基于归一化流的隐马尔可夫模型的可解释语音音素分类
Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
摘要：
为了追求可解释性，我们开发了序列数据的生成模型。所提出的模型提供了最先进的分类结果和语音电话分类的鲁棒性能。我们结合了现代神经网络（规范化流）和传统的生成模型（隐马尔可夫模型-障碍）。使用基于流的归一化混合模型（NNDT）来对HNDT中给定隐藏状态的条件概率分布进行建模。模型参数是通过经过时间考验的贝叶斯学习方法和当代神经网络学习方法的明智组合来学习的。我们主要结合期望最大化（EM）和小批量梯度下降。所提出的生成模型可以计算数据的可能性，因此直接适用于最大似然（ML）分类方法。由于Hondry的结构灵活性，我们可以使用不同的归一化流模型。这导致了不同类型的Hacking提供了数据建模能力的多样性。多样性为不同模型的简单决策融合提供了机会。对于一个标准的语音电话分类设置，涉及39个电话（类）和TIMIT数据集，我们表明，使用标准的功能称为梅尔频率倒谱系数（MFCC），建议的生成模型，并决定融合在一起，可以实现$86.6\%$的准确性生成训练。该结果接近最先进的结果，例如PyTorch-Kaldi工具包的$86.2\%$准确度[1]和使用光选通递归单元的$85.1\%$准确度[2]。在本文中，我们没有使用任何判别式学习方法和相关的复杂功能。
英文摘要：
In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speech phone classification. We combine modern neural networks (normalizing flows) and traditional generative models (hidden Markov models - HMMs). Normalizing flow-based mixture models (NMMs) are used to model the conditional probability distribution given the hidden state in the HMMs. Model parameters are learned through judicious combinations of time-tested Bayesian learning methods and contemporary neural network learning methods. We mainly combine expectation-maximization (EM) and mini-batch gradient descent. The proposed generative models can compute likelihood of a data and hence directly suitable for maximum-likelihood (ML) classification approach. Due to structural flexibility of HMMs, we can use different normalizing flow models. This leads to different types of HMMs providing diversity in data modeling capacity. The diversity provides an opportunity for easy decision fusion from different models. For a standard speech phone classification setup involving 39 phones (classes) and the TIMIT dataset, we show that the use of standard features called mel-frequency-cepstral-coeffcients (MFCCs), the proposed generative models, and the decision fusion together can achieve $86.6\%$ accuracy by generative training only. This result is close to state-of-the-art results, for examples, $86.2\%$ accuracy of PyTorch-Kaldi toolkit [1], and $85.1\%$ accuracy using light gated recurrent units [2]. We do not use any discriminative learning approach and related sophisticated features in this article.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
