Topic
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.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: This paper compared two methods for structural classification with the WFST-based features; the structured perceptron and conditional random field (CRF) techniques and confirmed that the proposed approach improved the ASR performance without sacrificing the computational efficiency of the decoders.
Abstract: The potential of structural classification methods for automatic speech recognition (ASR) has been attracting the speech community since they can realize the unified modeling of acoustic and linguistic aspects of recognizers. However, the structural classification approaches involve well-known tradeoffs between the richness of features and the computational efficiency of decoders. If we are to employ, for example, a frame-synchronous one-pass decoding technique, features considered to calculate the likelihood of each hypothesis must be restricted to the same form as the conventional acoustic and language models. This paper tackles this limitation directly by exploiting the structure of the weighted finite-state transducers (WFSTs) used for decoding. Although WFST arcs provide rich contextual information, close integration with a computationally efficient decoding technique is still possible since most decoding techniques only require that their likelihood functions are factorizable for each decoder arc and time frame. In this paper, we compare two methods for structural classification with the WFST-based features; the structured perceptron and conditional random field (CRF) techniques. To analyze the advantages of these two classifiers, we present experimental results for the TIMIT continuous phoneme recognition task, the WSJ transcription task, and the MIT lecture transcription task. We confirmed that the proposed approach improved the ASR performance without sacrificing the computational efficiency of the decoders, even though the baseline systems are already trained with discriminative training techniques (e.g., MPE).
9 citations
••
TL;DR: This paper proposes a novel method to obtain discriminative feature transformation based on output coding technique for speech recognition and shows that the proposed features achieve 10.5% ASR error rate reduction over the conventional spectral features.
9 citations
••
19 Sep 2018TL;DR: A novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass is proposed and its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches is shown.
Abstract: We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each \(1 \le k \le k_\mathrm {max}\), a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this “learning to cluster” and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.
9 citations
•
TL;DR: An extension of multi-teacher distillation methods to joint CTC-attention end-to-end ASR systems is proposed and three novel distillation strategies are introduced to integrate the error rate metric to the teacher selection rather than solely focusing on the observed losses.
Abstract: Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from ensembles of acoustic models has recently shown promising results in increasing recognition performance. In this paper, we propose an extension of multi-teacher distillation methods to joint CTC-attention end-to-end ASR systems. We also introduce three novel distillation strategies. The core intuition behind them is to integrate the error rate metric to the teacher selection rather than solely focusing on the observed losses. In this way, we directly distill and optimize the student toward the relevant metric for speech recognition. We evaluate these strategies under a selection of training procedures on different datasets (TIMIT, Librispeech, Common Voice) and various languages (English, French, Italian). In particular, state-of-the-art error rates are reported on the Common Voice French, Italian and TIMIT datasets.
9 citations
••
TL;DR: Experimental results show that the proposed method can extract appropriate i-vector which reduces the equal error rate (EER) and improve the accuracy of voice authentication system in clean and noisy environment.
Abstract: Recently, the accuracy of voice authentication system has increased significantly due to the successful application of the identity vector (i-vector) model. This paper proposes a new method for i-vector extraction. In the method, a perceptual wavelet packet transform (PWPT) is designed to convert speech utterances into wavelet entropy feature vectors, and a Convolutional Neural Network (CNN) is designed to estimate the frame posteriors of the wavelet entropy feature vectors. In the end, i-vector is extracted based on those frame posteriors. TIMIT and VoxCeleb speech corpus are used for experiments and the experimental results show that the proposed method can extract appropriate i-vector which reduces the equal error rate (EER) and improve the accuracy of voice authentication system in clean and noisy environment.
9 citations