http://hdl.handle.net/1842/3763 2013-05-22T11:39:52Z 2013-05-22T11:39:52Z King, Simon Tokuda, Keiichi Zen, Heiga Yamagishi, Junichi http://hdl.handle.net/1842/3841 2013-04-09T13:07:47Z 2008-09-01T00:00:00Z

Title: Unsupervised adaptation for HMM-based speech synthesis Authors: King, Simon; Tokuda, Keiichi; Zen, Heiga; Yamagishi, Junichi Abstract: It is now possible to synthesise speech using HMMs with a comparable quality to unit-selection techniques. Generating speech from a model has many potential advantages over concatenating waveforms. The most exciting is model adaptation. It has been shown that supervised speaker adaptation can yield high- quality synthetic voices with an order of magnitude less data than required to train a speaker-dependent model or to build a basic unit-selection system. Such supervised methods require labelled adaptation data for the target speaker. In this paper, we introduce a method capable of unsupervised adaptation, using only speech from the target speaker without any labelling.

2008-09-01T00:00:00Z Bell, Peter King, Simon http://hdl.handle.net/1842/3839 2010-10-05T12:45:15Z 2008-01-01T00:00:00Z

Title: A Shrinkage Estimator for Speech Recognition with Full Covariance HMMs Authors: Bell, Peter; King, Simon Abstract: We consider the problem of parameter estimation in full-covariance Gaussian mixture systems for automatic speech recognition. Due to the high dimensionality of the acoustic feature vector, the standard sample covariance matrix has a high variance and is often poorly-conditioned when the amount of training data is limited. We explain how the use of a shrinkage estimator can solve these problems, and derive a formula for the optimal shrinkage intensity. We present results of experiments on a phone recognition task, showing that the estimator gives a performance improvement over a standard full-covariance system

2008-01-01T00:00:00Z Toth, Laszlo Frankel, Joe Gosztolya, Gabor King, Simon http://hdl.handle.net/1842/3838 2010-10-05T12:43:37Z 2008-01-01T00:00:00Z

Title: Cross-lingual Portability of MLP-Based Tandem Features -- A Case Study for English and Hungarian Authors: Toth, Laszlo; Frankel, Joe; Gosztolya, Gabor; King, Simon Abstract: One promising approach for building ASR systems for less-resourced languages is cross-lingual adaptation. Tandem ASR is particularly well suited to such adaptation, as it includes two cascaded modelling steps: feature extraction using multi-layer perceptrons (MLPs), followed by modelling using a standard HMM. The language-specific tuning can be performed by adjusting the HMM only, leaving the MLP untouched. Here we examine the portability of feature extractor MLPs between an Indo-European (English) and a Finno-Ugric (Hungarian) language. We present experiments which use both conventional phone-posterior and articulatory feature (AF) detector MLPs, both trained on a much larger quantity of (English) data than the monolingual (Hungarian) system. We find that the cross-lingual configurations achieve similar performance to the monolingual system, and that, interestingly, the AF detectors lead to slightly worse performance, despite the expectation that they should be more language-independent than phone-based MLPs. However, the cross-lingual system outperforms all other configurations when the English phone MLP is adapted on the Hungarian data.

2008-01-01T00:00:00Z Wang, Dong Frankel, Joe Tejedor, Javier King, Simon http://hdl.handle.net/1842/3837 2010-10-05T12:43:27Z 2008-01-01T00:00:00Z

Title: A comparison of phone and grapheme-based spoken term detection Authors: Wang, Dong; Frankel, Joe; Tejedor, Javier; King, Simon Abstract: We propose grapheme-based sub-word units for spoken term detection (STD). Compared to phones, graphemes have a number of potential advantages. For out-of-vocabulary search terms, phone- based approaches must generate a pronunciation using letter-to-sound rules. Using graphemes obviates this potentially error-prone hard decision, shifting pronunciation modelling into the statistical models describing the observation space. In addition, long-span grapheme language models can be trained directly from large text corpora. We present experiments on Spanish and English data, comparing phone and grapheme-based STD. For Spanish, where phone and grapheme-based systems give similar transcription word error rates (WERs), grapheme-based STD significantly outperforms a phone- based approach. The converse is found for English, where the phone-based system outperforms a grapheme approach. However, we present additional analysis which suggests that phone-based STD performance levels may be achieved by a grapheme-based approach despite lower transcription accuracy, and that the two approaches may usefully be combined. We propose a number of directions for future development of these ideas, and suggest that if grapheme-based STD can match phone-based performance, the inherent flexibility in dealing with out-of-vocabulary terms makes this a desirable approach.

2008-01-01T00:00:00Z