Related papers: Investigation of Deep Neural Network Acoustic Mode…

Mispronunciation Detection and Diagnosis (MDD) systems, leveraging Automatic Speech Recognition (ASR), face two main challenges in Mandarin Chinese: 1) The two-stage models create an information gap between the phoneme or tone…

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish…

A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are…

Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the…

Most natural language processing systems based on machine learning are not robust to domain shift. For example, a state-of-the-art syntactic dependency parser trained on Wall Street Journal sentences has an absolute drop in performance of…

The problem of automatic accent identification is important for several applications like speaker profiling and recognition as well as for improving speech recognition systems. The accented nature of speech can be primarily attributed to…

This paper presents AMNet, an Acoustic Model Network designed to improve the performance of Mandarin speech synthesis by incorporating phrase structure annotation and local convolution modules. AMNet builds upon the FastSpeech 2…

Hidden Markov Model (HMM) is often regarded as the dynamical model of choice in many fields and applications. It is also at the heart of most state-of-the-art speech recognition systems since the 70's. However, from Gaussian mixture models…

This paper summarizes the work done by the authors for the Zero Resource Speech Challenge organized in the technical program of Interspeech 2015. The goal of the challenge is to discover linguistic units directly from unlabeled speech data.…

Multilingual speech recognition has drawn significant attention as an effective way to compensate data scarcity for low-resource languages. End-to-end (e2e) modelling is preferred over conventional hybrid systems, mainly because of no…

Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual…

Deep Neural Network--Hidden Markov Model (DNN-HMM) based methods have been successfully used for many always-on keyword spotting algorithms that detect a wake word to trigger a device. The DNN predicts the state probabilities of a given…

Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…

Despite the significant progress made in the last years, state-of-the-art speech recognition technologies provide a satisfactory performance only in the close-talking condition. Robustness of distant speech recognition in adverse acoustic…

In this paper, we present several adaptation methods for non-native speech recognition. We have tested pronunciation modelling, MLLR and MAP non-native pronunciation adaptation and HMM models retraining on the HIWIRE foreign accented…

A significant performance reduction is often observed in speech recognition when the rate of speech (ROS) is too low or too high. Most of present approaches to addressing the ROS variation focus on the change of speech signals in dynamic…

This paper demonstrates two novel methods to estimate the global SNR of speech signals. In both methods, Deep Neural Network-Hidden Markov Model (DNN-HMM) acoustic model used in speech recognition systems is leveraged for the additional…

It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target domain. Recently, Deep Neural Network (DNN) has become a…

In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…

The most recent deep neural network (DNN) models exhibit impressive denoising performance in the time-frequency (T-F) magnitude domain. However, the phase is also a critical component of the speech signal that is easily overlooked. In this…