O5 - Oral Session: Robustness in Automatic Speech Recognition

Date: Friday, 23 November

Hour: 9:00 - 10:40

Location: Building C, Sala de Grados.

Chairperson: Ascensión Gallardo Antolín.

O5-1: A robust pitch extractor based on DTW lines and CASA with application in noisy speech recognition, Juan Morales Cordovilla, Pablo Cabañas-Molero, Antonio Miguel Peinado Herreros, and Victoria Eugenia Sánchez Calle

O5-2: Speech Denoising Using Non-Negative Matrix Factorization with Kullback-Leibler Divergence and Sparseness Constraints, Jimmy Ludeña Choez and Ascensión Gallardo Antolín

O5-3: MMSE feature reconstruction based on an occlusion model for robust ASR, Jose Gonzalez, Antonio Miguel Peinado Herreros, and Angel Gomez

O5-4: Automatic Speech Recognition based on Ultrasonic Doppler Sensing for European Portuguese, João Freitas, António Teixeira, Francisco Vaz, and Miguel Dias

O5-5: Pairwise Likelihood Normalization-Based Channel Selection for Multi-Microphone ASRMartin Wolf and Climent Nadeu Camprubi


Additional information