Keith Levin

A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition

We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding zero resource (unsupervised) speech technologies and related models of early language acquisition. Centered around the tasks of phonetic and lexical discovery, we consider unified evaluation metrics, present two new approaches for improving speaker independence in the absence of supervision, and evaluate the application of Bayesian word segmentation algorithms to automatic subword unit tokenizations. Finally, we present two strategies for integrating zero resource techniques into supervised settings, demonstrating the potential of unsupervised methods to improve mainstream technologies.

Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings

Measures of acoustic similarity between words or other units are critical for segmental exemplar-based acoustic models, spoken term discovery, and query-by-example search. Dynamic time warping (DTW) alignment cost has been the most commonly used measure, but it has well-known inadequacies. Some recently proposed alternatives require large amounts of training data. In the interest of finding more efficient, accurate, and low-resource alternatives, we consider the problem of embedding speech segments of arbitrary length into fixed-dimensional spaces in which simple distances (such as cosine or Euclidean) serve as a proxy for linguistically meaningful (phonetic, lexical, etc.) dissimilarities. Such embeddings would enable efficient audio indexing and permit application of standard distance learning techniques to segmental acoustic modeling. In this paper, we explore several supervised and unsupervised approaches to this problem and evaluate them on an acoustic word discrimination task. We identify several embedding algorithms that match or improve upon the DTW baseline in low-resource settings.

Segmental acoustic indexing for zero resource keyword search

The task of zero resource query-by-example keyword search has received much attention in recent years as the speech technology needs of the developing world grow. These systems traditionally rely upon dynamic time warping (DTW) based retrieval algorithms with runtimes that are linear in the size of the search collection. As a result, their scalability substantially lags that of their supervised counterparts, which take advantage of efficient word-based indices. In this paper, we present a novel audio indexing approach called Segmental Randomized Acoustic Indexing and Logarithmic-time Search (S-RAILS). S-RAILS generalizes the original frame-based RAILS methodology to word-scale segments by exploiting a recently proposed acoustic segment embedding technique. By indexing word-scale segments directly, we avoid higher cost frame-based processing of RAILS while taking advantage of the improved lexical discrimination of the embeddings. Using the same conversational telephone speech benchmark, we demonstrate major improvements in both speed and accuracy over the original RAILS system.

Laplacian Eigenmaps From Sparse, Noisy Similarity Measurements

Manifold learning and dimensionality reduction techniques are ubiquitous in science and engineering, but can be computationally expensive procedures when applied to large datasets or when similarities are expensive to compute. To date, little work has been done to investigate the tradeoff between computational resources and the quality of learned representations. We present both theoretical and experimental explorations of this question. In particular, we consider Laplacian eigenmaps embeddings based on a kernel matrix, and explore how the embeddings behave when this kernel matrix is corrupted by occlusion and noise. Our main theoretical result shows that under modest noise and occlusion assumptions, we can (with high probability) recover a good approximation to the Laplacian eigenmaps embedding based on the uncorrupted kernel matrix. Our results also show how regularization can aid this approximation. Experimentally, we explore the effects of noise and occlusion on Laplacian eigenmaps embeddings of two real-world datasets, one from speech processing and one from neuroscience, as well as a synthetic dataset.

Accurate Low-Space Approximation of Metric k-Median for Insertion-Only Streams

We present a low-constant approximation for metric k-median on an insertion-only stream of n points using \(O(\epsilon ^{-3} k \log n)\) space. In particular, we present a streaming \((O(\epsilon ^{-3} k \log n), 2 + \epsilon )\)-bicriterion solution that reports cluster weights. It is well-known that running an offline algorithm on this bicriterion solution yields a \((17.66 + \epsilon )\)-approximation.