Speech Dictionary Research Articles

Examples of expressive prefixation - in the dialectal material of the Banjani, Grahovo and Oputne Rudine Speech

Expressive prefixes are a specific word-formation category, unknown in synchronic derivatology. It is about word-formation elements which are essentially prefixes, but which are not recognised as such in the structure of the word. They can be isolated only by word-formation and etymological analysis. In the present paper, this category is studied within the context of dialectal material provided by J. K. Koprivica?s Dictionary of the Banjani, Grahovo and Oputne Rudine Speech. It is concluded that the examined speech contains a considerable number of expressively prefixed forms. Many of them have developed word families (e.g. ceprljati ?to dig, scratch?, comrgiti se ?to frown?, kovrijeziti se ?to be angry?, kovrljati ?to roll?, koprciti se ?to show off, boast?, temezgati ?to be slow, sluggish?, totrciti se ?to swagger?), which testifies to their full integration into the lexical system of language and high frequency of use. The analysed material corroborates the statement that the expressive preverbs are a ?productive? word-formation category in the Serbian language.

Unseen Noise Estimation Using Separable Deep Auto Encoder for Speech Enhancement

Unseen noise estimation is a key yet challenging step to make a speech enhancement algorithm work in adverse environments. At worst, the only prior knowledge we know about the encountered noise is that it is different from the involved speech. Therefore, by subtracting the components which cannot be adequately represented by a well defined speech model, the noises can be estimated and removed. Given the good performance of deep learning in signal representation, a deep auto encoder (DAE) is employed in this work for accurately modeling the clean speech spectrum. In the subsequent stage of speech enhancement, an extra DAE is introduced to represent the residual part obtained by subtracting the estimated clean speech spectrum (by using the pre-trained DAE) from the noisy speech spectrum. By adjusting the estimated clean speech spectrum and the unknown parameters of the noise DAE, one can reach a stationary point to minimize the total reconstruction error of the noisy speech spectrum. The enhanced speech signal is thus obtained by transforming the estimated clean speech spectrum back into time domain. The above proposed technique is called separable deep auto encoder (SDAE). Given the under-determined nature of the above optimization problem, the clean speech reconstruction is confined in the convex hull spanned by a pre-trained speech dictionary. New learning algorithms are investigated to respect the non-negativity of the parameters in the SDAE. Experimental results on TIMIT with 20 noise types at various noise levels demonstrate the superiority of the proposed method over the conventional baselines.

Speech Enhancement Under Low SNR Conditions Via Noise Estimation Using Sparse and Low-Rank NMF with Kullback–Leibler Divergence

A key stage in speech enhancement is noise estimation which usually requires prior models for speech or noise or both. However, prior models can sometimes be difficult to obtain. In this paper, without any prior knowledge of speech and noise, sparse and low-rank nonnegative matrix factorization (NMF) with Kullback-Leibler divergence is proposed to noise and speech estimation by decomposing the input noisy magnitude spectrogram into a low-rank noise part and a sparse speech-like part. This initial unsupervised speech-noise estimation allows us to set a subsequent regularized version of NMF or convolutional NMF to reconstruct the noise and speech spectrogram, either by estimating a speech dictionary on the fly (categorized as unsupervised approaches) or by using a pre-trained speech dictionary on utterances with disjoint speakers (categorized as semi-supervised approaches). Information fusion was investigated by taking the geometric mean of the outputs from multiple enhancement algorithms. The performance of the algorithms were evaluated on five metrics (PESQ, SDR, SNR, STOI, and OVERALL) by making experiments on TIMIT with 15 noise types. The geometric means of the proposed unsupervised approaches outperformed spectral subtraction (SS), minimum mean square estimation (MMSE) under low input SNR conditions. All the proposed semi-supervised approaches showed superiority over SS and MMSE and also obtained better performance than the state-of-the-art algorithms which utilized a prior noise or speech dictionary under low SNR conditions.

