W.D. Andrews

The area of automatic speaker recognition has been dominated by systems using only short-term, low-level acoustic information, such as cepstral features. While these systems have indeed produced very low error rates, they ignore other levels of information beyond low-level acoustics that convey speaker information. Recently published work has shown examples that such high-level information can be used successfully in automatic speaker recognition systems and has the potential to improve accuracy and add robustness. For the 2002 JHU CLSP summer workshop, the SuperSID project (http://www.clsp.jhu.edu/ws2002/groups/supersid/) was undertaken to exploit these high-level information sources and dramatically increase speaker recognition accuracy on a defined NIST evaluation corpus and task. The paper provides an overview of the structure, data, task, tools, and accomplishments of this project. Wide ranging approaches using pronunciation models, prosodic dynamics, pitch and duration features, phone streams, and conversational interactions were explored and developed. We show how these novel features and classifiers indeed provide complementary information and can be fused together to drive down the equal error rate on the 2001 NIST extended data task to 0.2% - a 71% relative reduction in error over the previous state of the art.

We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing spatial and temporal pooling, feature normalization, choice of CNN layers as well as choice of classifiers. Making judicious choices along these dimensions led to a very significant increase in performance over more naive approaches that have been used till now. We evaluate our approach on the challenging TRECVID MED'14 dataset with two popular CNN architectures pretrained on ImageNet. On this MED'14 dataset, our methods, based entirely on image-trained CNN features, can outperform several state-of-the-art non-CNN models. Our proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED'14 from 34.95% to 38.74%. The fusion approach achieves the state-of-the-art classification performance on the challenging UCF-101 dataset.

We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing spatial and temporal pooling, feature normalization, choice of CNN layers as well as choice of classifiers. Making judicious choices along these dimensions led to a very significant increase in performance over more naive approaches that have been used till now. We evaluate our approach on the challenging TRECVID MED'14 dataset with two popular CNN architectures pretrained on ImageNet. On this MED'14 dataset, our methods, based entirely on image-trained CNN features, can outperform several state-of-the-art non-CNN models. Our proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED'14 from 34.95% to 38.74%. The fusion approach achieves the state-of-the-art classification performance on the challenging UCF-101 dataset.

This paper describes improvements to an innovative high-performance speaker recognition system. Recent experiments showed that with sufficient training data phone strings from multiple languages are exceptional features for speaker recognition. The prototype phonetic speaker recognition system used phone sequences from six languages to produce an equal error rate of 11.5% on Switchboard-I audio files. The improved system described in this paper reduces the equal error rate to less then 4%. This is accomplished by incorporating gender-dependent phone models, pre-processing the speech files to remove cross-talk, and developing more sophisticated fusion techniques for the multi-language likelihood scores.

Recent work in phonetic speaker recognition has shown that modeling phone sequences using n-grams is a viable and effective approach to speaker recognition, primarily aiming at capturing speaker-dependent pronunciation and also word usage. The paper describes a method involving binary-tree-structured statistical models for extending the phonetic context beyond that of standard n-grams (particularly bigrams) by exploiting statistical dependencies within a longer sequence window without exponentially increasing the model complexity, as is the case with n-grams. Two ways of dealing with data sparsity are also studied; namely, model adaptation and a recursive bottom-up smoothing of symbol distributions. Results obtained under a variety of experimental conditions using the NIST 2001 Speaker Recognition Extended Data Task indicate consistent improvements in equal-error rate performance as compared to standard bigram models. The described approach confirms the relevance of long phonetic context in phonetic speaker recognition and represents an intermediate stage between short phone context and word-level modeling without the need for any lexical knowledge, which suggests its language independence.