TIMIT

About: TIMIT is a research topic. Over the lifetime, 1401 publications have been published within this topic receiving 59888 citations. The topic is also known as: TIMIT Acoustic-Phonetic Continuous Speech Corpus.

Speech enhancement based on a combined multi-channel array with constrained iterative and auditory masked processing

Abstract: While a number of studies have investigated various speech enhancement and noise suppression schemes, most consider either a single channel or array processing framework. Clearly there are potential advantages in leveraging the strengths of array processing solutions in suppressing noise from a direction other than the speaker, with that seen in single channel methods that include speech spectral constraints or psychoacoustically motivated processing. In this paper, we propose to integrate a combined fixed/adaptive beamforming algorithm (CFA-BF) for speech enhancement with two single channel methods based on speech spectral constrained iterative processing (Auto-LSP), and an auditory masked threshold based method using equivalent rectangular bandwidth filtering (GMMSE-AMTERB). After formulating the method, we evaluate performance on a subset of the TIMIT corpus with four real noise sources. We demonstrate a consistent level of noise suppression and voice communication quality improvement using the proposed method as reflected by an overall average 26dB increase in SegSNR from the original degraded audio corpus.

Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks

Abstract: Ladder networks are a notable new concept in the field of semi-supervised learning by showing state-of-the-art results in image recognition tasks while being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the model is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.

Recognition of syllables in a continuous stream of speech by PARCOR parameters of linear predictive vocoder

Abstract: Linear predictive coding (LPC) has been used to compress and encode speech signals for digital transmission at a low bit rate. PARCOR parameter associated with LPC that represents a vocal tract model based on a lattice filter structure is considered for speech recognition. The use of FIR coefficients and the frequency response of AR model were previously investigated. This paper reports a method to detect syllables from a continuous stream of speech. The system being developed slides a time window of 20 ms and calculates the PARCOR parameters continuously, feeding them to a syllable classifier. The syllable classifier is a supervised classifier that requires training. The training uses TIMIT speech database, which contains the recordings of 630 speakers of 8 major dialects of American English. The voiced/unvoiced switch built into the LPC vocoder was modified to segment words included in the speech records. Preliminary results of classification are presented in the paper

Investigation of tandem deep belief network approach for phoneme recognition

Abstract: This paper proposes using tandem DBN approach - a hierarchical architecture that consists of two or more deep belief networks (DBNs) in tandem manner - for phoneme recognition task on TIMIT. First we describe the standard DBN approach applied in phoneme recognition and discuss the motivation of combining it with tandem classifier approach. We then perform series of experiments to find out the best configuration for the DBN in the second level and discover the full potential of this method. The experiments show that for the DBN in the second level, (a) 2048 units in each hidden layer is better than 1024 and 512 units, (b) for sufficient length of temporal context, two hidden layers are better, (c) the one gives best performance on development set shows 4% relative improvement on coretest set.

A novel neural-based pronunciation modeling method for robust speech recognition

Abstract: This paper describes a recurrent neural network (RNN) based articulatory-phonetic inversion (API) model for improved speech recognition. And a specialized optimization algorithm is introduced to enable human-like heuristic learning in an efficient data-driven manner to capture the dynamic nature of English speech pronunciations. The API model demonstrates superior pronunciation modeling ability and robustness against noise contaminations in large-vocabulary speech recognition experiments. Using a simple rescoring formula, it improves the hidden Markov model (HMM) baseline speech recognizer with consistent error rates reduction of 5.30% and 10.14% for phoneme recognition tasks on clean and noisy speech respectively on the selected TIMIT datasets. And an error rate reduction of 3.35% is obtained for the SCRIBE-TIMIT word recognition tasks. The proposed system qualifies as a competitive candidate for profound pronunciation modeling with intrinsic salient features such as generality and portability.