mlsanityData to 19 Oct 2026

Speaker Characterization by means of Attention Pooling

arXiv 2405.04096 ↗First posted 7 May 2024eess.AS cs.SDcited by 0

On the map: Speech and audio language models → Speaker recognition and diarization

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models. Builds on 14 of its 38 references that are in the map. First posted on arXiv 7 May 2024.

Builds on

14 of 38 references.

References · 14

  1. 2018VoxCeleb2: Deep Speaker Recognitioncited by 1,166
  2. 2017VoxCeleb: a large-scale speaker identification datasetcited by 985
  3. 2018Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition Systemcited by 79
  4. 2019Utterance-level Aggregation For Speaker Recognition In The Wildcited by 68
  5. 2017Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LMcited by 60
  6. 2019Large Margin Softmax Loss for Speaker Verificationcited by 59
  7. 2020x-vectors meet emotions: A study on dependencies between emotion and speaker recognitioncited by 45
  8. 2021The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primatescited by 33
  9. 2019Self Multi-Head Attention for Speaker Recognitioncited by 29
  10. 2020Detecting COVID-19 from Breathing and Coughing Sounds using Deep Neural Networkscited by 14
  11. 2017Language Identification Using Deep Convolutional Recurrent Neural Networkscited by 10
  12. 2017Towards Speech Emotion Recognition "in the wild" using Aggregated Corpora and Deep Multi-Task Learningcited by 7
2 more
  1. 2020Double Multi-Head Attention for Speaker Verificationcited by 6
  2. 2019Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verificationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
  2. 2025Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification
  3. 2024Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
  4. 2021Study on the temporal pooling used in deep neural networks for speaker verification
  5. 2022Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification
  6. 2022An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification
  7. 2021Poformer: A simple pooling transformer for speaker verification
  8. 2022Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning