相关论文: Context-Dependent Acoustic Modeling without Explic…

The hidden Markov model (HMM) is a fundamental tool for sequence modeling that cleanly separates the hidden state from the emission structure. However, this separation makes it difficult to fit HMMs to large datasets in modern NLP, and they…

Deep LSTM is an ideal candidate for text recognition. However text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation,…

We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

This report describes a new technique for inducing the structure of Hidden Markov Models from data which is based on the general `model merging' strategy (Omohundro 1992). The process begins with a maximum likelihood HMM that directly…

Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training…

In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the difference in behavior…

Deep neural networks (DNNs) have achieved substantial predictive performance in various speech processing tasks. Particularly, it has been shown that a monaural speech separation task can be successfully solved with a DNN-based method…

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…

Pretrained language models have achieved state-of-the-art performance when adapted to a downstream NLP task. However, theoretical analysis of these models is scarce and challenging since the pretraining and downstream tasks can be very…

Unsupervised discovery of acoustic tokens from audio corpora without annotation and learning vector representations for these tokens have been widely studied. Although these techniques have been shown successful in some applications such as…

In recent years multilayer perceptrons (MLPs) with many hid- den layers Deep Neural Network (DNN) has performed sur- prisingly well in many speech tasks, i.e. speech recognition, speaker verification, speech synthesis etc. Although in the…

Translation models based on hierarchical phrase-based statistical machine translation (HSMT) have shown better performances than the non-hierarchical phrase-based counterparts for some language pairs. The standard approach to HSMT learns…

Machine learning algorithms such as linear regression, SVM and neural network have played an increasingly important role in the process of scientific discovery. However, none of them is both interpretable and accurate on nonlinear datasets.…

As the foundation of current natural language processing methods, pre-trained language model has achieved excellent performance. However, the black-box structure of the deep neural network in pre-trained language models seriously limits the…

State-of-the-art speech recognition systems typically employ neural network acoustic models. However, compared to Gaussian mixture models, deep neural network (DNN) based acoustic models often have many more model parameters, making it…

Deep neural models, particularly the LSTM-RNN model, have shown great potential for language identification (LID). However, the use of phonetic information has been largely overlooked by most existing neural LID methods, although this…

We propose to learn acoustic word embeddings with temporal context for query-by-example (QbE) speech search. The temporal context includes the leading and trailing word sequences of a word. We assume that there exist spoken word pairs in…

This paper presents an "elitist approach" for extracting automatically well-realized speech sounds with high confidence. The elitist approach uses a speech recognition system based on Hidden Markov Models (HMM). The HMM are trained on…

Speaker clustering is the task of differentiating speakers in a recording. In a way, the aim is to answer "who spoke when" in audio recordings. A common method used in industry is feature extraction directly from the recording thanks to…