arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.06950cs.CLcs.LG
收藏

一种完全无监督大词汇量语音识别的分段框架

A segmental framework for fully-unsupervised large-vocabulary speech recognition

School of Informatics, University of Edinburgh(爱丁堡大学信息学院);Google, Inc.(谷歌公司)

Herman Kamper, Aren Jansen, Sharon Goldwater

摘要:

零资源语音技术是一个不断发展的研究领域,其目的是在没有transmittance,词典或语言模型文本的情况下开发语音处理方法。早期的术语发现系统专注于识别语料库中孤立的重复模式,而最近的全覆盖系统试图将音频完全分割和聚类成类似单词的单元--有效地执行无监督的语音识别。本文介绍了第一次尝试,我们知道这样一个系统应用于大词汇量的多说话人数据。我们的系统使用贝叶斯建模框架与分段词表示:每个词段表示为一个固定的维度的声学嵌入,通过映射的特征帧序列到一个单一的嵌入向量。我们将我们的系统在英语和Xitsonga数据集上与最先进的基线进行比较,使用各种测量方法,包括单词出错率(通过将无监督输出映射到地面真实transmittance获得)。非常高的字出错率的报告--在70- 80%的顺序为发言者依赖和80- 95%的发言者无关的系统--突出了这项任务的难度。然而,在集群质量和分词指标方面,我们表明,通过实施一致的自上而下的分割,同时也使用自下而上的知识,从检测到的音节边界,单扬声器和多扬声器版本的系统优于一个纯粹的自下而上的单扬声器音节为基础的方法。我们还表明,所发现的集群可以通过使用无监督的自动编码器样的特征提取器来学习更好的帧级特征(在嵌入之前),从而减少说话者和性别的特定性。我们的系统发现的集群仍然不如那些无监督的长期发现系统纯,但提供更大的覆盖面。

英文摘要:

Zero-resource speech technology is a growing research area that aims to develop methods for speech processing in the absence of transcriptions, lexicons, or language modelling text. Early term discovery systems focused on identifying isolated recurring patterns in a corpus, while more recent full-coverage systems attempt to completely segment and cluster the audio into word-like units---effectively performing unsupervised speech recognition. This article presents the first attempt we are aware of to apply such a system to large-vocabulary multi-speaker data. Our system uses a Bayesian modelling framework with segmental word representations: each word segment is represented as a fixed-dimensional acoustic embedding obtained by mapping the sequence of feature frames to a single embedding vector. We compare our system on English and Xitsonga datasets to state-of-the-art baselines, using a variety of measures including word error rate (obtained by mapping the unsupervised output to ground truth transcriptions). Very high word error rates are reported---in the order of 70--80% for speaker-dependent and 80--95% for speaker-independent systems---highlighting the difficulty of this task. Nevertheless, in terms of cluster quality and word segmentation metrics, we show that by imposing a consistent top-down segmentation while also using bottom-up knowledge from detected syllable boundaries, both single-speaker and multi-speaker versions of our system outperform a purely bottom-up single-speaker syllable-based approach. We also show that the discovered clusters can be made less speaker- and gender-specific by using an unsupervised autoencoder-like feature extractor to learn better frame-level features (prior to embedding). Our system's discovered clusters are still less pure than those of unsupervised term discovery systems, but provide far greater coverage.

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。

↑