speaker VerificationText-Independent Speaker VerificationSelf Multi-Head Attention for Speaker Recognition
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 thos…
Speaker RecognitionTransport-Oriented Feature Aggregation for Speaker Embedding Learning
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 r…
Speaker Verification