This paper investigates data augmentation for deep neural network acoustic modeling based on label-preserving transformations to deal with data sparsity. Two data augmentation approaches, vocal tract length perturbation (VTLP) and stochastic feature mapping (SFM), are investigated for both deep neural networks (DNNs) and convolutional neural networks (CNNs). The approaches are focused on increasing speaker and speech variations of the limited training data such that the acoustic models trained with the augmented data are more robust to such variations. In addition, a two-stage data augmentation scheme based on a stacked architecture is proposed to combine VTLP and SFM as complementary approaches. Experiments are conducted on Assamese and Haitian Creole, two development languages of the IARPA Babel program, and improved performance on automatic speech recognition (ASR) and keyword search (KWS) is reported.

Data augmentation for deep neural network acoustic modeling

In this paper we present an algorithm that produces pitch and probability-of-voicing estimates for use as features in automatic speech recognition systems. These features give large performance improvements on tonal languages for ASR systems, and even substantial improvements for non-tonal languages. Our method, which we are calling the Kaldi pitch tracker (because we are adding it to the Kaldi ASR toolkit), is a highly modified version of the getf0 (RAPT) algorithm. Unlike the original getf0 we do not make a hard decision whether any given frame is voiced or unvoiced; instead, we assign a pitch even to unvoiced frames while constraining the pitch trajectory to be continuous. Our algorithm also produces a quantity that can be used as a probability of voicing measure; it is based on the normalized autocorrelation measure that our pitch extractor uses. We present results on data from various languages in the BABEL project, and show a large improvement over systems without tonal features and systems where pitch and POV information was obtained from SAcC or getf0.

/pdf/a-pitch-extraction-algorithm-tuned-for-automatic-speech-1jvxkhe8mo.pdf

A pitch extraction algorithm tuned for automatic speech recognition

This paper examines a query-by-example approach to spoken term detection in audio files. The approach is designed for low-resource situations in which limited or no in-domain training material is available and accurate word-based speech recognition capability is unavailable. Instead of using word or phone strings as search terms, the user presents the system with audio snippets of desired search terms to act as the queries. Query and test materials are represented using phonetic posteriorgrams obtained from a phonetic recognition system. Query matches in the test data are located using a modified dynamic time warping search between query templates and test utterances. Experiments using this approach are presented using data from the Fisher corpus.

Query-by-example spoken term detection using phonetic posteriorgram templates

Recently there has been increased interest in Automatic Speech Recognition (ASR) and Key Word Spotting (KWS) systems for low resource languages. One of the driving forces for this research direction is the IARPA Babel project. This paper describes some of the research funded by this project at Cambridge University, as part of the Lorelei team co-ordinated by IBM. A range of topics are discussed including: deep neural network based acoustic models; data augmentation; and zero acoustic model resource systems. Performance for all approaches is evaluated using the Limited (approximately 10 hours) and/or Full (approximately 80 hours) language packs distributed by IARPA. Both KWS and ASR performance figures are given. Though absolute performance varies from language to language, and keyword list, the approaches described show consistent trends over the languages investigated to date. Using comparable systems over the five Option Period 1 languages indicates a strong correlation between ASR performance and KWS performance.

/pdf/speech-recognition-and-keyword-spotting-for-low-resource-334xmaxzpo.pdf

Speech recognition and keyword spotting for low-resource languages : Babel project research at CUED

Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner.

paper presents the pilot evaluation of Spoken Term Detection technologies, held during the latter part of 2006. Spoken Term Detection systems rapidly detect the presence of a term , which is a sequence of words consecutively spoken, in a large audio corpus of heterogeneous speech material. The paper describes the evaluation task posed to Spoken Term Detection systems, the evaluation methodologies, the Arabic, English and Mandarin evaluation corpora, and the results of the evaluation. Ten participants submitted systems for the evaluation.

George Doddingtion

Papers

Results of the 2006 Spoken Term Detection Evaluation