基于析因语音处理模型的单耳多人语音识别
Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models
摘要：
提出了一个Pascal挑战，题目是单耳多说话者语音识别，目标是针对明显降低自动语音识别系统性能的类语音噪声的鲁棒自动语音识别问题。在这个挑战中，两个竞争的发言者同时说一个简单的命令，目标是识别目标发言者的语音。令人惊讶的是，在挑战过程中，来自IBM研究的一个团队在这项任务上的表现比人类听众更好。IBM团队提出的方法，包括一个中间的语音分离，然后是一个单一的说话者语音识别。本文重新考虑这一挑战的基础上增益自适应阶乘语音处理模型的任务。它开发了一个联合令牌传递算法的直接话语解码的目标和掩蔽扬声器，同时。与挑战获胜者相比，它在解码过程中使用了过去两阶段方法中无法使用的最大不确定性。基于概率图模型的一般推理过程，详细推导了这些模型的推理过程。作为另一个改进，它使用深度神经网络进行联合说话人辨识和增益估计，这使得这两个步骤比之前更容易为这些步骤产生有竞争力的结果。这项工作提出的方法优于过去的超人结果，甚至是微软最近使用深度神经网络研究取得的结果。与第一个超级人类系统相比，它实现了5.5%的绝对任务性能提升，与最近的竞争对手相比，它实现了2.7%的绝对任务性能提升。
英文摘要：
A Pascal challenge entitled monaural multi-talker speech recognition was developed, targeting the problem of robust automatic speech recognition against speech like noises which significantly degrades the performance of automatic speech recognition systems. In this challenge, two competing speakers say a simple command simultaneously and the objective is to recognize speech of the target speaker. Surprisingly during the challenge, a team from IBM research, could achieve a performance better than human listeners on this task. The proposed method of the IBM team, consist of an intermediate speech separation and then a single-talker speech recognition. This paper reconsiders the task of this challenge based on gain adapted factorial speech processing models. It develops a joint-token passing algorithm for direct utterance decoding of both target and masker speakers, simultaneously. Comparing it to the challenge winner, it uses maximum uncertainty during the decoding which cannot be used in the past two-phased method. It provides detailed derivation of inference on these models based on general inference procedures of probabilistic graphical models. As another improvement, it uses deep neural networks for joint-speaker identification and gain estimation which makes these two steps easier than before producing competitive results for these steps. The proposed method of this work outperforms past super-human results and even the results were achieved recently by Microsoft research, using deep neural networks. It achieved 5.5% absolute task performance improvement compared to the first super-human system and 2.7% absolute task performance improvement compared to its recent competitor.
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。
