Kenneth Church

Learn More
The spoken term discovery task takes speech as input and identifies terms of possible interest. The challenge is to perform this task efficiently on large amounts of speech with zero resources (no training data and no dictionaries), where we must fall back to more basic properties of language. We find that long (∼ 1 s) repetitions tend to be contentful(More)
Can we automatically discover speaker independent phonemelike subword units with zero resources in a surprise language? There have been a number of recent efforts to automatically discover repeated spoken terms without a recognizer. This paper investigates the feasibility of using these results as constraints for unsupervised acoustic model training. We(More)
We propose a new technique for training deep neural networks (DNNs) as data-driven feature front-ends for large vocabulary continuous speech recognition (LVCSR) in low resource settings. To circumvent the lack of sufficient training data for acoustic modeling in these scenarios, we use transcribed multilingual data and semi-supervised training to build the(More)
Very large data centers are very expensive (servers, power/cooling, networking, physical plant.) Newer, geo-diverse, distributed or containerized designs offer a more economical alternative. We argue that a significant portion of cloud services are embarrassingly distributed – meaning there are high performance realizations that do not require massive(More)
In this paper, we present strategies to incorporate long context information directly during the first pass decoding and also for the second pass lattice re-scoring in speech recognition systems. Long-span language models that capture complex syntactic and/or semantic information are seldom used in the first pass of large vocabulary continuous speech(More)
What is a multiword expression (MWE) and how many are there? Mark Liberman gave a great invited talk at ACL-89, titled “How Many Words Do People Know?” where he spent the entire hour questioning the question. Many of the same questions apply to multiword expressions. What is a word? An expression? What is many? What(More)
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(More)
A re-scoring strategy is proposed that makes it feasible to capture more long-distance dependencies in the natural language. Two pass strategies have become popular in a number of recognition tasks such as ASR (automatic speech recognition), MT (machine translation) and OCR (optical character recognition). The first pass typically applies a weak language(More)
We consider the problem of predicting the probability of a click for an advertisement when the outcome of a click or no-click is expressed by means of a set of a large number of variables. Many, if not most, of these variables are very weakly related to the clicking of the ad. Thus, a traditional approach to address this problem that treats each variable on(More)