2013年12月12日 · Deep Neural Network Hidden Markov Models, or DNN-HMMs, are recently very promising acoustic models achieving good speech recognition results over Gaussian mixture model based HMMs (GMM-HMMs). In this paper, for emotion recognition from speech, we investigate DNN-HMMs with restricted Boltzmann Machine (RBM) based unsupervised pre-training, and DNN-HMMs with discriminative pre-training. Emotion ...

2022年8月25日 · 而 DNN-HMM 系统利用 DNN 很强的表现 学习 能力，再配合 HMM 的系列化建模能力，在很多大规模 语音识别 任务中都超过了GMM 模型。 下图给出一个 DNN-HMM 系统的结构图。 在这个框架中， HMM 用来描述语音信号的动态变化，用... AI大语音（十 …

2014年11月12日 · In this chapter, we describe one of the several possible ways of exploiting deep neural networks (DNNs) in automatic speech recognition systems—the deep neural network-hidden Markov model (DNN-HMM) hybrid system. The …

deep neural network-hidden Markov model (DNN-HMM) hybrid system. The DNN-HMM hybrid system takes advantage of DNN’s strong representation learn-ing power and HMM’s sequential modeling ability, and outperforms conventional Gaussian …

标签可以通过GMM-HMM在训练语料上进行 Viterbi 强制对齐得到。 利用标签和输入特征训练DNN模型，用DNN模型替换GMM进行观察概率的计算，保留转移概率和初始概率等其他部分。

We address this loss-metric mismatch with a novel end-to-end training strategy that learns the DNN parameters by optimizing for the detection score. To this end, we make the HMM decoder (dynamic programming) differentiable and back-propagate through it to maximize the score for the keyword and minimize the scores for non-keyword speech segments.

其中状态序列使用HMM进行建模，相关原理介绍详见 《隐马尔科夫模型（HMM），一个不可被忽视的统计学习模型||语音识别中的HMM》，而输出概率使用高斯混合模型GMM建模，如下图所示：

A pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output that can significantly outperform the conventional context-dependent …

This paper takes CD-DNN-HMM based recognition into a real-life deployment for audio indexing. We find that for our best speaker-independent CD-DNN-HMM, with 32k senones trained on 2000h of data, the one-fourth reduction does carry over to …

nd signal enhancement. We show that the recognition accuracy of the DNN-HMM hybrid system improves by incorporating uncertainty decoding based on random sampling and that the proposed weighted DNN-output averaging further reduces the