RT info:eu-repo/semantics/article
T1 MeWEHV: Mel and Wave Embeddings for Human Voice Tasks
A1 Carofilis Vasco, Roberto Andrés
A1 Fernández Robles, Laura
A1 Alegre Gutiérrez, Enrique
A1 Fidalgo Fernández, Eduardo
A2 Ingenieria de Sistemas y Automatica
K1 Informática
K1 Ingeniería de sistemas
K1 Embeddings
K1 Hubert
K1 Speech classification
K1 WavLM
K1 XLSR-Wav2Vec2
K1 YouSpeakers204
K1 1203.04 Inteligencia Artificial
K1 3304.05 Sistemas de Reconocimiento de Caracteres
AB [EN] A recent trend in speech processing is the use of embeddings created through machine learning models trained on a specific task with large datasets. By leveraging the knowledge already acquired, these models can be reused in new tasks where the amount of available data is small. This paper proposes a pipeline to create a new model, called Mel and Wave Embeddings for Human Voice Tasks (MeWEHV), capable of generating robust embeddings for speech processing. MeWEHV combines the embeddings generated by a pre-trained raw audio waveform encoder model, and deep features extracted from Mel Frequency Cepstral Coefficients (MFCCs) using Convolutional Neural Networks (CNNs). We evaluate the performance of MeWEHV on three tasks: speaker, language, and accent identification. For the first one, we use the VoxCeleb1, and VBHIR datasets and present YouSpeakers204, a new and publicly available dataset for English speaker identification that contains 19607 audio clips from 204 persons speaking in six different accents, allowing other researchers to work with a very balanced dataset, and to create new models that are robust to multiple accents. For evaluating the language identification task, we use the VoxForge, Common Language, and the LRE17 datasets. Finally, for accent identification, we use the Latin American Spanish Corpora (LASC), Common Voice, and the NISP datasets. Our approach allows a significant increase in the performance of state-of-the-art embedding generation models on all the tested datasets, with a low additional computational cost.
PB Institute of Electrical and Electronics Engineers
LK https://hdl.handle.net/10612/19740
UL https://hdl.handle.net/10612/19740
NO Carofilis, A., Fernandez-Robles, L., Alegre, E., & Fidalgo, E. (2023). MeWEHV: Mel and Wave Embeddings for Human Voice Tasks. IEEE Access, 11, 80089-80104. https://doi.org/10.1109/ACCESS.2023.3300973
DS BULERIA. Repositorio Institucional de la Universidad de León
RD 07-jun-2024