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.

Unfolding speaker clustering potential: a biomimetic approach

Abstract: Speaker clustering is the task of grouping a set of speech utterances into speaker-specific classes. The basic techniques for solving this task are similar to those used for speaker verification and identification. The hypothesis of this paper is that the techniques originally developed for speaker verification and identification are not sufficiently discriminative for speaker clustering. However, the processing chain for speaker clustering is quite large - there are many potential areas for improvement. The question is: where should improvements be made to improve the final result? To answer this question, this paper takes a biomimetic approach based on a study with human participants acting as an automatic speaker clustering system. Our findings are twofold: it is the stage of modeling that has the highest potential, and information with respect to the temporal succession of frames is crucially missing. Experimental results with our implementation of a speaker clustering system incorporating our findings and applying it on TIMIT data show the validity of our approach.

Robust voice activity detection directed by noise classification

Abstract: In this paper voice activity detection (VAD) is formulated as a two-class classification problem using sup- port vector machines (SVM). The proposed method com- bines a noise robust speech processing feature extraction process together with SVM models trained in different back- ground noises for speech/non-speech classification. A multi- class SVM is also used to classify background noises in order to select SVM model for VAD. The proposed VAD is tested with TIMIT data artificially distorted by different additive noise types and is compared with state-of-the-art VADs. Experimental results show that the proposed VAD can extract speech activity under poor SNR conditions, and it is also insensitive to variable levels of noise.

Connectionist model combination for large vocabulary speech recognition

Abstract: Reports in the statistics and neural networks literature have expounded the benefits of merging multiple models to improve classification and prediction performance. The Cambridge University connectionist speech group has developed a hybrid connectionist-hidden Markov model system for large vocabulary talker independent speech recognition. The performance of this system has been greatly enhanced through the merging of connectionist acoustic models. This paper presents and compares a number of different approaches to connectionist model merging and evaluates them on the TIMIT phone recognition and ARPA Wall Street Journal word recognition tasks. >

Neural network based speaker classification and verification systems with enhanced features

Abstract: This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100% classification rate in classification and less than 6% Equal Error Rate (ERR), using merely about 1 second and 5 seconds of data respectively. Features with stricter Voice Active Detection (VAD) than the regular one for speech recognition ensure extracting stronger voiced portion for speaker recognition, speaker-level mean and variance normalization helps to eliminate the discrepancy between samples from the same speaker. Both are proven to improve the system performance. In building the neural network speaker classifier, the network structure parameters are optimized with grid search and dynamically reduced regularization parameters are used to avoid training terminated in local minimum. It enables the training goes further with lower cost. In speaker verification, performance is improved with prediction score normalization, which rewards the speaker identity indices with distinct peaks and penalizes the weak ones with high scores but more competitors, and speaker-specific thresholding, which significantly reduces ERR in the ROC curve. TIMIT corpus with 8K sampling rate is used here. First 200 male speakerwje used to train and test the classification performance. The testing files of them are used as in-domain registered speakers, while data from the remaining 126 male speakers are used as out-of-domain speakers, i.e. imposters in speaker verification.