Speaker: Elías Hernández Abstract: La prueba de ADN ha supuesto un gran avance en el contexto judicial y muchas veces es considerada como la prueba definitiva para condenar o absolver a un acusado. Los resultados de una prueba de ADN… Read More
Improving Fairness in Speaker Recognition
Speaker: Almudena Aguilera Abstract: Speaker Recognition Systems aim to automatically recognize the identity of an individual from a recording of his/her speech or voice. Despite the progress of these systems in terms of accuracy, we must ask ourselves: “What happen… Read More
Speech Enhancement for Wake-up Word detection in Voice Assistants
Speaker: William Fernando López Abstract: Wake-up-word (WuW) detection is a fundamental component in voice assistants. Undesired activation of the device is often due to external noises such as background conversations, TV or music. In Telefónica we have been working on… Read More
Unsupervised pre-training for learning speech representations: Wav2Vec and Wav2Vec2.0
Speaker: Laura Herrera Abstract: These papers (https://arxiv.org/pdf/1904.05862.pdf and https://arxiv.org/pdf/2006.11477.pdf) explore unsupervised learning from raw audio for speech recognition.A large amount of labelled data is not always available, consequently wav2vec uses a causal convolutional network trained with large amounts of unlabelled… Read More
Large-scale pre-training of End-to-End Multi-Talker ASR for meeting Transcription with Single Distant Microphone
Speaker: María Pilar Fernández Gallego Abstract: Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous studies… Read More
Selective Kernel Networks
Speaker: Sergio Segovia Abstract: It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in… Read More
Alicia Lozano Díez returns to UAM as Assistant Professor after almost two years in the prestigious research group Speech@FIT (Brno University of Technology, Czech Republic)
Alicia has made a postdoctoral research stay funded by the European Union under program H2020 Marie Slodowska-Curie Individual Fellowship. The project “Robust End-To-End SPEAKER recognition based on deep learning and attention models” (ETE SPEAKER, 843627) she has developed between 2019… Read More
Calibration of Multiclass Probabilistic Classifiers
Speaker: Sergio Márquez Abstract: Today’s Deep Neural Networks (DNNs) are used for numerous classification tasks, achieving high performance in terms of accuracy. In some cases, probabilistic classifiers, which assign a confidence value to each of the predictions made, are used.… Read More
Deep Learning Models with Self-Attention for the Detection of Audio Events
Speaker: Julio González Abstract: This talk is a presentation of the BsC Thesis “Modelos de aprendizajeprofundo con auto-atención para detección de eventos de audio”. Itdescribes the implementation of the Transformer and Conformer neuralnetworks and presents the results of the test… Read More
End-to-end Speaker Diarization
Speaker: Alicia Lozano Diez Abstract: In this talk, I will describe new approaches to the task of speaker diarization based on end-to-end neural networks, which present several advantages with respect to traditional systems based on clustering of speaker embeddings. I… Read More