Speech & natural language publications

This work investigates the performance of traditional deep neural networks under varying acoustic conditions and evaluates their performance with speech recorded under realistic background conditions that are mismatched with respect…

This paper focuses on the problem of selecting the best-possible subset of available audio data given a budgeted time for annotation.

Using bottleneck features extracted from a deep neural network (DNN) trained to predict senone posteriors has resulted in new, state-of-the-art technology for language and speaker identification.

In this paper, we focus on a dataset of highly degraded signals, developed under the DARPA Robust Automatic Transcription of Speech (RATS) program.

We present the work done by our group for the 2015 language recognition evaluation (LRE) organized by the National Institute of Standards and Technology (NIST).

This study compares the effect of noise and reverberation on depression prediction using standard mel-frequency cepstral coefficients, and features designed for noise robustness, damped oscillator cepstral coefficients.

This paper introduces the MERL/SRI system designed for the 3rd CHiME speech separation and recognition challenge (CHiME-3). 

In this work, we explore the role of robust acoustic features motivated by human speech perception studies, for building ASR systems robust to reverberation effects.

This work presents a modified CDNN architecture that we call the time-frequency convolutional network (TFCNN), in which two parallel layers of convolution are performed on the input feature space: convolution…

This paper compares different approaches for using deep neural networks (DNNs) trained to predict senone posteriors for the task of spoken language recognition (SLR).