Spectrum enhancement with sparse coding for robust speech recognition

Recently, a trend in speech recognition is to introduce sparse coding for noise robustness. Although several methods have been proposed, the performance of sparse coding in speech denoising is not so optimistic. One assumption with sparse coding is that the representation of speech over the speech dictionary is sparse, while that of the noise is dense. This assumption is obviously not sustained in the speech denoising scenario. Many noises are also sparse over the speech dictionary. In such a condition, the representation of noisy speech still contains noise components, resulting in degraded performance. To solve this problem, we first analyze the assumption of sparse coding and then propose a novel method to enhance speech spectrum. This method first finds out the atoms which represent the noise sparsely, and then selectively ignores them in the reconstruction of speech to reduce the residual noise. Speech features are then extracted from the enhanced spectrum for speech recognition. Experimental results show that the proposed method can improve the noise robustness of a speech recognition system substantially.

Voice Activity Detection Via Noise Reducing Using Non-Negative Sparse Coding

This letter presents a voice activity detection (VAD) approach using non-negative sparse coding to improve the detection performance in low signal-to-noise ratio (SNR) conditions. The basic idea is to use features extracted from a noise-reduced representation of original audio signals. We decompose the magnitude spectrum of an audio signal on a speech dictionary learned from clean speech and a noise dictionary learned from noise samples. Only coefficients corresponding to the speech dictionary are considered and used as the noise-reduced representation of the signal for feature extraction. A conditional random field (CRF) is used to model the correlation between feature sequences and voice activity labels along audio signals. Then, we assign the voice activity labels for a given audio by decoding the CRF. Experimental results demonstrate that our VAD approach has a good performance in low SNR conditions.

Speech Enhancement Using Generative Dictionary Learning

The enhancement of speech degraded by real-world interferers is a highly relevant and difficult task. Its importance arises from the multitude of practical applications, whereas the difficulty is due to the fact that interferers are often nonstationary and potentially similar to speech. The goal of monaural speech enhancement is to separate a single mixture into its underlying clean speech and interferer components. This under-determined problem is solved by incorporating prior knowledge in the form of learned speech and interferer dictionaries. The clean speech is recovered from the degraded speech by sparse coding of the mixture in a composite dictionary consisting of the concatenation of a speech and an interferer dictionary. Enhancement performance is measured using objective measures and is limited by two effects. A too sparse coding of the mixture causes the speech component to be explained with too few speech dictionary atoms, which induces an approximation error we denote source distortion. However, a too dense coding of the mixture results in source confusion, where parts of the speech component are explained by interferer dictionary atoms and vice-versa. Our method enables the control of the source distortion and source confusion trade-off, and therefore achieves superior performance compared to powerful approaches like geometric spectral subtraction and codebook-based filtering, for a number of challenging interferer classes such as speech babble and wind noise.

Speech synthesis using multi-mode coding with a speech segment dictionary

Speech segment data are encoded in accordance with their respective optimum encoding schemes. The speech segment data thus encoded are registered in a speech segment dictionary along with information specifying the encoding methods used in the encoding.

Voice synthesizing method and voice synthesizer performing the same

A stereotypical sentence is synthesized into a voice of an arbitrary speech style. A third party is able to prepare prosody data and a user of a terminal device having a voice synthesizing part can acquire the prosody data. The voice synthesizing method determines a voice-contents identifier to point to a type of voice contents of a stereotypical sentence, prepares a speech style dictionary including speech style and prosody data which correspond to the voice-contents identifier, selects prosody data of the synthesized voice to be generated from the speech style dictionary, and adds the selected prosody data to a voice synthesizer 13 as voice-synthesizer driving data to thereby perform voice synthesis with a specific speech style. Thus, a voice of a stereotypical sentence can be synthesized with an arbitrary speech style.

A Dictionary ofSpeech Pathology and Therapy, by Samuel D Robbins, London, Peter Owen, 1962, 112 PP. 30s.

A Dictionary ofSpeech Pathology and Therapy, by Samuel D Robbins, London, Peter Owen, 1962, 112 PP. 30<i>s</i>.

Tulu Prose Texts in Two Dialects.

I. Tuḷuva, a Dravidian speech spoken by about 400,000 people within a comparatively small area in the district of south Kanara, on the west coast of Madras Presidency, has preserved its individuality from a very early time, despite its being an uncultivated dialect with no literature of its own. The Mangalore missionaries were the first to reduce this unwritten language to writing, and they published in the closing decades of the last century a grammar and a dictionary of this speech, besides a few scriptural texts. An attempt is now being made by educated Tuḵuvas to cultivate their mother tongue as a literary speech through the composition of essays, stories, and poems.